1
|
Nowroozi A, Salehi MA, Shobeiri P, Agahi S, Momtazmanesh S, Kaviani P, Kalra MK. Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis. Clin Radiol 2024:S0009-9260(24)00200-9. [PMID: 38772766 DOI: 10.1016/j.crad.2024.04.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Revised: 04/09/2024] [Accepted: 04/15/2024] [Indexed: 05/23/2024]
Abstract
PURPOSE Fracture detection is one of the most commonly used and studied aspects of artificial intelligence (AI) in medicine. In this systematic review and meta-analysis, we aimed to summarize available literature and data regarding AI performance in fracture detection on plain radiographs and various factors affecting it. METHODS We systematically reviewed studies evaluating AI algorithms in detecting bone fractures in plain radiographs, combined their performance using meta-analysis (a bivariate regression approach), and compared it with that of clinicians. We also analyzed the factors potentially affecting algorithm performance using meta-regression. RESULTS Our analysis included 100 studies. In 83 studies with confusion matrices, AI algorithms showed a sensitivity of 91.43% and a specificity of 92.12% (Area under the summary receiver operator curve = 0.968). After adjustment and false discovery rate correction, tibia/fibula (excluding ankle) fractures were associated with higher (7.0%, p=0.004) AI sensitivity, while more recent publications (5.5%, p=0.003) and Xception architecture (6.6%, p<0.001) were associated with higher specificity. Clinicians and AI showed similar specificity in fracture identification, although AI leaned to higher sensitivity (7.6%, p=0.07). Radiologists, on the other hand, were more specific than AI overall and in several subgroups, and more sensitive to hip fractures before FDR correction. CONCLUSIONS Currently available AI aids could result in a significant improvement in care where radiologists are not readily available. Moreover, identifying factors affecting algorithm performance could guide AI development teams in their process of optimizing their products.
Collapse
Affiliation(s)
- A Nowroozi
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - M A Salehi
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - P Shobeiri
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - S Agahi
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - S Momtazmanesh
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - P Kaviani
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA
| | - M K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA.
| |
Collapse
|
2
|
Haag F, Hokamp NG, Overhoff D, Dasegowda G, Kuru M, Nörenberg D, Schoenberg SO, Kalra MK, Froelich MF. Potential of photon counting computed tomography derived spectral reconstructions to reduce beam-hardening artifacts in chest CT. Eur J Radiol 2024; 175:111448. [PMID: 38574510 DOI: 10.1016/j.ejrad.2024.111448] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Revised: 02/02/2024] [Accepted: 03/25/2024] [Indexed: 04/06/2024]
Abstract
PURPOSE Aim of the recent study is to point out a method to optimize quality of CT scans in oncological patients with port systems. This study investigates the potential of photon counting computed tomography (PCCT) for reduction of beam hardening artifacts caused by port-implants in chest imaging by means of spectral reconstructions. METHOD In this retrospective single-center study, 8 ROIs for 19 spectral reconstructions (polyenergetic imaging, monoenergetic reconstructions from 40 to 190 keV as well as iodine maps and virtual non contrast (VNC)) of 49 patients with pectoral port systems undergoing PCCT of the chest for staging of oncologic disease were measured. Mean values and standard deviation (SD) Hounsfield unit measurements of port-chamber associated hypo- and hyperdense artifacts, bilateral muscles and vessels has been carried out. Also, a structured assessment of artifacts and imaging findings was performed by two radiologists. RESULTS A significant association of keV with iodine contrast as well as artifact intensity was noted (all p < 0.001). In qualitative assessment, utilization of 120 keV monoenergetic reconstructions could reduce severe and pronounced artifacts completely, as compared to lower keV reconstructions (p < 0.001). Regarding imaging findings, no significant difference between monoenergetic reconstructions was noted (all p > 0.05). In cases with very high iodine concentrations in the subclavian vein, image distortions were noted at 40 keV images (p < 0.01). CONCLUSIONS The present study demonstrates that PCCT derived spectral reconstructions can be used in oncological imaging of the thorax to reduce port-derived beam-hardening artefacts. When evaluating image data sets within a staging, it can be particularly helpful to consider the 120 keV VMIs, in which the artefacts are comparatively low.
Collapse
Affiliation(s)
- Florian Haag
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany
| | - Nils Große Hokamp
- Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Germany
| | - Daniel Overhoff
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany; Bundeswehrzentralkrankenhaus, Koblenz, Germany
| | - Giridhar Dasegowda
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Mustafa Kuru
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany
| | - Dominik Nörenberg
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany
| | - Stefan O Schoenberg
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Matthias F Froelich
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
3
|
Singh J, Khanna NN, Rout RK, Singh N, Laird JR, Singh IM, Kalra MK, Mantella LE, Johri AM, Isenovic ER, Fouda MM, Saba L, Fatemi M, Suri JS. GeneAI 3.0: powerful, novel, generalized hybrid and ensemble deep learning frameworks for miRNA species classification of stationary patterns from nucleotides. Sci Rep 2024; 14:7154. [PMID: 38531923 DOI: 10.1038/s41598-024-56786-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Accepted: 03/11/2024] [Indexed: 03/28/2024] Open
Abstract
Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present AtheroPoint's GeneAI 3.0, a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a composite feature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of 5 EML and 6 EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11 + 27 = 38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL > HDL > SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences.
Collapse
Affiliation(s)
- Jaskaran Singh
- Department of Computer Science, Graphic Era Deemed to be University, Dehradun, Uttarakhand, India
| | - Narendra N Khanna
- Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi, India
| | - Ranjeet K Rout
- Department of Computer Science and Engineering, NIT Srinagar, Hazratbal, Srinagar, India
| | - Narpinder Singh
- Department of Food Science, Graphic Era Deemed to be University, Dehradun, Uttarakhand, India
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St Helena, CA, USA
| | - Inder M Singh
- Advanced Cardiac and Vascular Institute, Sacramento, CA, USA
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA, 02115, USA
| | - Laura E Mantella
- Department of Biomedical and Molecular Sciences, Queen's University, Kingston, ON, Canada
| | - Amer M Johri
- Department of Biomedical and Molecular Sciences, Queen's University, Kingston, ON, Canada
| | - Esma R Isenovic
- Laboratory for Molecular Genetics and Radiobiology, University of Belgrade, Belgrade, Serbia
| | - Mostafa M Fouda
- Department of Electrical and Computer Engineering, Idaho State University, Pocatello, ID, 83209, USA
| | - Luca Saba
- Department of Neurology, University of Cagliari, Cagliari, Italy
| | - Mostafa Fatemi
- Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, 55905, USA
| | - Jasjit S Suri
- Stroke Monitoring and Diagnostic Division, AtheroPoint LLC, Roseville, CA, 95661, USA.
| |
Collapse
|
4
|
Cadavid L, Karout L, Kalra MK, Morgado F, Londoño MA, Pérez L, Galeano M, Montaño M, Wesley L, Almanza J, Pacheco W, Gómez L, Moscatelli A, Muglia V, Kiipper F, Lucena R, Bernardo M, Ugas C. Setting up regional diagnostic reference levels for pediatric computed tomography in Latin America: preliminary results, challenges and the work ahead. Pediatr Radiol 2024; 54:457-467. [PMID: 37227466 DOI: 10.1007/s00247-023-05676-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Revised: 04/11/2023] [Accepted: 04/12/2023] [Indexed: 05/26/2023]
Abstract
We established a framework for collecting radiation doses for head, chest and abdomen-pelvis computed tomography (CT) in children scanned at multiple imaging sites across Latin America with an aim towards establishing diagnostic reference levels (DRLs) and achievable doses (ADs) in pediatric CT in Latin America. Our study included 12 Latin American sites (in Argentina, Bolivia, Brazil, Chile, Colombia, Ecuador, Honduras and Panama) contributing data on the four most common pediatric CT examinations (non-contrast head, non-contrast chest, post-contrast chest and post-contrast abdomen-pelvis). Sites contributed data on patients' age, sex and weight, scan factors (tube current and potential), volume CT dose index (CTDIvol) and dose length product (DLP). Data were verified, leading to the exclusion of two sites with missing or incorrect data entries. We estimated overall and site-specific 50th (AD) and 75th (diagnostic reference level [DRL]) percentile CTDIvol and DLP for each CT protocol. Non-normal data were compared using the Kruskal-Wallis test. Sites contributed data from 3,934 children (1,834 females) for different CT exams (head CT 1,568/3,934, 40%; non-contrast chest CT 945/3,934, 24%; post-contrast chest CT 581/3,934, 15%; abdomen-pelvis CT 840/3,934, 21%). There were significant statistical differences in 50th and 75th percentile CTDIvol and DLP values across the participating sites (P<0.001). The 50th and 75th percentile doses for most CT protocols were substantially higher than the corresponding doses reported from the United States of America. Our study demonstrates substantial disparities and variations in pediatric CT examinations performed in multiple sites in Latin America. We will use the collected data to improve scan protocols and perform a follow-up CT study to establish DRLs and ADs based on clinical indications.
Collapse
Affiliation(s)
- Lina Cadavid
- Department of Radiology, Hospital Pablo Tobón Uribe, Calle 78B#69-240, Medellín, Antioquia, 050034, Colombia.
| | - Lina Karout
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Flavio Morgado
- Pontificie Universidade Católica de São Paulo, São Paulo, Brazil
| | - María Antonieta Londoño
- Universidad Nacional de Colombia/Fundación Hospital Pediátrico La Misericordia, Bogotá, Colombia
| | - Lizbeth Pérez
- Department of Radiology, Clinica alemana de Santiago - Universidad del Desarrollo, Santiago de Chile, Chile
| | - Monica Galeano
- Department of Radiology, Hospital del Niño Prof Dr. Ramón Exeni, La Matanza provincia de Buenos Aires, Argentina
| | - Mario Montaño
- Department of Radiology, Hospital Santa Cruz C.P.S, Santa Cruz de la Sierra, Bolivia
| | - Lavinia Wesley
- Department of Radiology, Hospital del Niño Dr. José Renán Esquivel, Ciudad de Panamá, Panamá
| | - Judith Almanza
- Department of Radiology, Salud Digna., Ciudad de México, México
| | - Walter Pacheco
- Department of Radiology, Maria Hospital, Pediatric Specialties, Tegucigalpa, Honduras
| | - Lucia Gómez
- Department of Radiology, Hospital Metropolitano, Quito, Ecuador
| | | | - Valdair Muglia
- Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo, Ribeirão Preto, Brazil
| | | | | | - Monica Bernardo
- Pontifícia Universidade Católica de São Paulo, Hospital Miguel Soeiro, Sorocaba, Brazil
| | - Carlos Ugas
- Department of Diagnostic Imaging, Instituto Nacional de Salud del Niño San Borja, Lima, Perú
| |
Collapse
|
5
|
Merit VT, Kirk ME, Schultz JG, Hansen JV, Lyhne MD, Kramer AD, Pedersen CCE, Karout L, Kalra MK, Andersen A, Nielsen-Kudsk JE. Changes in Pulmonary Vascular Resistance and Obstruction Score Following Acute Pulmonary Embolism in Pigs. Crit Care Explor 2024; 6:e1040. [PMID: 38511125 PMCID: PMC10954062 DOI: 10.1097/cce.0000000000001040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/22/2024] Open
Abstract
OBJECTIVES To investigate the contribution of mechanical obstruction and pulmonary vasoconstriction to pulmonary vascular resistance (PVR) in acute pulmonary embolism (PE) in pigs. DESIGN Controlled, animal study. SETTING Tertiary university hospital, animal research laboratory. SUBJECTS Female Danish slaughter pigs (n = 12, ~60 kg). INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS PE was induced by infusion of autologous blood clots in pigs. CT pulmonary angiograms were performed at baseline, after PE (first experimental day [PEd0]) and the following 2 days (second experimental day [PEd1] and third experimental day [PEd2]), and clot burden quantified by a modified Qanadli Obstruction Score. Hemodynamics were evaluated with left and right heart catheterization and systemic invasive pressures each day before, under, and after treatment with the pulmonary vasodilators sildenafil (0.1 mg/kg) and oxygen (Fio2 40%). PE increased PVR (baseline vs. PEd0: 178 ± 54 vs. 526 ± 160 dynes; p < 0.0001) and obstruction score (baseline vs. PEd0: 0% vs. 45% ± 13%; p < 0.0001). PVR decreased toward baseline at day 1 (baseline vs. PEd1: 178 ± 54 vs. 219 ± 48; p = 0.16) and day 2 (baseline vs. PEd2: 178 ± 54 vs. 201 ± 50; p = 0.51). Obstruction score decreased only slightly at day 1 (PEd0 vs. PEd1: 45% ± 12% vs. 43% ± 14%; p = 0.04) and remained elevated throughout the study (PEd1 vs. PEd2: 43% ± 14% vs. 42% ± 17%; p = 0.74). Sildenafil and oxygen in combination decreased PVR at day 0 (-284 ± 154 dynes; p = 0.0064) but had no effects at day 1 (-8 ± 27 dynes; p = 0.4827) or day 2 (-18 ± 32 dynes; p = 0.0923). CONCLUSIONS Pulmonary vasoconstriction, and not mechanical obstruction, was the predominant cause of increased PVR in acute PE in pigs. PVR rapidly declined over the first 2 days after onset despite a persistent mechanical obstruction of the pulmonary circulation from emboli. The findings suggest that treatment with pulmonary vasodilators might only be effective in the acute phase of PE thereby limiting the window for such therapy.
Collapse
Affiliation(s)
- Victor T Merit
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
| | - Mathilde E Kirk
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
| | - Jacob G Schultz
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
| | - Jacob V Hansen
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
| | - Mads D Lyhne
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
- Department of Anesthesia and Intensive Care, Aarhus University Hospital, Aarhus N, Denmark
| | - Anders D Kramer
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
| | | | - Lina Karout
- Department of Radiology, Massachusetts General Hospital, Boston, MA
| | | | - Asger Andersen
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
| | - Jens Erik Nielsen-Kudsk
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
- Department of Clinical Medicine, Aarhus University Hospital, Aarhus N, Denmark
| |
Collapse
|
6
|
Zhang J, Chao H, Dasegowda G, Wang G, Kalra MK, Yan P. Revisiting the Trustworthiness of Saliency Methods in Radiology AI. Radiol Artif Intell 2024; 6:e220221. [PMID: 38166328 PMCID: PMC10831523 DOI: 10.1148/ryai.220221] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Revised: 10/04/2023] [Accepted: 10/23/2023] [Indexed: 01/04/2024]
Abstract
Purpose To determine whether saliency maps in radiology artificial intelligence (AI) are vulnerable to subtle perturbations of the input, which could lead to misleading interpretations, using prediction-saliency correlation (PSC) for evaluating the sensitivity and robustness of saliency methods. Materials and Methods In this retrospective study, locally trained deep learning models and a research prototype provided by a commercial vendor were systematically evaluated on 191 229 chest radiographs from the CheXpert dataset and 7022 MR images from a human brain tumor classification dataset. Two radiologists performed a reader study on 270 chest radiograph pairs. A model-agnostic approach for computing the PSC coefficient was used to evaluate the sensitivity and robustness of seven commonly used saliency methods. Results The saliency methods had low sensitivity (maximum PSC, 0.25; 95% CI: 0.12, 0.38) and weak robustness (maximum PSC, 0.12; 95% CI: 0.0, 0.25) on the CheXpert dataset, as demonstrated by leveraging locally trained model parameters. Further evaluation showed that the saliency maps generated from a commercial prototype could be irrelevant to the model output, without knowledge of the model specifics (area under the receiver operating characteristic curve decreased by 8.6% without affecting the saliency map). The human observer studies confirmed that it is difficult for experts to identify the perturbed images; the experts had less than 44.8% correctness. Conclusion Popular saliency methods scored low PSC values on the two datasets of perturbed chest radiographs, indicating weak sensitivity and robustness. The proposed PSC metric provides a valuable quantification tool for validating the trustworthiness of medical AI explainability. Keywords: Saliency Maps, AI Trustworthiness, Dynamic Consistency, Sensitivity, Robustness Supplemental material is available for this article. © RSNA, 2023 See also the commentary by Yanagawa and Sato in this issue.
Collapse
Affiliation(s)
- Jiajin Zhang
- From the Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, 110 8th St, Biotech 4231, Troy, NY 12180 (J.Z., H.C., G.W., P.Y.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (G.D., M.K.K.)
| | - Hanqing Chao
- From the Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, 110 8th St, Biotech 4231, Troy, NY 12180 (J.Z., H.C., G.W., P.Y.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (G.D., M.K.K.)
| | - Giridhar Dasegowda
- From the Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, 110 8th St, Biotech 4231, Troy, NY 12180 (J.Z., H.C., G.W., P.Y.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (G.D., M.K.K.)
| | - Ge Wang
- From the Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, 110 8th St, Biotech 4231, Troy, NY 12180 (J.Z., H.C., G.W., P.Y.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (G.D., M.K.K.)
| | - Mannudeep K. Kalra
- From the Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, 110 8th St, Biotech 4231, Troy, NY 12180 (J.Z., H.C., G.W., P.Y.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (G.D., M.K.K.)
| | - Pingkun Yan
- From the Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, 110 8th St, Biotech 4231, Troy, NY 12180 (J.Z., H.C., G.W., P.Y.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (G.D., M.K.K.)
| |
Collapse
|
7
|
Karout L, Digumarthy SR, Savage C, Fahimi R, Garza-Frias E, Kaviani P, Dasegowda G, Kalra MK. Low Contrast Volume Protocol in Routine Chest CT Amid the Global Contrast Shortage: A Single Institution Experience. Acad Radiol 2023; 30:2913-2920. [PMID: 37164818 DOI: 10.1016/j.acra.2023.03.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Revised: 03/16/2023] [Accepted: 03/17/2023] [Indexed: 05/12/2023]
Abstract
OBJECTIVE To assess the effectiveness of low contrast volume (LCV) chest CT performed with multiple contrast agents on multivendor CT with varying scanning techniques. METHODS The study included 361 patients (65 ± 15 years; M: F 173:188) who underwent LCV chest CT on one of the six 64-256 detector-row CT scanners using single-energy (SECT) or dual-energy (DECT) modes. All patients were scanned with either a fixed-LCV (LCVf, n = 103) or weight-based LCV (LCVw, n = 258) protocol. Two thoracic radiologists independently assessed all LCV CT and patients' prior standard contrast volume (SCV, n = 263) chest CT for optimality of contrast enhancement in thoracic vasculature, cardiac chambers, and in pleuro-parenchymal and mediastinal abnormalities. CT attenuations were recorded in the main pulmonary trunk, ascending, and descending thoracic aorta. To assess the interobserver agreement, pulmonary arterial enhancement was divided into two groups: optimal or suboptimal. RESULTS There was no significant difference among patients' BMI (p = 0.883) in the three groups. DECT had a significantly higher aortic arterial enhancement (250 ± 99HU vs 228 ± 76 HU for SECT, p < 0.001). Optimal enhancement was present in 558 of 624 chest CT (89.4%), whereas 66 of 624 chest CT with suboptimal enhancement was noted in 48 of 258 LCVw (18.6%) and 14 of 103 LCVf (13.6%). Most patients with suboptimal enhancement with LCVw injection protocol were overweight/obese (30/48; 62.5%), (p < 0.001). CONCLUSION LCV chest CT can be performed across complex multivendor, multicontrast media, multiscanner, and multiprotocol CT practices. However, LCV chest CT examinations can result in suboptimal contrast enhancement in patients with larger body habitus.
Collapse
Affiliation(s)
- Lina Karout
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 75 Blossom Court, Boston, Massachusetts, 02114
| | - Subba R Digumarthy
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 75 Blossom Court, Boston, Massachusetts, 02114
| | - Cristy Savage
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Roshan Fahimi
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 75 Blossom Court, Boston, Massachusetts, 02114
| | - Emiliano Garza-Frias
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 75 Blossom Court, Boston, Massachusetts, 02114
| | - Parisa Kaviani
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 75 Blossom Court, Boston, Massachusetts, 02114
| | - Giridhar Dasegowda
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 75 Blossom Court, Boston, Massachusetts, 02114
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 75 Blossom Court, Boston, Massachusetts, 02114.
| |
Collapse
|
8
|
Dasegowda G, Bizzo BC, Gupta RV, Kaviani P, Ebrahimian S, Ricciardelli D, Abedi-Tari F, Neumark N, Digumarthy SR, Kalra MK, Dreyer KJ. Radiologist-Trained AI Model for Identifying Suboptimal Chest-Radiographs. Acad Radiol 2023; 30:2921-2930. [PMID: 37019698 DOI: 10.1016/j.acra.2023.03.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Revised: 02/28/2023] [Accepted: 03/06/2023] [Indexed: 04/05/2023]
Abstract
RATIONALE AND OBJECTIVES Suboptimal chest radiographs (CXR) can limit interpretation of critical findings. Radiologist-trained AI models were evaluated for differentiating suboptimal(sCXR) and optimal(oCXR) chest radiographs. MATERIALS AND METHODS Our IRB-approved study included 3278 CXRs from adult patients (mean age 55 ± 20 years) identified from a retrospective search of CXR in radiology reports from 5 sites. A chest radiologist reviewed all CXRs for the cause of suboptimality. The de-identified CXRs were uploaded into an AI server application for training and testing 5 AI models. The training set consisted of 2202 CXRs (n = 807 oCXR; n = 1395 sCXR) while 1076 CXRs (n = 729 sCXR; n = 347 oCXR) were used for testing. Data were analyzed with the Area under the curve (AUC) for the model's ability to classify oCXR and sCXR correctly. RESULTS For the two-class classification into sCXR or oCXR from all sites, for CXR with missing anatomy, AI had sensitivity, specificity, accuracy, and AUC of 78%, 95%, 91%, 0.87(95% CI 0.82-0.92), respectively. AI identified obscured thoracic anatomy with 91% sensitivity, 97% specificity, 95% accuracy, and 0.94 AUC (95% CI 0.90-0.97). Inadequate exposure with 90% sensitivity, 93% specificity, 92% accuracy, and AUC of 0.91 (95% CI 0.88-0.95). The presence of low lung volume was identified with 96% sensitivity, 92% specificity, 93% accuracy, and 0.94 AUC (95% CI 0.92-0.96). The sensitivity, specificity, accuracy, and AUC of AI in identifying patient rotation were 92%, 96%, 95%, and 0.94 (95% CI 0.91-0.98), respectively. CONCLUSION The radiologist-trained AI models can accurately classify optimal and suboptimal CXRs. Such AI models at the front end of radiographic equipment can enable radiographers to repeat sCXRs when necessary.
Collapse
Affiliation(s)
- Giridhar Dasegowda
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114
| | - Bernardo C Bizzo
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114
| | - Reya V Gupta
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114
| | - Parisa Kaviani
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114
| | - Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114
| | - Debra Ricciardelli
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114
| | - Faezeh Abedi-Tari
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114
| | - Nir Neumark
- Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114
| | - Subba R Digumarthy
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114.
| | - Keith J Dreyer
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114
| |
Collapse
|
9
|
Khanna NN, Singh M, Maindarkar M, Kumar A, Johri AM, Mentella L, Laird JR, Paraskevas KI, Ruzsa Z, Singh N, Kalra MK, Fernandes JFE, Chaturvedi S, Nicolaides A, Rathore V, Singh I, Teji JS, Al-Maini M, Isenovic ER, Viswanathan V, Khanna P, Fouda MM, Saba L, Suri JS. Polygenic Risk Score for Cardiovascular Diseases in Artificial Intelligence Paradigm: A Review. J Korean Med Sci 2023; 38:e395. [PMID: 38013648 PMCID: PMC10681845 DOI: 10.3346/jkms.2023.38.e395] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Accepted: 10/15/2023] [Indexed: 11/29/2023] Open
Abstract
Cardiovascular disease (CVD) related mortality and morbidity heavily strain society. The relationship between external risk factors and our genetics have not been well established. It is widely acknowledged that environmental influence and individual behaviours play a significant role in CVD vulnerability, leading to the development of polygenic risk scores (PRS). We employed the PRISMA search method to locate pertinent research and literature to extensively review artificial intelligence (AI)-based PRS models for CVD risk prediction. Furthermore, we analyzed and compared conventional vs. AI-based solutions for PRS. We summarized the recent advances in our understanding of the use of AI-based PRS for risk prediction of CVD. Our study proposes three hypotheses: i) Multiple genetic variations and risk factors can be incorporated into AI-based PRS to improve the accuracy of CVD risk predicting. ii) AI-based PRS for CVD circumvents the drawbacks of conventional PRS calculators by incorporating a larger variety of genetic and non-genetic components, allowing for more precise and individualised risk estimations. iii) Using AI approaches, it is possible to significantly reduce the dimensionality of huge genomic datasets, resulting in more accurate and effective disease risk prediction models. Our study highlighted that the AI-PRS model outperformed traditional PRS calculators in predicting CVD risk. Furthermore, using AI-based methods to calculate PRS may increase the precision of risk predictions for CVD and have significant ramifications for individualized prevention and treatment plans.
Collapse
Affiliation(s)
- Narendra N Khanna
- Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi, India
- Asia Pacific Vascular Society, New Delhi, India
| | - Manasvi Singh
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA
- Bennett University, Greater Noida, India
| | - Mahesh Maindarkar
- Asia Pacific Vascular Society, New Delhi, India
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA
- School of Bioengineering Sciences and Research, Maharashtra Institute of Technology's Art, Design and Technology University, Pune, India
| | | | - Amer M Johri
- Department of Medicine, Division of Cardiology, Queen's University, Kingston, Canada
| | - Laura Mentella
- Department of Medicine, Division of Cardiology, University of Toronto, Toronto, Canada
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA, USA
| | | | - Zoltan Ruzsa
- Invasive Cardiology Division, University of Szeged, Szeged, Hungary
| | - Narpinder Singh
- Department of Food Science and Technology, Graphic Era Deemed to be University, Dehradun, Uttarakhand, India
| | | | | | - Seemant Chaturvedi
- Department of Neurology & Stroke Program, University of Maryland, Baltimore, MD, USA
| | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre and University of Nicosia Medical School, Cyprus
| | - Vijay Rathore
- Nephrology Department, Kaiser Permanente, Sacramento, CA, USA
| | - Inder Singh
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA
| | - Jagjit S Teji
- Ann and Robert H. Lurie Children's Hospital of Chicago, Chicago, IL, USA
| | - Mostafa Al-Maini
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON, Canada
| | - Esma R Isenovic
- Department of Radiobiology and Molecular Genetics, National Institute of The Republic of Serbia, University of Belgrade, Beograd, Serbia
| | | | - Puneet Khanna
- Department of Anaesthesiology, AIIMS, New Delhi, India
| | - Mostafa M Fouda
- Department of Electrical and Computer Engineering, Idaho State University, Pocatello, ID, USA
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria, Cagliari, Italy
| | - Jasjit S Suri
- Asia Pacific Vascular Society, New Delhi, India
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA
- Department of Computer Engineering, Graphic Era Deemed to be University, Dehradun, India.
| |
Collapse
|
10
|
Dragsbaek SJ, Lyhne MD, Hansen JV, Pedersen CCE, Jujo-Sanada T, Karout L, Kalra MK, Nielsen-Kudsk JE, Andersen A. A porcine model of human-like chronic thromboembolic pulmonary disease. Thromb Res 2023; 231:25-28. [PMID: 37769413 DOI: 10.1016/j.thromres.2023.09.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2023] [Revised: 08/25/2023] [Accepted: 09/21/2023] [Indexed: 09/30/2023]
Affiliation(s)
- Simone J Dragsbaek
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.
| | - Mads D Lyhne
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Anesthesiology and Intensive Care, Aarhus University Hospital, Aarhus, Denmark.
| | - Jacob V Hansen
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.
| | | | - Takayuki Jujo-Sanada
- Department of Respirology, Graduate School of Medicine, Chiba, Japan; Laboratory of Vaccine Materials, National Institutes of Biomedical Innovation, Health and Nutrition, Osaka, Japan
| | - Lina Karout
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA.
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA.
| | - Jens E Nielsen-Kudsk
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.
| | - Asger Andersen
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark.
| |
Collapse
|
11
|
Sanga P, Singh J, Dubey AK, Khanna NN, Laird JR, Faa G, Singh IM, Tsoulfas G, Kalra MK, Teji JS, Al-Maini M, Rathore V, Agarwal V, Ahluwalia P, Fouda MM, Saba L, Suri JS. DermAI 1.0: A Robust, Generalized, and Novel Attention-Enabled Ensemble-Based Transfer Learning Paradigm for Multiclass Classification of Skin Lesion Images. Diagnostics (Basel) 2023; 13:3159. [PMID: 37835902 PMCID: PMC10573070 DOI: 10.3390/diagnostics13193159] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 09/03/2023] [Accepted: 10/04/2023] [Indexed: 10/15/2023] Open
Abstract
Skin lesion classification plays a crucial role in dermatology, aiding in the early detection, diagnosis, and management of life-threatening malignant lesions. However, standalone transfer learning (TL) models failed to deliver optimal performance. In this study, we present an attention-enabled ensemble-based deep learning technique, a powerful, novel, and generalized method for extracting features for the classification of skin lesions. This technique holds significant promise in enhancing diagnostic accuracy by using seven pre-trained TL models for classification. Six ensemble-based DL (EBDL) models were created using stacking, softmax voting, and weighted average techniques. Furthermore, we investigated the attention mechanism as an effective paradigm and created seven attention-enabled transfer learning (aeTL) models before branching out to construct three attention-enabled ensemble-based DL (aeEBDL) models to create a reliable, adaptive, and generalized paradigm. The mean accuracy of the TL models is 95.30%, and the use of an ensemble-based paradigm increased it by 4.22%, to 99.52%. The aeTL models' performance was superior to the TL models in accuracy by 3.01%, and aeEBDL models outperformed aeTL models by 1.29%. Statistical tests show significant p-value and Kappa coefficient along with a 99.6% reliability index for the aeEBDL models. The approach is highly effective and generalized for the classification of skin lesions.
Collapse
Affiliation(s)
- Prabhav Sanga
- Department of Information Technology, Bharati Vidyapeeth’s College of Engineering, New Delhi 110063, India; (P.S.); (A.K.D.)
- Global Biomedical Technologies, Inc., Roseville, CA 95661, USA
| | - Jaskaran Singh
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA (I.M.S.); (V.R.)
| | - Arun Kumar Dubey
- Department of Information Technology, Bharati Vidyapeeth’s College of Engineering, New Delhi 110063, India; (P.S.); (A.K.D.)
| | - Narendra N. Khanna
- Department of Cardiology, Indraprastha Apollo Hospitals, New Delhi 110076, India;
| | - John R. Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA 94574, USA;
| | - Gavino Faa
- Department of Pathology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy;
| | - Inder M. Singh
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA (I.M.S.); (V.R.)
| | - Georgios Tsoulfas
- Department of Surgery, Aristoteleion University of Thessaloniki, 54124 Thessaloniki, Greece;
| | - Mannudeep K. Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, USA;
| | - Jagjit S. Teji
- Department of Pediatrics, Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL 60611, USA;
| | - Mustafa Al-Maini
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON L4Z 4C4, Canada;
| | - Vijay Rathore
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA (I.M.S.); (V.R.)
| | - Vikas Agarwal
- Department of Immunology, Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow 226014, India;
| | - Puneet Ahluwalia
- Department of Uro Oncology, Medanta the Medicity, Gurugram 122001, India;
| | - Mostafa M. Fouda
- Department of Electrical and Computer Engineering, Idaho State University, Pocatello, ID 83209, USA;
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy;
| | - Jasjit S. Suri
- Global Biomedical Technologies, Inc., Roseville, CA 95661, USA
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA (I.M.S.); (V.R.)
- Department of Electrical and Computer Engineering, Idaho State University, Pocatello, ID 83209, USA;
- Department of Computer Science and Engineering, Graphic Era University (G.E.U.), Dehradun 248002, India
| |
Collapse
|
12
|
Lyhne MD, Giordano N, Dudzinski D, Torrey J, Wang G, Zheng H, Parry BA, Kalra MK, Kabrhel C. Authors' reply. Emerg Radiol 2023:10.1007/s10140-023-02145-6. [PMID: 37301788 DOI: 10.1007/s10140-023-02145-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2023] [Accepted: 05/17/2023] [Indexed: 06/12/2023]
Affiliation(s)
- Mads Dam Lyhne
- Department of Emergency Medicine, Massachusetts General Hospital, 0 Emerson Place, Suite 3B, Boston, MA, 02114, USA
- Department of Anesthesiology and Intensive Care, Aarhus University Hospital, Aarhus, Denmark
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark
| | - Nicholas Giordano
- Department of Emergency Medicine, Massachusetts General Hospital, 0 Emerson Place, Suite 3B, Boston, MA, 02114, USA
| | - David Dudzinski
- Department of Cardiology, Massachusetts General Hospital, Boston, MA, USA
| | - Jasmine Torrey
- Department of Emergency Medicine, Massachusetts General Hospital, 0 Emerson Place, Suite 3B, Boston, MA, 02114, USA
| | - Grace Wang
- Department of Emergency Medicine, Massachusetts General Hospital, 0 Emerson Place, Suite 3B, Boston, MA, 02114, USA
| | - Hui Zheng
- Department of Biostatistics, Massachusetts General Hospital, Boston, MA, USA
| | - Blair Alden Parry
- Department of Emergency Medicine, Massachusetts General Hospital, 0 Emerson Place, Suite 3B, Boston, MA, 02114, USA
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Christopher Kabrhel
- Department of Emergency Medicine, Massachusetts General Hospital, 0 Emerson Place, Suite 3B, Boston, MA, 02114, USA.
| |
Collapse
|
13
|
Dubey AK, Chabert GL, Carriero A, Pasche A, Danna PSC, Agarwal S, Mohanty L, Sharma N, Yadav S, Jain A, Kumar A, Kalra MK, Sobel DW, Laird JR, Singh IM, Singh N, Tsoulfas G, Fouda MM, Alizad A, Kitas GD, Khanna NN, Viskovic K, Kukuljan M, Al-Maini M, El-Baz A, Saba L, Suri JS. Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework. Diagnostics (Basel) 2023; 13:diagnostics13111954. [PMID: 37296806 DOI: 10.3390/diagnostics13111954] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 05/22/2023] [Accepted: 05/29/2023] [Indexed: 06/12/2023] Open
Abstract
BACKGROUND AND MOTIVATION Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. METHODOLOGY The system consists of a cascade of quality control, ResNet-UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL's. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts-Croatia (80 COVID) and Italy (72 COVID and 30 controls)-leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. RESULTS Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. CONCLUSION EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.
Collapse
Affiliation(s)
- Arun Kumar Dubey
- Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India
| | - Gian Luca Chabert
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy
| | - Alessandro Carriero
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy
| | - Alessio Pasche
- Department of Radiology, "Maggiore della Carità" Hospital, University of Piemonte Orientale, Via Solaroli 17, 28100 Novara, Italy
| | - Pietro S C Danna
- Department of Radiology, "Maggiore della Carità" Hospital, University of Piemonte Orientale, Via Solaroli 17, 28100 Novara, Italy
| | - Sushant Agarwal
- Advanced Knowledge Engineering Centre, GBTI, Roseville, CA 95661, USA
| | - Lopamudra Mohanty
- ABES Engineering College, Ghaziabad 201009, India
- Department of Computer Science Engineering, Bennett University, Greater Noida 201310, India
| | - Neeraj Sharma
- School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi 221005, India
| | - Sarita Yadav
- Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India
| | - Achin Jain
- Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India
| | - Ashish Kumar
- Department of Computer Science Engineering, Bennett University, Greater Noida 201310, India
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02115, USA
| | - David W Sobel
- Men's Health Centre, Miriam Hospital Providence, Providence, RI 02906, USA
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA 94574, USA
| | - Inder M Singh
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA
| | - Narpinder Singh
- Department of Food Science and Technology, Graphic Era, Deemed to be University, Dehradun 248002, India
| | - George Tsoulfas
- Department of Surgery, Aristoteleion University of Thessaloniki, 54124 Thessaloniki, Greece
| | - Mostafa M Fouda
- Department of Electrical and Computer Engineering, Idaho State University, Pocatello, ID 83209, USA
| | - Azra Alizad
- Department of Physiology & Biomedical Engineering, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA
| | - George D Kitas
- Academic Affairs, Dudley Group NHS Foundation Trust, Dudley DY1 2HQ, UK
| | - Narendra N Khanna
- Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi 110001, India
| | - Klaudija Viskovic
- Department of Radiology and Ultrasound, University Hospital for Infectious Diseases, 10000 Zagreb, Croatia
| | - Melita Kukuljan
- Department of Interventional and Diagnostic Radiology, Clinical Hospital Center Rijeka, 51000 Rijeka, Croatia
| | - Mustafa Al-Maini
- Allergy, Clinical Immunology & Rheumatology Institute, Toronto, ON L4Z 4C4, Canada
| | - Ayman El-Baz
- Biomedical Engineering Department, University of Louisville, Louisville, KY 40292, USA
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09123 Cagliari, Italy
| | - Jasjit S Suri
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA
| |
Collapse
|
14
|
Lyhne MD, Giordano N, Dudzinski D, Torrey J, Wang G, Zheng H, Parry BA, Kalra MK, Kabrhel C. Low concordance between CTPA and echocardiography in identification of right ventricular strain in PERT patients with acute pulmonary embolism. Emerg Radiol 2023; 30:325-331. [PMID: 37084161 DOI: 10.1007/s10140-023-02130-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Accepted: 03/29/2023] [Indexed: 04/22/2023]
Abstract
PURPOSE Right ventricular strain (RVS) is used to risk stratify patients with acute pulmonary embolism (PE) and influence treatment decisions. Guidelines suggest that either computed tomography pulmonary angiography (CTPA) or transthoracic echocardiography (TTE) can be used to assess RVS. We sought to determine how often CTPA and TTE yield discordant results and to assess the test characteristics of CTPA compared to TTE. METHODS We analyzed data from a single-center registry of PE cases severe enough to warrant activation of the hospital's Pulmonary Embolism Response Team (PERT). We defined RVS as a right ventricular to left ventricular ratio (RV/LV) ≥ 1 or radiologist's interpretation of RVS on CTPA or as the presence of either RV dilation, hypokinesis, or septal bowing on TTE. RESULTS We included 554 patients in our analysis, of whom 333 (60%) had concordant RVS findings on CTPA and TTE. Using TTE as the reference standard, CTPA had a sensitivity of 95% (95% CI 92-97%) and a specificity of 4% (95% CI 2-8%) for identifying RVS. CONCLUSIONS In a selected population of patients with acute PE for which PERT was activated, CTPA is highly sensitive but not specific for the detection of RVS when compared to TTE.
Collapse
Affiliation(s)
- Mads Dam Lyhne
- Center for Vascular Emergencies, Department of Emergency Medicine, Massachusetts General Hospital, Boston, MA, USA
- Department of Anesthesiology and Intensive Care, Aarhus University Hospital, Aarhus, Denmark & Department of Clinical Medicine, Aarhus University, Aarhus, Denmark
| | - Nicholas Giordano
- Center for Vascular Emergencies, Department of Emergency Medicine, Massachusetts General Hospital, Boston, MA, USA
| | - David Dudzinski
- Department of Cardiology, Massachusetts General Hospital, Boston, MA, USA
| | - Jasmine Torrey
- Center for Vascular Emergencies, Department of Emergency Medicine, Massachusetts General Hospital, Boston, MA, USA
| | - Grace Wang
- Center for Vascular Emergencies, Department of Emergency Medicine, Massachusetts General Hospital, Boston, MA, USA
| | - Hui Zheng
- Biostatistics Center, Massachusetts General Hospital, Boston, MA, USA
| | - Blair Alden Parry
- Center for Vascular Emergencies, Department of Emergency Medicine, Massachusetts General Hospital, Boston, MA, USA
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Christopher Kabrhel
- Center for Vascular Emergencies, Department of Emergency Medicine, Massachusetts General Hospital, Boston, MA, USA.
| |
Collapse
|
15
|
Xin Y, Kim T, Winkler T, Brix G, Gaulton T, Gerard SE, Herrmann J, Martin KT, Victor M, Reutlinger K, Amato M, Berra L, Kalra MK, Cereda M. Improving Pulmonary Perfusion Assessment by Dynamic Contrast-Enhanced Computed Tomography in an Experimental Lung Injury Model. J Appl Physiol (1985) 2023; 134:1496-1507. [PMID: 37167261 DOI: 10.1152/japplphysiol.00159.2023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/13/2023] Open
Abstract
Introduction: Pulmonary perfusion has been poorly characterized in acute respiratory distress syndrome(ARDS). Optimizing protocols to measure pulmonary blood flow(PBF) via dynamic contrast-enhanced(DCE) computed tomography(CT) could improve understanding of how ARDS alters pulmonary perfusion. In this study, comparative evaluations of injection protocols and tracer-kinetic analysis models were performed based on DCE-CT data measured in ventilated pigs with and without lung injury. Materials and Methods: 10 Yorkshire pigs were anesthetized, intubated, and mechanically ventilated; lung injury was induced by bronchial hydrochloric acid instillation. Each DCE-CT scan was obtained during 30-second end-expiratory breath-hold. Reproducibility of PBF measurements was evaluated in 3 pigs. In 8 pigs, undiluted and diluted Isovue-370 were separately injected to evaluate the effect of contrast viscosity on estimated PBF values. PBF was estimated with the peak-enhancement and the steepest-slope approach. Total-lung PBF was estimated in 2 healthy pigs to compare with cardiac output measured invasively by thermodilution in the pulmonary artery. Results: Repeated measurements in the same animals yielded a good reproducibility of computed PBF maps. Injecting diluted isovue-370 resulted in smaller contrast-time curves in the pulmonary artery(p<0.01) and vein(p<0.01) without substantially diminishing peak signal intensity(p=0.46 in the pulmonary artery) compared to the pure contrast agent since its viscosity is closer to that of blood. As compared to the peak-enhancement model, PBF values estimated by the steepest-slope model with diluted contrast were much closer to the cardiac output(R2=0.82) as compared to the peak-enhancement model. Conclusion: DCE-CT using the steepest-slope model and diluted contrast agent provided reliable quantitative estimates of PBF.
Collapse
Affiliation(s)
- Yi Xin
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, United States
- Department of Anesthesia, Critical Care and Pain Medicine, Harvard Medical School, Boston, MA, United States
| | - Taehwan Kim
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, United States
| | - Tilo Winkler
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, United States
- Department of Anesthesia, Critical Care and Pain Medicine, Harvard Medical School, Boston, MA, United States
| | - Gunnar Brix
- Department of Medical and Occupational Radiation Protection, Federal Office for Radiation Protection, Germany
| | - Timothy Gaulton
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, United States
- Department of Anesthesia, Critical Care and Pain Medicine, Harvard Medical School, Boston, MA, United States
| | - Sarah E Gerard
- Roy J. Carver Department of Biomedical Engineering, University of Iowa, Iowa City, IA, United States
| | - Jacob Herrmann
- Roy J. Carver Department of Biomedical Engineering, University of Iowa, Iowa City, IA, United States
| | - Kevin T Martin
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, United States
| | - Marcus Victor
- Disciplina de Pneumologia, Instituto do Coração, Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil
- Electronics Engineering Division, Aeronautics Institute of Technology, Sao Paulo, Brazil
| | - Kristan Reutlinger
- Department of Anesthesiology and Critical Care, University of Pennsylvania, Philadelphia, PA, United States
| | - Marcelo Amato
- Disciplina de Pneumologia, Instituto do Coração, Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil
| | - Lorenzo Berra
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, United States
- Department of Anesthesia, Critical Care and Pain Medicine, Harvard Medical School, Boston, MA, United States
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA, United States
- Department of Radiology, Harvard Medical School, Boston, MA, United States
| | - Maurizio Cereda
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, United States
- Department of Anesthesia, Critical Care and Pain Medicine, Harvard Medical School, Boston, MA, United States
| |
Collapse
|
16
|
Bizzo BC, Dasegowda G, Bridge C, Miller B, Hillis JM, Kalra MK, Durniak K, Stout M, Schultz T, Alkasab T, Dreyer KJ. Addressing the Challenges of Implementing Artificial Intelligence Tools in Clinical Practice: Principles From Experience. J Am Coll Radiol 2023; 20:352-360. [PMID: 36922109 DOI: 10.1016/j.jacr.2023.01.002] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2022] [Revised: 01/19/2023] [Accepted: 01/24/2023] [Indexed: 03/14/2023]
Abstract
The multitude of artificial intelligence (AI)-based solutions, vendors, and platforms poses a challenging proposition to an already complex clinical radiology practice. Apart from assessing and ensuring acceptable local performance and workflow fit to improve imaging services, AI tools require multiple stakeholders, including clinical, technical, and financial, who collaborate to move potential deployable applications to full clinical deployment in a structured and efficient manner. Postdeployment monitoring and surveillance of such tools require an infrastructure that ensures proper and safe use. Herein, the authors describe their experience and framework for implementing and supporting the use of AI applications in radiology workflow.
Collapse
Affiliation(s)
- Bernardo C Bizzo
- Senior Director, Data Science Office, Mass General Brigham, Boston, Massachusetts; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts.
| | - Giridhar Dasegowda
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Christopher Bridge
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Benjamin Miller
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - James M Hillis
- Data Science Office, Mass General Brigham, Boston, Massachusetts; Director of Clinical Operations, Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Director, Webster Center for Quality and Safety, Massachusetts General Hospital, Boston, Massachusetts
| | - Kimberly Durniak
- Senior Director, Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Markus Stout
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Senior Director, Medical Imaging Informatics, Mass General Brigham, Boston, Massachusetts
| | - Thomas Schultz
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Senior Director, Enterprise Medical Imaging, Mass General Brigham, Boston, Massachusetts
| | - Tarik Alkasab
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Associate Chair for Enterprise IT/Informatics, Massachusetts General Hospital, Boston, Massachusetts; Co-Medical Director, Medical Imaging Informatics, Mass General Brigham, Boston, Massachusetts
| | - Keith J Dreyer
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Chief Data Science Officer and Chief Imaging Information Officer, Mass General Brigham, Boston, Massachusetts; Vice Chair of Radiology, Massachusetts General Hospital, Boston, Massachusetts; Chief Science Officer, Data Science Institute, American College of Radiology, Reston, Virginia
| |
Collapse
|
17
|
Ebrahimian S, Digumarthy SR, Bizzo BC, Dreyer KJ, Kalra MK. Automatic segmentation and measurement of tracheal collapsibility in tracheomalacia. Clin Imaging 2023; 95:47-51. [PMID: 36610270 DOI: 10.1016/j.clinimag.2022.11.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2022] [Revised: 11/15/2022] [Accepted: 11/28/2022] [Indexed: 12/12/2022]
Abstract
PURPOSE To assess feasibility of automated segmentation and measurement of tracheal collapsibility for detecting tracheomalacia on inspiratory and expiratory chest CT images. METHODS Our study included 123 patients (age 67 ± 11 years; female: male 69:54) who underwent clinically indicated chest CT examinations in both inspiration and expiration phases. A thoracic radiologist measured anteroposterior length of trachea in inspiration and expiration phase image at the level of maximum collapsibility or aortic arch (in absence of luminal change). Separately, another investigator separately processed the inspiratory and expiratory DICOM CT images with Airway Segmentation component of a commercial COPD software (IntelliSpace Portal, Philips Healthcare). Upon segmentation, the software automatically estimated average lumen diameter (in mm) and lumen area (sq.mm) both along the entire length of trachea and at the level of aortic arch. Data were analyzed with independent t-tests and area under the receiver operating characteristic curve (AUC). RESULTS Of the 123 patients, 48 patients had tracheomalacia and 75 patients did not. Ratios of inspiration to expiration phases average lumen area and lumen diameter from the length of trachea had the highest AUC of 0.93 (95% CI = 0.88-0.97) for differentiating presence and absence of tracheomalacia. A decrease of ≥25% in average lumen diameter had sensitivity of 82% and specificity of 87% for detecting tracheomalacia. A decrease of ≥40% in the average lumen area had sensitivity and specificity of 86% for detecting tracheomalacia. CONCLUSION Automatic segmentation and measurement of tracheal dimension over the entire tracheal length is more accurate than a single-level measurement for detecting tracheomalacia.
Collapse
Affiliation(s)
- Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Suite 248, Boston, MA 02114, USA; Harvard Medical School, Boston, MA, USA.
| | - Subba R Digumarthy
- Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Suite 248, Boston, MA 02114, USA; Harvard Medical School, Boston, MA, USA.
| | - Bernardo C Bizzo
- Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Suite 248, Boston, MA 02114, USA; Harvard Medical School, Boston, MA, USA; MGH & BWH Center for Clinical Data Science, Boston, USA.
| | - Keith J Dreyer
- Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Suite 248, Boston, MA 02114, USA; Harvard Medical School, Boston, MA, USA; MGH & BWH Center for Clinical Data Science, Boston, USA.
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Suite 248, Boston, MA 02114, USA; Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
18
|
Dasegowda G, Bizzo BC, Kaviani P, Karout L, Ebrahimian S, Digumarthy SR, Neumark N, Hillis JM, Kalra MK, Dreyer KJ. Auto-Detection of Motion Artifacts on CT Pulmonary Angiograms with a Physician-Trained AI Algorithm. Diagnostics (Basel) 2023; 13:778. [PMID: 36832266 PMCID: PMC9955317 DOI: 10.3390/diagnostics13040778] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Revised: 02/02/2023] [Accepted: 02/16/2023] [Indexed: 02/22/2023] Open
Abstract
Purpose: Motion-impaired CT images can result in limited or suboptimal diagnostic interpretation (with missed or miscalled lesions) and patient recall. We trained and tested an artificial intelligence (AI) model for identifying substantial motion artifacts on CT pulmonary angiography (CTPA) that have a negative impact on diagnostic interpretation. Methods: With IRB approval and HIPAA compliance, we queried our multicenter radiology report database (mPower, Nuance) for CTPA reports between July 2015 and March 2022 for the following terms: "motion artifacts", "respiratory motion", "technically inadequate", and "suboptimal" or "limited exam". All CTPA reports were from two quaternary (Site A, n = 335; B, n = 259) and a community (C, n = 199) healthcare sites. A thoracic radiologist reviewed CT images of all positive hits for motion artifacts (present or absent) and their severity (no diagnostic effect or major diagnostic impairment). Coronal multiplanar images from 793 CTPA exams were de-identified and exported offline into an AI model building prototype (Cognex Vision Pro, Cognex Corporation) to train an AI model to perform two-class classification ("motion" or "no motion") with data from the three sites (70% training dataset, n = 554; 30% validation dataset, n = 239). Separately, data from Site A and Site C were used for training and validating; testing was performed on the Site B CTPA exams. A five-fold repeated cross-validation was performed to evaluate the model performance with accuracy and receiver operating characteristics analysis (ROC). Results: Among the CTPA images from 793 patients (mean age 63 ± 17 years; 391 males, 402 females), 372 had no motion artifacts, and 421 had substantial motion artifacts. The statistics for the average performance of the AI model after five-fold repeated cross-validation for the two-class classification included 94% sensitivity, 91% specificity, 93% accuracy, and 0.93 area under the ROC curve (AUC: 95% CI 0.89-0.97). Conclusion: The AI model used in this study can successfully identify CTPA exams with diagnostic interpretation limiting motion artifacts in multicenter training and test datasets. Clinical relevance: The AI model used in the study can help alert technologists about the presence of substantial motion artifacts on CTPA, where a repeat image acquisition can help salvage diagnostic information.
Collapse
Affiliation(s)
- Giridhar Dasegowda
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Bernardo C. Bizzo
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Parisa Kaviani
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Lina Karout
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Shadi Ebrahimian
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
| | - Subba R. Digumarthy
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
| | - Nir Neumark
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - James M. Hillis
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Mannudeep K. Kalra
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Keith J. Dreyer
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| |
Collapse
|
19
|
Kaviani P, Primak A, Bizzo B, Ebrahimian S, Saini S, Dreyer KJ, Kalra MK. Performance of threshold-based stone segmentation and radiomics for determining the composition of kidney stones from single-energy CT. Jpn J Radiol 2023; 41:194-200. [PMID: 36331701 DOI: 10.1007/s11604-022-01349-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2022] [Accepted: 09/30/2022] [Indexed: 11/06/2022]
Abstract
PURPOSE Knowledge of kidney stone composition can help in patient management; urine composition analysis and dual-energy CT are frequently used to assess stone type. We assessed if threshold-based stone segmentation and radiomics can determine the composition of kidney stones from single-energy, non-contrast abdomen-pelvis CT. METHODS With IRB approval, we identified 218 consecutive patients (mean age 64 ± 13 years; male:female 138:80) with the presence of kidney stones on non-contrast, abdomen-pelvis CT and surgical or biochemical proof of their stone composition. CT examinations were performed on one of the seven multidetector-row scanners from four vendors (GE, Philips, Siemens, Toshiba). Deidentified CT images were processed with a radiomics prototype (Frontier, Siemens Healthineers) to segment the entire kidney volumes with an AI-based organ segmentation tool. We applied a threshold of 130 HU to isolate stones in the segmented kidneys and to estimate radiomics over the segmented stone volume. A coinvestigator verified kidney stone segmentation and adjusted the volume of interest to include the entire stone volume when necessary. We applied multiple logistic regression tests with precision recall plots to obtain area under the curve (AUC) using a built-in R statistical program. RESULTS The threshold-based stone segmentation successfully isolated kidney stones (uric acid: n = 102 patients, calcium oxalate/phosphate: n = 116 patients) in all patients. Radiomics differentiated between calcium and uric acid stones with an AUC of 0.78 (p < 0.01, 95% CI 0.73-0.83), 0.79 sensitivity, and 0.90 specificity regardless of CT vendors (GE CT: AUC = 0.82, p < 0.01, 95% CI 0.740-0896; Siemens CT: AUC = 0.77, 95% CI 0.700-0.846, p < 0.01). CONCLUSION Automated threshold-based stone segmentation and radiomics can differentiate between calcium oxalate/phosphate and urate stones from non-contrast, single-energy abdomen CT.
Collapse
Affiliation(s)
- Parisa Kaviani
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA, 02114, USA
| | - Andrew Primak
- Siemens Medical Solutions USA Inc, Malvern, PA, 19355, USA
| | - Bernardo Bizzo
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA, 02114, USA.,MGH and BWH Center for Clinical Data Science, Boston, USA
| | - Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA, 02114, USA
| | - Sanjay Saini
- Department of Radiology, Massachusetts General Hospital, 55 Fruit St, Boston, MA, 02114, USA
| | - Keith J Dreyer
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA, 02114, USA.,MGH and BWH Center for Clinical Data Science, Boston, USA.,Department of Radiology, Massachusetts General Hospital, 25 New Chardon Street, Boston, MA, 02114, USA
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA, 02114, USA.
| |
Collapse
|
20
|
Hillis JM, Bizzo BC, Mercaldo S, Chin JK, Newbury-Chaet I, Digumarthy SR, Gilman MD, Muse VV, Bottrell G, Seah JC, Jones CM, Kalra MK, Dreyer KJ. Evaluation of an Artificial Intelligence Model for Detection of Pneumothorax and Tension Pneumothorax in Chest Radiographs. JAMA Netw Open 2022; 5:e2247172. [PMID: 36520432 PMCID: PMC9856508 DOI: 10.1001/jamanetworkopen.2022.47172] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/23/2022] Open
Abstract
IMPORTANCE Early detection of pneumothorax, most often via chest radiography, can help determine need for emergent clinical intervention. The ability to accurately detect and rapidly triage pneumothorax with an artificial intelligence (AI) model could assist with earlier identification and improve care. OBJECTIVE To compare the accuracy of an AI model vs consensus thoracic radiologist interpretations in detecting any pneumothorax (incorporating both nontension and tension pneumothorax) and tension pneumothorax. DESIGN, SETTING, AND PARTICIPANTS This diagnostic study was a retrospective standalone performance assessment using a data set of 1000 chest radiographs captured between June 1, 2015, and May 31, 2021. The radiographs were obtained from patients aged at least 18 years at 4 hospitals in the Mass General Brigham hospital network in the United States. Included radiographs were selected using 2 strategies from all chest radiography performed at the hospitals, including inpatient and outpatient. The first strategy identified consecutive radiographs with pneumothorax through a manual review of radiology reports, and the second strategy identified consecutive radiographs with tension pneumothorax using natural language processing. For both strategies, negative radiographs were selected by taking the next negative radiograph acquired from the same radiography machine as each positive radiograph. The final data set was an amalgamation of these processes. Each radiograph was interpreted independently by up to 3 radiologists to establish consensus ground-truth interpretations. Each radiograph was then interpreted by the AI model for the presence of pneumothorax and tension pneumothorax. This study was conducted between July and October 2021, with the primary analysis performed between October and November 2021. MAIN OUTCOMES AND MEASURES The primary end points were the areas under the receiver operating characteristic curves (AUCs) for the detection of pneumothorax and tension pneumothorax. The secondary end points were the sensitivities and specificities for the detection of pneumothorax and tension pneumothorax. RESULTS The final analysis included radiographs from 985 patients (mean [SD] age, 60.8 [19.0] years; 436 [44.3%] female patients), including 307 patients with nontension pneumothorax, 128 patients with tension pneumothorax, and 550 patients without pneumothorax. The AI model detected any pneumothorax with an AUC of 0.979 (95% CI, 0.970-0.987), sensitivity of 94.3% (95% CI, 92.0%-96.3%), and specificity of 92.0% (95% CI, 89.6%-94.2%) and tension pneumothorax with an AUC of 0.987 (95% CI, 0.980-0.992), sensitivity of 94.5% (95% CI, 90.6%-97.7%), and specificity of 95.3% (95% CI, 93.9%-96.6%). CONCLUSIONS AND RELEVANCE These findings suggest that the assessed AI model accurately detected pneumothorax and tension pneumothorax in this chest radiograph data set. The model's use in the clinical workflow could lead to earlier identification and improved care for patients with pneumothorax.
Collapse
Affiliation(s)
- James M. Hillis
- Data Science Office, Mass General Brigham, Boston, Massachusetts
- Department of Neurology, Massachusetts General Hospital, Boston
- Harvard Medical School, Boston, Massachusetts
| | - Bernardo C. Bizzo
- Data Science Office, Mass General Brigham, Boston, Massachusetts
- Harvard Medical School, Boston, Massachusetts
- Department of Radiology, Massachusetts General Hospital, Boston
| | - Sarah Mercaldo
- Data Science Office, Mass General Brigham, Boston, Massachusetts
- Harvard Medical School, Boston, Massachusetts
- Department of Radiology, Massachusetts General Hospital, Boston
| | - John K. Chin
- Data Science Office, Mass General Brigham, Boston, Massachusetts
| | | | - Subba R. Digumarthy
- Harvard Medical School, Boston, Massachusetts
- Department of Radiology, Massachusetts General Hospital, Boston
| | - Matthew D. Gilman
- Harvard Medical School, Boston, Massachusetts
- Department of Radiology, Massachusetts General Hospital, Boston
| | - Victorine V. Muse
- Harvard Medical School, Boston, Massachusetts
- Department of Radiology, Massachusetts General Hospital, Boston
| | | | | | - Catherine M. Jones
- Annalise-AI, Sydney, Australia
- I-MED Radiology Network, Brisbane, Australia
- Faculty of Medicine and Health, University of Sydney, Sydney, Australia
| | - Mannudeep K. Kalra
- Data Science Office, Mass General Brigham, Boston, Massachusetts
- Harvard Medical School, Boston, Massachusetts
- Department of Radiology, Massachusetts General Hospital, Boston
| | - Keith J. Dreyer
- Data Science Office, Mass General Brigham, Boston, Massachusetts
- Harvard Medical School, Boston, Massachusetts
- Department of Radiology, Massachusetts General Hospital, Boston
| |
Collapse
|
21
|
Gupta RV, Kalra MK, Ebrahimian S, Kaviani P, Primak A, Bizzo B, Dreyer KJ. Complex Relationship Between Artificial Intelligence and CT Radiation Dose. Acad Radiol 2022; 29:1709-1719. [PMID: 34836775 DOI: 10.1016/j.acra.2021.10.024] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2021] [Revised: 10/15/2021] [Accepted: 10/17/2021] [Indexed: 12/22/2022]
Abstract
Concerns over need for CT radiation dose optimization and reduction led to improved scanner efficiency and introduction of several reconstruction techniques and image processing-based software. The latest technologies use artificial intelligence (AI) for CT dose optimization and image quality improvement. While CT dose optimization has and can benefit from AI, variations in scanner technologies, reconstruction methods, and scan protocols can lead to substantial variations in radiation doses and image quality across and within different scanners. These variations in turn can influence performance of AI algorithms being deployed for tasks such as detection, segmentation, characterization, and quantification. We review the complex relationship between AI and CT radiation dose.
Collapse
Affiliation(s)
- Reya V Gupta
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, Massachusetts
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, Massachusetts.
| | - Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, Massachusetts
| | - Parisa Kaviani
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, Massachusetts
| | - Andrew Primak
- Siemens Medical Solutions USA Inc, Malvern, Pennsylvania
| | - Bernardo Bizzo
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, Massachusetts; MGH & BWH Center for Clinical Data Science, Boston, Massachusetts
| | - Keith J Dreyer
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, Massachusetts; MGH & BWH Center for Clinical Data Science, Boston, Massachusetts
| |
Collapse
|
22
|
Suri JS, Agarwal S, Saba L, Chabert GL, Carriero A, Paschè A, Danna P, Mehmedović A, Faa G, Jujaray T, Singh IM, Khanna NN, Laird JR, Sfikakis PP, Agarwal V, Teji JS, R Yadav R, Nagy F, Kincses ZT, Ruzsa Z, Viskovic K, Kalra MK. Multicenter Study on COVID-19 Lung Computed Tomography Segmentation with varying Glass Ground Opacities using Unseen Deep Learning Artificial Intelligence Paradigms: COVLIAS 1.0 Validation. J Med Syst 2022; 46:62. [PMID: 35988110 PMCID: PMC9392994 DOI: 10.1007/s10916-022-01850-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Accepted: 08/02/2022] [Indexed: 11/09/2022]
Abstract
Variations in COVID-19 lesions such as glass ground opacities (GGO), consolidations, and crazy paving can compromise the ability of solo-deep learning (SDL) or hybrid-deep learning (HDL) artificial intelligence (AI) models in predicting automated COVID-19 lung segmentation in Computed Tomography (CT) from unseen data leading to poor clinical manifestations. As the first study of its kind, “COVLIAS 1.0-Unseen” proves two hypotheses, (i) contrast adjustment is vital for AI, and (ii) HDL is superior to SDL. In a multicenter study, 10,000 CT slices were collected from 72 Italian (ITA) patients with low-GGO, and 80 Croatian (CRO) patients with high-GGO. Hounsfield Units (HU) were automatically adjusted to train the AI models and predict from test data, leading to four combinations—two Unseen sets: (i) train-CRO:test-ITA, (ii) train-ITA:test-CRO, and two Seen sets: (iii) train-CRO:test-CRO, (iv) train-ITA:test-ITA. COVILAS used three SDL models: PSPNet, SegNet, UNet and six HDL models: VGG-PSPNet, VGG-SegNet, VGG-UNet, ResNet-PSPNet, ResNet-SegNet, and ResNet-UNet. Two trained, blinded senior radiologists conducted ground truth annotations. Five types of performance metrics were used to validate COVLIAS 1.0-Unseen which was further benchmarked against MedSeg, an open-source web-based system. After HU adjustment for DS and JI, HDL (Unseen AI) > SDL (Unseen AI) by 4% and 5%, respectively. For CC, HDL (Unseen AI) > SDL (Unseen AI) by 6%. The COVLIAS-MedSeg difference was < 5%, meeting regulatory guidelines.Unseen AI was successfully demonstrated using automated HU adjustment. HDL was found to be superior to SDL.
Collapse
|
23
|
Aly A, Ebrahimian S, Kharita MH, Heidous M, Ashruf MZ, Kumar D, Kalra MK, Al Naemi HM. Effect of technologist and patient attributes on centering for body CT examinations: Influence of cultural and ethnic factors. PLoS One 2022; 17:e0273227. [PMID: 35984837 PMCID: PMC9390905 DOI: 10.1371/journal.pone.0273227] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2022] [Accepted: 07/21/2022] [Indexed: 11/19/2022] Open
Abstract
There are no published data on the effect of patient and technologist gender and ethnicity attributes on off-centering in CT. Therefore, we assessed the impact of patient and technologist variations on off-centering patients undergoing body CT. With institutional review board approval, our retrospective study included 1000 consecutive adult patients (age ranged 22–96 years; 756 males: 244 females) who underwent chest or abdomen CT examinations. We recorded patient (age, gender, nationality, body weight, height,), technologist gender, and scan-related (scanner vendor, body region imaged, scan length, CT dose index volume, dose length product) information. Lateral and anteroposterior (AP) diameters were recorded to calculate effective diameter and size-specific dose estimate (SSDE). Off-centering represented the distance between the anterior-posterior centers of the scan field of view and the patient at the level of carina (for chest CT) and iliac crest (for abdomen CT). About 76% of the patients (760/1000) were off-centered with greater off-centering for chest (22 mm) than for abdomen (15 mm). Although ethnicity or patient gender was not a significant determinant of off-centering, technologist-patient gender mismatch was associated with a significantly greater frequency of off-centering (p<0.001). Off-centering below the gantry isocenter was twice as common as off-centering above the gantry isocenter (p<0.001). The latter occurred more frequently in larger patients and was associated with higher radiation doses than those centered below the isocenter (p<0.001). Technologists’ years of experience and patient factors profoundly affect the presence and extent of off-centering for both chest and abdomen CTs. Larger patients are more often off-centered than smaller patients.
Collapse
Affiliation(s)
- Antar Aly
- Hamad Medical Corporation, Doha, Qatar
- * E-mail:
| | - Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, United States of America
| | | | | | | | | | - Mannudeep K. Kalra
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, United States of America
| | | |
Collapse
|
24
|
Lyhne MD, Witkin AS, Dasegowda G, Tanayan C, Kalra MK, Dudzinski DM. Evaluating cardiopulmonary function following acute pulmonary embolism. Expert Rev Cardiovasc Ther 2022; 20:747-760. [PMID: 35920239 DOI: 10.1080/14779072.2022.2108789] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/16/2022]
Abstract
INTRODUCTION Pulmonary embolism is a common cause of cardiopulmonary mortality and morbidity worldwide. Survivors of acute pulmonary embolism may experience dyspnea, report reduced exercise capacity, or develop overt pulmonary hypertension. Clinicians must be alert for these phenomena and appreciate the modalities and investigations available for evaluation. AREAS COVERED In this review, the current understanding of available contemporary imaging and physiologic modalities is discussed, based on available literature and professional society guidelines. The purpose of the review is to provide clinicians with an overview of these modalities, their strengths and disadvantages, and how and when these investigations can support the clinical work-up of patients post-pulmonary embolism. EXPERT OPINION Echocardiography is a first test in symptomatic patients post-pulmonary embolism, with ventilation/perfusion scanning vital to determination of whether there is chronic residual emboli. The role of computed tomography and magnetic resonance in assessing the pulmonary arterial tree in post-pulmonary embolism patients is evolving. Functional testing, in particular cardiopulmonary exercise testing, is emerging as an important modality to quantify and determine cause of functional limitation. It is possible that future investigations of the post-pulmonary embolism recovery period will better inform treatment decisions for acute pulmonary embolism patients.
Collapse
Affiliation(s)
- Mads Dam Lyhne
- Department of Cardiology, Massachusetts General Hospital, Boston, MA, USA.,Department of Anesthesiology and Intensive Care Medicine, Aarhus University Hospital and Department of Clinical Medicine, Aarhus University, Denmark
| | - Alison S Witkin
- Department of Pulmonary Medicine and Critical Care, Massachusetts General Hospital, Boston, MA, USA
| | - Giridhar Dasegowda
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Christopher Tanayan
- Cardiovascular Performance Program, Massachusetts General Hospital, Boston, MA, USA
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - David M Dudzinski
- Department of Cardiology, Massachusetts General Hospital, Boston, MA, USA.,Echocardiography Laboratory, Massachusetts General Hospital, Boston, MA, USA
| |
Collapse
|
25
|
Ahn JS, Ebrahimian S, McDermott S, Lee S, Naccarato L, Di Capua JF, Wu MY, Zhang EW, Muse V, Miller B, Sabzalipour F, Bizzo BC, Dreyer KJ, Kaviani P, Digumarthy SR, Kalra MK. Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency. JAMA Netw Open 2022; 5:e2229289. [PMID: 36044215 PMCID: PMC9434361 DOI: 10.1001/jamanetworkopen.2022.29289] [Citation(s) in RCA: 28] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023] Open
Abstract
IMPORTANCE The efficient and accurate interpretation of radiologic images is paramount. OBJECTIVE To evaluate whether a deep learning-based artificial intelligence (AI) engine used concurrently can improve reader performance and efficiency in interpreting chest radiograph abnormalities. DESIGN, SETTING, AND PARTICIPANTS This multicenter cohort study was conducted from April to November 2021 and involved radiologists, including attending radiologists, thoracic radiology fellows, and residents, who independently participated in 2 observer performance test sessions. The sessions included a reading session with AI and a session without AI, in a randomized crossover manner with a 4-week washout period in between. The AI produced a heat map and the image-level probability of the presence of the referrable lesion. The data used were collected at 2 quaternary academic hospitals in Boston, Massachusetts: Beth Israel Deaconess Medical Center (The Medical Information Mart for Intensive Care Chest X-Ray [MIMIC-CXR]) and Massachusetts General Hospital (MGH). MAIN OUTCOMES AND MEASURES The ground truths for the labels were created via consensual reading by 2 thoracic radiologists. Each reader documented their findings in a customized report template, in which the 4 target chest radiograph findings and the reader confidence of the presence of each finding was recorded. The time taken for reporting each chest radiograph was also recorded. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were calculated for each target finding. RESULTS A total of 6 radiologists (2 attending radiologists, 2 thoracic radiology fellows, and 2 residents) participated in the study. The study involved a total of 497 frontal chest radiographs-247 from the MIMIC-CXR data set (demographic data for patients were not available) and 250 chest radiographs from MGH (mean [SD] age, 63 [16] years; 133 men [53.2%])-from adult patients with and without 4 target findings (pneumonia, nodule, pneumothorax, and pleural effusion). The target findings were found in 351 of 497 chest radiographs. The AI was associated with higher sensitivity for all findings compared with the readers (nodule, 0.816 [95% CI, 0.732-0.882] vs 0.567 [95% CI, 0.524-0.611]; pneumonia, 0.887 [95% CI, 0.834-0.928] vs 0.673 [95% CI, 0.632-0.714]; pleural effusion, 0.872 [95% CI, 0.808-0.921] vs 0.889 [95% CI, 0.862-0.917]; pneumothorax, 0.988 [95% CI, 0.932-1.000] vs 0.792 [95% CI, 0.756-0.827]). AI-aided interpretation was associated with significantly improved reader sensitivities for all target findings, without negative impacts on the specificity. Overall, the AUROCs of readers improved for all 4 target findings, with significant improvements in detection of pneumothorax and nodule. The reporting time with AI was 10% lower than without AI (40.8 vs 36.9 seconds; difference, 3.9 seconds; 95% CI, 2.9-5.2 seconds; P < .001). CONCLUSIONS AND RELEVANCE These findings suggest that AI-aided interpretation was associated with improved reader performance and efficiency for identifying major thoracic findings on a chest radiograph.
Collapse
Affiliation(s)
| | - Shadi Ebrahimian
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
- Internal Medicine, Icahn School of Medicine at Mount Sinai, Elmhurst Hospital Center, Elmhurst, New York
| | - Shaunagh McDermott
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | | | - Laura Naccarato
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - John F. Di Capua
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Markus Y. Wu
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Eric W. Zhang
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Victorine Muse
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Benjamin Miller
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
- Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Farid Sabzalipour
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
- Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Bernardo C. Bizzo
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
- Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Keith J. Dreyer
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
- Data Science Office, Mass General Brigham, Boston, Massachusetts
| | - Parisa Kaviani
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Subba R. Digumarthy
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Mannudeep K. Kalra
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
- Data Science Office, Mass General Brigham, Boston, Massachusetts
| |
Collapse
|
26
|
Ebrahimian S, Singh R, Netaji A, Madhusudhan KS, Homayounieh F, Primak A, Lades F, Saini S, Kalra MK, Sharma S. Characterization of Benign and Malignant Pancreatic Lesions with DECT Quantitative Metrics and Radiomics. Acad Radiol 2022; 29:705-713. [PMID: 34412944 DOI: 10.1016/j.acra.2021.07.008] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2021] [Revised: 07/07/2021] [Accepted: 07/14/2021] [Indexed: 12/24/2022]
Abstract
RATIONALE AND OBJECTIVES To compare dual energy CT (DECT) quantitative metrics and radiomics for differentiating benign and malignant pancreatic lesions on contrast enhanced abdomen CT. MATERIALS AND METHODS Our study included 103 patients who underwent contrast-enhanced DECT for assessing focal pancreatic lesions at one of the two hospitals (Site A: age 68 ± 12 yrs; malignant = 41, benign = 18; Site B: age 46 ± 2 yrs; malignant = 23, benign = 21). All malignant lesions had histologic confirmation, and benign lesions were stable on follow up CT (>12 months) or had characteristic benign features on MRI. Arterial-phase, low- and high-kV DICOM images were processed with the DECT Tumor Analysis (DETA) to obtain DECT quantitative metrics such as HU, iodine and water content from a region of interest (ROI) over focal pancreatic lesions. Separately, we obtained DECT radiomics from the same ROI. Data were analyzed with multiple logistic regression and receiver operating characteristics to generate area under the curve (AUC) for best predictive variables. RESULTS DECT quantitative metrics and radiomics had AUCs of 0.98-0.99 at site A and 0.89-0.94 at site B data for classifying benign and malignant pancreatic lesions. There was no significant difference in the AUCs and accuracies of DECT quantitative metrics and radiomics from lesion rims and volumes among patients at both sites (p > 0.05). Supervised learning-based model with data from the two sites demonstrated best AUCs of 0.94 (DECT radiomics) and 0.90 (DECT quantitative metrics) for characterizing pancreatic lesions as benign or malignant. CONCLUSION Compared to complex DECT radiomics, quantitative DECT information provide a simpler but accurate method of differentiating benign and malignant pancreatic lesions.
Collapse
Affiliation(s)
- Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom court, Boston, MA 02114
| | - Ramandeep Singh
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom court, Boston, MA 02114
| | - Arjunlokesh Netaji
- Department of Radiodiagnosis and Interventional Radiology, All India Institute of Medical Sciences, New Delhi, India
| | - Kumble Seetharama Madhusudhan
- Department of Radiodiagnosis and Interventional Radiology, All India Institute of Medical Sciences, New Delhi, India
| | - Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom court, Boston, MA 02114
| | - Andrew Primak
- Siemens Medical Solutions USA Inc., Malvern, Pennsylvania
| | | | - Sanjay Saini
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom court, Boston, MA 02114
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom court, Boston, MA 02114.
| | - Sanjay Sharma
- Department of Radiodiagnosis and Interventional Radiology, All India Institute of Medical Sciences, New Delhi, India
| |
Collapse
|
27
|
Ebrahimian S, Homayounieh F, Singh R, Primak A, Kalra MK, Romero JM. Spectral segmentation and radiomic features predict carotid stenosis and ipsilateral ischemic burden from DECT angiography. Diagn Interv Radiol 2022; 28:264-274. [PMID: 35748211 DOI: 10.5152/dir.2022.20842] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
PURPOSE The purpose of this study is to compare spectral segmentation, spectral radiomic, and single- energy radiomic features in the assessment of internal and common carotid artery (ICA/CCA) stenosis and prediction of surgical outcome. METHODS Our ethical committee-approved, Health Insurance Portability and Accountability Act (HIPAA)- compliant study included 85 patients (mean age, 73 ± 10 years; male : female, 56 : 29) who under- went contrast-enhanced, dual-source dual-energy CT angiography (DECTA) (Siemens Definition Flash) of the neck for assessing ICA/CCA stenosis. Patients with a prior surgical or interventional treatment of carotid stenosis were excluded. Two radiologists graded the severity of carotid ste- nosis on DECTA images as mild (<50% luminal narrowing), moderate (50%-69%), and severe (>70%) stenosis. Thin-section, low- and high-kV DICOM images from the arterial phase acquisi- tion were processed with a dual-energy CT prototype (DTA, eXamine, Siemens Healthineers) to generate spectral segmentation and radiomic features over regions of interest along the entire length (volume) and separately at a single-section with maximum stenosis. Multiple logistic regressions and area under the receiver operating characteristic curve (AUC) were used for data analysis. RESULTS Among 85 patients, 22 ICA/CCAs had normal luminal dimensions and 148 ICA/CCAs had luminal stenosis (mild stenosis: 51, moderate: 38, severe: 59). For differentiating non-severe and severe ICA/CCA stenosis, radiomic features (volume: AUC=0.94, 95% CI 0.88-0.96; section: AUC=0.92, 95% CI 0.86-0.93) were significantly better than spectral segmentation features (volume: AUC = 0.86, 95% CI 0.74-0.87; section: AUC = 0.68, 95% CI 0.66-0.78) (P < .001). Spectral radiomic features predicted revascularization procedure (AUC = 0.77) and the presence of ipsilateral intra- cranial ischemic changes (AUC = 0.76). CONCLUSION Spectral segmentation and radiomic features from DECTA can differentiate patients with differ- ent luminal ICA/CCA stenosis grades.
Collapse
Affiliation(s)
- Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, Massachusetts, USA; MGH Webster Center for Quality and Safety, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, Massachusetts, USA; MGH Webster Center for Quality and Safety, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Ramandeep Singh
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, Massachusetts, USA
| | - Andrew Primak
- Siemens Healthcare USA Inc., Malvern, Pennsylvania, USA
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, Massachusetts, USA; MGH Webster Center for Quality and Safety, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Javier M Romero
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
28
|
Ebrahimian S, Kalra MK, Agarwal S, Bizzo BC, Elkholy M, Wald C, Allen B, Dreyer KJ. FDA-regulated AI Algorithms: Trends, Strengths, and Gaps of Validation Studies. Acad Radiol 2022; 29:559-566. [PMID: 34969610 DOI: 10.1016/j.acra.2021.09.002] [Citation(s) in RCA: 37] [Impact Index Per Article: 18.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2021] [Revised: 08/24/2021] [Accepted: 09/04/2021] [Indexed: 12/31/2022]
Abstract
RATIONALE AND OBJECTIVES To assess key trends, strengths, and gaps in validation studies of the Food and Drug Administration (FDA)-regulated imaging-based artificial intelligence/machine learning (AI/ML) algorithms. MATERIALS AND METHODS We audited publicly available details of regulated AI/ML algorithms in imaging from 2008 until April 2021. We reviewed 127 regulated software (118 AI/ML) to classify information related to their parent company, subspecialty, body area and specific anatomy type, imaging modality, date of FDA clearance, indications for use, target pathology (such as trauma) and findings (such as fracture), technique (CAD triage, CAD detection and/or characterization, CAD acquisition or improvement, and image processing/quantification), product performance, presence, type, strength and availability of clinical validation data. Pertaining to validation data, where available, we recorded the number of patients or studies included, sensitivity, specificity, accuracy, and/or receiver operating characteristic area under the curve, along with information on ground-truthing of use-cases. Data were analyzed with pivot tables and charts for descriptive statistics and trends. RESULTS We noted an increasing number of FDA-regulated AI/ML from 2008 to 2021. Seventeen (17/118) regulated AI/ML algorithms posted no validation claims or data. Just 9/118 reviewed AI/ML algorithms had a validation dataset sizes of over 1000 patients. The most common type of AI/ML included image processing/quantification (IPQ; n = 59/118), and triage (CADt; n = 27/118). Brain, breast, and lungs dominated the targeted body regions of interest. CONCLUSION Insufficient public information on validation datasets in several FDA-regulated AI/ML algorithms makes it difficult to justify clinical applications since their generalizability and presence of bias cannot be inferred.
Collapse
|
29
|
Božanić A, Šegota D, Debeljuh DD, Kolacio MŠ, Radojčić ĐS, Ružić K, Budanec M, Kasabašić M, Hrepić D, Valković Zujić P, Brambilla M, Kalra MK, Jurković S. National reference levels of CT procedures dedicated for treatment planning in radiation oncology. Phys Med 2022; 96:123-129. [PMID: 35278930 DOI: 10.1016/j.ejmp.2022.03.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/19/2021] [Revised: 02/16/2022] [Accepted: 03/02/2022] [Indexed: 11/17/2022] Open
Abstract
OBJECTIVE To present results of the first national survey on reference levels of CT imaging performed for the treatment planning purposes in radiation oncology in Croatia. METHODS Data for CT protocols of five anatomical regions including head, head and neck, pelvis, breast, and thorax were collected at eight radiation oncology departments in Croatia. Data included volume CT dose index (CTDIvol), dose-length product (DLP), scan length and set of acquisition and reconstruction parameters. Data on a total of 600 patients were collected. Median values of scan length, DLP and CTDIvol were calculated for each acquisition protocol. Third quartiles of the median CTDIvol and DLP values were proposed as the national radiotherapy planning reference levels (RPRL). RESULTS The largest CoV were assessed for RT Breast (63.8% for CTDIvol), RT Thorax (79.7% for DLP) and RT H&N (21.2% for scan length). RT Head had the lowest CoV for CTDIvol (1,9%) and DLP (17,2%), while RT Breast had the lowest coefficient of variation for scan length (12.8%). Proposed national RPRLs are: for RT Head CTDIvol16cm = 62 mGy and DLP16cm = 1738 mGy.cm; for RT H&N CTDIvol16cm = 35 mGy and DLP16cm = 1444 mGy.cm; for RT Breast CTDIvol32cm = 16 mGy and DLP32cm = 731 mGy.cm; for RT Thorax CTDIvol32cm = 17 mGy and DLP32cm = 865 mGy.cm; for RT Pelvis CTDIvol32cm = 20 mGy and DLP32cm = 1133 mGy.cm. CONCLUSIONS Results of this study show variations in CT imaging for treatment planning practice at the national level which call for optimization of procedures.
Collapse
Affiliation(s)
- Ana Božanić
- Medical Physics and Radiation Protection Department, Clinical Hospital Centre Rijeka, Krešimirova 42, Rijeka, Croatia; Medical Physics and Biophysics Department, Medical Faculty, University of Rijeka, Braće Branchetta 20, Rijeka, Croatia.
| | - Doris Šegota
- Medical Physics and Radiation Protection Department, Clinical Hospital Centre Rijeka, Krešimirova 42, Rijeka, Croatia
| | - Dea Dundara Debeljuh
- Medical Physics and Radiation Protection Department, Clinical Hospital Centre Rijeka, Krešimirova 42, Rijeka, Croatia; Medical Physics and Biophysics Department, Medical Faculty, University of Rijeka, Braće Branchetta 20, Rijeka, Croatia; Radiology Department, General Hospital Pula, Santiorova 24a, Pula, Croatia
| | - Manda Švabić Kolacio
- Medical Physics and Radiation Protection Department, Clinical Hospital Centre Rijeka, Krešimirova 42, Rijeka, Croatia
| | - Đeni Smilović Radojčić
- Medical Physics and Radiation Protection Department, Clinical Hospital Centre Rijeka, Krešimirova 42, Rijeka, Croatia; Medical Physics and Biophysics Department, Medical Faculty, University of Rijeka, Braće Branchetta 20, Rijeka, Croatia
| | - Katarina Ružić
- Department of Medical Physics, The University Hospital Centre Zagreb, Kišpatićeva 12, Zagreb, Croatia
| | - Mirjana Budanec
- University Clinical Hospital Center Sestre Milosrdnice, Department of Medical Physics, Vinogradska 29, Zagreb, Croatia
| | - Mladen Kasabašić
- Osijek University Hospital, Department of Medical Physics, Osijek, Josipa Huttlera 4, Croatia
| | - Darijo Hrepić
- Department of Medical Physics, University Hospital of Split, Spinčićeva 1, Split, Croatia
| | - Petra Valković Zujić
- Radiology Department, University Hospital Rijeka, Krešimirova 42, Rijeka, Croatia; Radiology Department, Medical Faculty, University of Rijeka, Braće Branchetta 20, Rijeka, Croatia
| | - Marco Brambilla
- Department of Medical Physics, Azienda Ospedaliero Universitaria Maggiore della Carità, Novara, Italy
| | - Mannudeep K Kalra
- Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA
| | - Slaven Jurković
- Medical Physics and Radiation Protection Department, Clinical Hospital Centre Rijeka, Krešimirova 42, Rijeka, Croatia; Medical Physics and Biophysics Department, Medical Faculty, University of Rijeka, Braće Branchetta 20, Rijeka, Croatia
| |
Collapse
|
30
|
Nillmani, Jain PK, Sharma N, Kalra MK, Viskovic K, Saba L, Suri JS. Four Types of Multiclass Frameworks for Pneumonia Classification and Its Validation in X-ray Scans Using Seven Types of Deep Learning Artificial Intelligence Models. Diagnostics (Basel) 2022; 12:652. [PMID: 35328205 PMCID: PMC8946935 DOI: 10.3390/diagnostics12030652] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2022] [Revised: 03/04/2022] [Accepted: 03/04/2022] [Indexed: 12/31/2022] Open
Abstract
Background and Motivation: The novel coronavirus causing COVID-19 is exceptionally contagious, highly mutative, decimating human health and life, as well as the global economy, by consistent evolution of new pernicious variants and outbreaks. The reverse transcriptase polymerase chain reaction currently used for diagnosis has major limitations. Furthermore, the multiclass lung classification X-ray systems having viral, bacterial, and tubercular classes—including COVID-19—are not reliable. Thus, there is a need for a robust, fast, cost-effective, and easily available diagnostic method. Method: Artificial intelligence (AI) has been shown to revolutionize all walks of life, particularly medical imaging. This study proposes a deep learning AI-based automatic multiclass detection and classification of pneumonia from chest X-ray images that are readily available and highly cost-effective. The study has designed and applied seven highly efficient pre-trained convolutional neural networks—namely, VGG16, VGG19, DenseNet201, Xception, InceptionV3, NasnetMobile, and ResNet152—for classification of up to five classes of pneumonia. Results: The database consisted of 18,603 scans with two, three, and five classes. The best results were using DenseNet201, VGG16, and VGG16, respectively having accuracies of 99.84%, 96.7%, 92.67%; sensitivity of 99.84%, 96.63%, 92.70%; specificity of 99.84, 96.63%, 92.41%; and AUC of 1.0, 0.97, 0.92 (p < 0.0001 for all), respectively. Our system outperformed existing methods by 1.2% for the five-class model. The online system takes <1 s while demonstrating reliability and stability. Conclusions: Deep learning AI is a powerful paradigm for multiclass pneumonia classification.
Collapse
Affiliation(s)
- Nillmani
- School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi 221005, India; (N.); (P.K.J.); (N.S.)
| | - Pankaj K. Jain
- School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi 221005, India; (N.); (P.K.J.); (N.S.)
| | - Neeraj Sharma
- School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi 221005, India; (N.); (P.K.J.); (N.S.)
| | - Mannudeep K. Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02115, USA;
| | - Klaudija Viskovic
- Department of Radiology and Ultrasound, University Hospital for Infectious Diseases, 10000 Zagreb, Croatia;
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 10015 Cagliari, Italy;
| | - Jasjit S. Suri
- Stroke Diagnostic and Monitoring Division, AtheroPoint, Roseville, CA 95661, USA
- Knowledge Engineering Center, Global Biomedical Technologies, Inc., Roseville, CA 95661, USA
| |
Collapse
|
31
|
Bernardo M, Homayounieh F, Cuter MCR, Bellegard LM, Oliveira Junior HM, Buril GO, de Melo Tapajós JS, Sales DM, de Moura Carvalho LC, Alves Pinto D, Varella R, Tapajós LL, Ebrahimian S, Vassileva J, Kalra MK, Khoury HJ. CHEST CT USAGE IN COVID-19 PNEUMONIA: MULTICENTER STUDY ON RADIATION DOSES AND DIAGNOSTIC QUALITY IN BRAZIL. Radiat Prot Dosimetry 2021; 197:135-145. [PMID: 34875692 PMCID: PMC8903326 DOI: 10.1093/rpd/ncab171] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/18/2021] [Revised: 10/15/2021] [Accepted: 05/08/2021] [Indexed: 06/13/2023]
Abstract
We assessed variations in chest CT usage, radiation dose and image quality in COVID-19 pneumonia. Our study included all chest CT exams performed in 533 patients from 6 healthcare sites from Brazil. We recorded patients' age, gender and body weight and the information number of CT exams per patient, scan parameters and radiation doses (volume CT dose index-CTDIvol and dose length product-DLP). Six radiologists assessed all chest CT exams for the type of pulmonary findings and classified CT appearance of COVID-19 pneumonia as typical, indeterminate, atypical or negative. In addition, each CT was assessed for diagnostic quality (optimal or suboptimal) and presence of artefacts. Artefacts were frequent (367/841), often related to respiratory motion (344/367 chest CT exams with artefacts) and resulted in suboptimal evaluation in mid-to-lower lungs (176/344) or the entire lung (31/344). There were substantial differences in CT usage, patient weight, CTDIvol and DLP across the participating sites.
Collapse
|
32
|
Suri JS, Agarwal S, Carriero A, Paschè A, Danna PSC, Columbu M, Saba L, Viskovic K, Mehmedović A, Agarwal S, Gupta L, Faa G, Singh IM, Turk M, Chadha PS, Johri AM, Khanna NN, Mavrogeni S, Laird JR, Pareek G, Miner M, Sobel DW, Balestrieri A, Sfikakis PP, Tsoulfas G, Protogerou A, Misra DP, Agarwal V, Kitas GD, Teji JS, Al-Maini M, Dhanjil SK, Nicolaides A, Sharma A, Rathore V, Fatemi M, Alizad A, Krishnan PR, Nagy F, Ruzsa Z, Gupta A, Naidu S, Paraskevas KI, Kalra MK. COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts. Diagnostics (Basel) 2021; 11:diagnostics11122367. [PMID: 34943603 PMCID: PMC8699928 DOI: 10.3390/diagnostics11122367] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2021] [Revised: 11/29/2021] [Accepted: 12/13/2021] [Indexed: 02/07/2023] Open
Abstract
(1) Background: COVID-19 computed tomography (CT) lung segmentation is critical for COVID lung severity diagnosis. Earlier proposed approaches during 2020–2021 were semiautomated or automated but not accurate, user-friendly, and industry-standard benchmarked. The proposed study compared the COVID Lung Image Analysis System, COVLIAS 1.0 (GBTI, Inc., and AtheroPointTM, Roseville, CA, USA, referred to as COVLIAS), against MedSeg, a web-based Artificial Intelligence (AI) segmentation tool, where COVLIAS uses hybrid deep learning (HDL) models for CT lung segmentation. (2) Materials and Methods: The proposed study used 5000 ITALIAN COVID-19 positive CT lung images collected from 72 patients (experimental data) that confirmed the reverse transcription-polymerase chain reaction (RT-PCR) test. Two hybrid AI models from the COVLIAS system, namely, VGG-SegNet (HDL 1) and ResNet-SegNet (HDL 2), were used to segment the CT lungs. As part of the results, we compared both COVLIAS and MedSeg against two manual delineations (MD 1 and MD 2) using (i) Bland–Altman plots, (ii) Correlation coefficient (CC) plots, (iii) Receiver operating characteristic curve, and (iv) Figure of Merit and (v) visual overlays. A cohort of 500 CROATIA COVID-19 positive CT lung images (validation data) was used. A previously trained COVLIAS model was directly applied to the validation data (as part of Unseen-AI) to segment the CT lungs and compare them against MedSeg. (3) Result: For the experimental data, the four CCs between COVLIAS (HDL 1) vs. MD 1, COVLIAS (HDL 1) vs. MD 2, COVLIAS (HDL 2) vs. MD 1, and COVLIAS (HDL 2) vs. MD 2 were 0.96, 0.96, 0.96, and 0.96, respectively. The mean value of the COVLIAS system for the above four readings was 0.96. CC between MedSeg vs. MD 1 and MedSeg vs. MD 2 was 0.98 and 0.98, respectively. Both had a mean value of 0.98. On the validation data, the CC between COVLIAS (HDL 1) vs. MedSeg and COVLIAS (HDL 2) vs. MedSeg was 0.98 and 0.99, respectively. For the experimental data, the difference between the mean values for COVLIAS and MedSeg showed a difference of <2.5%, meeting the standard of equivalence. The average running times for COVLIAS and MedSeg on a single lung CT slice were ~4 s and ~10 s, respectively. (4) Conclusions: The performances of COVLIAS and MedSeg were similar. However, COVLIAS showed improved computing time over MedSeg.
Collapse
Affiliation(s)
- Jasjit S. Suri
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA; (I.M.S.); (P.S.C.)
- Advanced Knowledge Engineering Centre, Global Biomedical Technologies, Inc., Roseville, CA 95661, USA; (S.A.); (S.A.); (L.G.)
- Correspondence: ; Tel.: +1-(916)-749-5628
| | - Sushant Agarwal
- Advanced Knowledge Engineering Centre, Global Biomedical Technologies, Inc., Roseville, CA 95661, USA; (S.A.); (S.A.); (L.G.)
- Department of Computer Science Engineering, Pranveer Singh Institute of Technology, Kanpur 209305, India
| | - Alessandro Carriero
- Department of Radiology, “Maggiore della Carità” Hospital, University of Piemonte Orientale (UPO), 28100 Novara, Italy;
| | - Alessio Paschè
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy; (A.P.); (P.S.C.D.); (M.C.); (L.S.); (A.B.)
| | - Pietro S. C. Danna
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy; (A.P.); (P.S.C.D.); (M.C.); (L.S.); (A.B.)
| | - Marta Columbu
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy; (A.P.); (P.S.C.D.); (M.C.); (L.S.); (A.B.)
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy; (A.P.); (P.S.C.D.); (M.C.); (L.S.); (A.B.)
| | - Klaudija Viskovic
- Department of Radiology and Ultrasound, University Hospital for Infectious Diseases, 10 000 Zagreb, Croatia; (K.V.); (A.M.)
| | - Armin Mehmedović
- Department of Radiology and Ultrasound, University Hospital for Infectious Diseases, 10 000 Zagreb, Croatia; (K.V.); (A.M.)
| | - Samriddhi Agarwal
- Advanced Knowledge Engineering Centre, Global Biomedical Technologies, Inc., Roseville, CA 95661, USA; (S.A.); (S.A.); (L.G.)
- Department of Computer Science Engineering, Pranveer Singh Institute of Technology, Kanpur 209305, India
| | - Lakshya Gupta
- Advanced Knowledge Engineering Centre, Global Biomedical Technologies, Inc., Roseville, CA 95661, USA; (S.A.); (S.A.); (L.G.)
| | - Gavino Faa
- Department of Pathology, AOU of Cagliari, 09124 Cagliari, Italy;
| | - Inder M. Singh
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA; (I.M.S.); (P.S.C.)
| | - Monika Turk
- The Hanse-Wissenschaftskolleg Institute for Advanced Study, 27753 Delmenhorst, Germany;
| | - Paramjit S. Chadha
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA; (I.M.S.); (P.S.C.)
| | - Amer M. Johri
- Department of Medicine, Division of Cardiology, Queen’s University, Kingston, ON K7L 3N6, Canada;
| | - Narendra N. Khanna
- Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi 110076, India;
| | - Sophie Mavrogeni
- Cardiology Clinic, Onassis Cardiac Surgery Center, 17674 Athens, Greece;
| | - John R. Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St Helena, CA 94574, USA;
| | - Gyan Pareek
- Minimally Invasive Urology Institute, Brown University, Providence, RI 02912, USA; (G.P.); (D.W.S.)
| | - Martin Miner
- Men’s Health Center, Miriam Hospital, Providence, RI 02906, USA;
| | - David W. Sobel
- Minimally Invasive Urology Institute, Brown University, Providence, RI 02912, USA; (G.P.); (D.W.S.)
| | - Antonella Balestrieri
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 09124 Cagliari, Italy; (A.P.); (P.S.C.D.); (M.C.); (L.S.); (A.B.)
| | - Petros P. Sfikakis
- Rheumatology Unit, National Kapodistrian University of Athens, 15772 Athens, Greece;
| | - George Tsoulfas
- Department of Surgery, Aristoteleion University of Thessaloniki, 54124 Thessaloniki, Greece;
| | - Athanasios Protogerou
- Cardiovascular Prevention and Research Unit, Department of Pathophysiology, National & Kapodistrian University of Athens, 15772 Athens, Greece;
| | - Durga Prasanna Misra
- Department of Immunology, Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow 226014, India; (D.P.M.); (V.A.)
| | - Vikas Agarwal
- Department of Immunology, Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow 226014, India; (D.P.M.); (V.A.)
| | - George D. Kitas
- Academic Affairs, Dudley Group NHS Foundation Trust, Dudley DY1 2HQ, UK;
- Arthritis Research UK Epidemiology Unit, Manchester University, Manchester M13 9PL, UK
| | - Jagjit S. Teji
- Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL 60611, USA;
| | - Mustafa Al-Maini
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON L4Z 4C4, Canada;
| | | | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre and University of Nicosia Medical School, Nicosia 2408, Cyprus;
| | - Aditya Sharma
- Division of Cardiovascular Medicine, University of Virginia, Charlottesville, VA 22904, USA;
| | - Vijay Rathore
- AtheroPoint LLC, Roseville, CA 95611, USA; (S.K.D.); (V.R.)
| | - Mostafa Fatemi
- Department of Physiology & Biomedical Engg., Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA;
| | - Azra Alizad
- Department of Radiology, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA;
| | | | - Ferenc Nagy
- Internal Medicine Department, University of Szeged, 6725 Szeged, Hungary;
| | - Zoltan Ruzsa
- Invasive Cardiology Division, University of Szeged, 6725 Szeged, Hungary;
| | - Archna Gupta
- Radiology Department, Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow 226014, India;
| | - Subbaram Naidu
- Electrical Engineering Department, University of Minnesota, Duluth, MN 55812, USA;
| | | | - Mannudeep K. Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, USA;
| |
Collapse
|
33
|
Suri JS, Agarwal S, Elavarthi P, Pathak R, Ketireddy V, Columbu M, Saba L, Gupta SK, Faa G, Singh IM, Turk M, Chadha PS, Johri AM, Khanna NN, Viskovic K, Mavrogeni S, Laird JR, Pareek G, Miner M, Sobel DW, Balestrieri A, Sfikakis PP, Tsoulfas G, Protogerou A, Misra DP, Agarwal V, Kitas GD, Teji JS, Al-Maini M, Dhanjil SK, Nicolaides A, Sharma A, Rathore V, Fatemi M, Alizad A, Krishnan PR, Ferenc N, Ruzsa Z, Gupta A, Naidu S, Kalra MK. Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography. Diagnostics (Basel) 2021; 11:2025. [PMID: 34829372 PMCID: PMC8625039 DOI: 10.3390/diagnostics11112025] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Revised: 10/26/2021] [Accepted: 10/27/2021] [Indexed: 02/05/2023] Open
Abstract
Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.
Collapse
Affiliation(s)
- Jasjit S. Suri
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA; (I.M.S.); (P.S.C.)
- Advanced Knowledge Engineering Centre, GBTI, Roseville, CA 95661, USA; (S.A.); (P.E.)
| | - Sushant Agarwal
- Advanced Knowledge Engineering Centre, GBTI, Roseville, CA 95661, USA; (S.A.); (P.E.)
- Department of Computer Science Engineering, PSIT, Kanpur 209305, India
| | - Pranav Elavarthi
- Advanced Knowledge Engineering Centre, GBTI, Roseville, CA 95661, USA; (S.A.); (P.E.)
- Thomas Jefferson High School for Science and Technology, Alexandria, VA 22312, USA
| | - Rajesh Pathak
- Department of Computer Science Engineering, Rawatpura Sarkar University, Raipur 492001, India;
| | | | - Marta Columbu
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 10015 Cagliari, Italy; (M.C.); (L.S.); (A.B.)
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 10015 Cagliari, Italy; (M.C.); (L.S.); (A.B.)
| | - Suneet K. Gupta
- Department of Computer Science, Bennett University, Noida 201310, India;
| | - Gavino Faa
- Department of Pathology, Azienda Ospedaliero Universitaria (A.O.U.), 10015 Cagliari, Italy;
| | - Inder M. Singh
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA; (I.M.S.); (P.S.C.)
| | - Monika Turk
- The Hanse-Wissenschaftskolleg Institute for Advanced Study, 27753 Delmenhorst, Germany;
| | - Paramjit S. Chadha
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA; (I.M.S.); (P.S.C.)
| | - Amer M. Johri
- Department of Medicine, Division of Cardiology, Queen’s University, Kingston, ON K7L 3N6, Canada;
| | - Narendra N. Khanna
- Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi 110076, India;
| | | | - Sophie Mavrogeni
- Cardiology Clinic, Onassis Cardiac Surgery Center, 10558 Athens, Greece;
| | - John R. Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA 94574, USA;
| | - Gyan Pareek
- Minimally Invasive Urology Institute, Brown University, Providence, RI 02912, USA; (G.P.); (D.W.S.)
| | - Martin Miner
- Men’s Health Center, Miriam Hospital, Providence, RI 02906, USA;
| | - David W. Sobel
- Minimally Invasive Urology Institute, Brown University, Providence, RI 02912, USA; (G.P.); (D.W.S.)
| | - Antonella Balestrieri
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), 10015 Cagliari, Italy; (M.C.); (L.S.); (A.B.)
| | - Petros P. Sfikakis
- Rheumatology Unit, National & Kapodistrian University of Athens, 10679 Athens, Greece;
| | - George Tsoulfas
- Aristoteleion University of Thessaloniki, 54636 Thessaloniki, Greece;
| | | | - Durga Prasanna Misra
- Department of Immunology, Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow 226014, India; (D.P.M.); (V.A.)
| | - Vikas Agarwal
- Department of Immunology, Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow 226014, India; (D.P.M.); (V.A.)
| | - George D. Kitas
- Academic Affairs, Dudley Group NHS Foundation Trust, Dudley DY1 2HQ, UK;
- Arthritis Research UK Epidemiology Unit, Manchester University, Manchester M13 9PT, UK
| | - Jagjit S. Teji
- Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL 60611, USA;
| | - Mustafa Al-Maini
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON L4Z 4C4, Canada;
| | | | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre, University of Nicosia Medical School, Nicosia 2368, Cyprus;
| | - Aditya Sharma
- Division of Cardiovascular Medicine, University of Virginia, Charlottesville, VA 22904, USA;
| | - Vijay Rathore
- AtheroPoint LLC, Roseville, CA 95611, USA; (S.K.D.); (V.R.)
| | - Mostafa Fatemi
- Department of Physiology & Biomedical Engineering, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA;
| | - Azra Alizad
- Department of Radiology, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA;
| | | | - Nagy Ferenc
- Internal Medicine Department, University of Szeged, 6725 Szeged, Hungary;
| | - Zoltan Ruzsa
- Zoltan Invasive Cardiology Division, University of Szeged, 6725 Szeged, Hungary;
| | - Archna Gupta
- Radiology Department, Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow 226014, India;
| | - Subbaram Naidu
- Electrical Engineering Department, University of Minnesota, Duluth, MN 55812, USA;
| | - Mannudeep K. Kalra
- Department of Radiology, Massachusetts General Hospital, 55 Fruit Street, Boston, MA 02114, USA;
| |
Collapse
|
34
|
Bai T, Wang B, Nguyen D, Wang B, Dong B, Cong W, Kalra MK, Jiang S. Deep Interactive Denoiser (DID) for X-Ray Computed Tomography. IEEE Trans Med Imaging 2021; 40:2965-2975. [PMID: 34329156 DOI: 10.1109/tmi.2021.3101241] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
Low-dose computed tomography (LDCT) is desirable for both diagnostic imaging and image-guided interventions. Denoisers are widely used to improve the quality of LDCT. Deep learning (DL)-based denoisers have shown state-of-the-art performance and are becoming mainstream methods. However, there are two challenges to using DL-based denoisers: 1) a trained model typically does not generate different image candidates with different noise-resolution tradeoffs, which are sometimes needed for different clinical tasks; and 2) the model's generalizability might be an issue when the noise level in the testing images differs from that in the training dataset. To address these two challenges, in this work, we introduce a lightweight optimization process that can run on top of any existing DL-based denoiser during the testing phase to generate multiple image candidates with different noise-resolution tradeoffs suitable for different clinical tasks in real time. Consequently, our method allows users to interact with the denoiser to efficiently review various image candidates and quickly pick the desired one; thus, we termed this method deep interactive denoiser (DID). Experimental results demonstrated that DID can deliver multiple image candidates with different noise-resolution tradeoffs and shows great generalizability across various network architectures, as well as training and testing datasets with various noise levels.
Collapse
|
35
|
Ebrahimian S, Digumarthy SR, Bizzo B, Primak A, Zimmermann M, Tarbiah MM, Kalra MK, Dreyer KJ. Artificial Intelligence has Similar Performance to Subjective Assessment of Emphysema Severity on Chest CT. Acad Radiol 2021; 29:1189-1195. [PMID: 34657812 DOI: 10.1016/j.acra.2021.09.007] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2021] [Revised: 09/03/2021] [Accepted: 09/06/2021] [Indexed: 12/12/2022]
Abstract
RATIONALE AND OBJECTIVES To compare an artificial intelligence (AI)-based prototype and subjective grading for predicting disease severity in patients with emphysema. METHODS Our IRB approved HIPAA-compliant study included 113 adults (71±8 years; 47 females, 66 males) who had both non-contrast chest CT and pulmonary function tests performed within a span of 2 months. The disease severity was classified based on the forced expiratory volume in 1 second (FEV1 as % of predicted) into mild, moderate, and severe. 2 thoracic radiologists (RA), blinded to the clinical and AI results, graded severity of emphysema on a 5-point scale suggested by the Fleischner Society for each lobe. The whole lung scores were derived from the summation of lobar scores. Thin-section CT images were processed with the AI-Rad Companion Chest prototype (Siemens Healthineers) to quantify low attenuation areas (LAA < - 950 HU) in whole lung and each lobe separately. Bronchial abnormality was assessed by both radiologists and a fully automated software (Philips Healthcare). RESULTS Both AI (AUC of 0.77; 95% CI: 0.68 - 0.85) and RA (AUC: 0.76, 95% CI: 0.65 - 0.84) emphysema quantification could differentiate mild, moderate, and severe disease based on FEV1. There was a strong positive correlation between AI and RA (r = 0.72 - 0.80; p <0.001). The combination of emphysema and bronchial abnormality quantification from radiologists' and AI assessment could differentiate between different severities with AUC of 0.80 - 0.82 and 0.87, respectively. CONCLUSION The assessed AI-prototypes can predict the disease severity in patients with emphysema with the same predictive value as the radiologists.
Collapse
|
36
|
Mulligan KM, Zheng DX, Narang J, Eversman A, Kalra MK, Morgan F, Obi EE, Osei-Koomson W, Russell ER, Wei AH, Sharma TR. The effect of COVID-19-related changes on geographical outcomes in the 2021 dermatology residency match. Clin Exp Dermatol 2021; 47:445-447. [PMID: 34560815 PMCID: PMC8653266 DOI: 10.1111/ced.14946] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2021] [Revised: 09/20/2021] [Accepted: 09/23/2021] [Indexed: 11/30/2022]
Affiliation(s)
- K M Mulligan
- Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - D X Zheng
- Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - J Narang
- Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH, USA
| | - A Eversman
- Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - M K Kalra
- Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - F Morgan
- Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH, USA
| | - E E Obi
- Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - W Osei-Koomson
- Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH, USA
| | - E R Russell
- Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - A H Wei
- Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH, USA
| | - T R Sharma
- Case Western Reserve University School of Medicine, Cleveland, OH, USA.,Department of Dermatology, University Hospitals Cleveland Medical Center, Case Western Reserve University, Cleveland, OH, USA
| |
Collapse
|
37
|
Bernardo MO, Homayounieh F, Ebrahimian S, de Melo Tapajós JS, de Moura Carvalho LC, Varella R, Khoury HJ, Kalra MK. PRACTICAL CHALLENGES WITH IMAGING COVID-19 IN BRAZIL: MITIGATION IN AND BEYOND THE PANDEMIC. Radiat Prot Dosimetry 2021; 195:92-98. [PMID: 34386818 PMCID: PMC8385955 DOI: 10.1093/rpd/ncab121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/19/2021] [Revised: 06/23/2021] [Accepted: 07/21/2021] [Indexed: 06/13/2023]
Abstract
UNLABELLED Computed tomography (CT) provides useful information in patients with known or suspected COVID-19 infection. However, there are substantial variations and challenges in scanner technologies and scan practices that have negative effect on the image quality and can increase radiation dose associated with CT. OBJECTIVE In this article, we present major issues and challenges with use of CT at five Brazilian CT facilities for imaging patients with known or suspected COVID-19 infection and offer specific mitigating strategies. METHODS Observational, retrospective and prospective study of five CT facilities from different states and regions of Brazil, with approval of research and ethics committees. RESULTS The most important issues include frequent use of CT, lack of up-to-date and efficient scanner technologies, over-scanning and patient off-centring. Mitigating strategies can include updating scanner technology and improving scan practices.
Collapse
Affiliation(s)
- Mônica O Bernardo
- Pontificia University Catholic of São Paulo, São Paulo, Brazil
- Hospital Miguel Soeiro—UNIMED, Sorocaba, São Paulo, Brazil
| | - Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | | | | | | | - Helen Jamil Khoury
- Hospital das Clínicas—Federal University of Pernambuco, Recife, Pernambuco, Brazil
| | | |
Collapse
|
38
|
Homayounieh F, Digumarthy SR, Febbo JA, Garrana S, Nitiwarangkul C, Singh R, Khera RD, Gilman M, Kalra MK. Comparison of Baseline, Bone-Subtracted, and Enhanced Chest Radiographs for Detection of Pneumothorax. Can Assoc Radiol J 2021; 72:519-524. [DOI: 10.1177/0846537120908852] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/01/2023] Open
Abstract
Purpose: To assess and compare detectability of pneumothorax on unprocessed baseline, single-energy, bone-subtracted, and enhanced frontal chest radiographs (chest X-ray, CXR). Method and Materials: Our retrospective institutional review board–approved study included 202 patients (mean age 53 ± 24 years; 132 men, 70 women) who underwent frontal CXR and had trace, moderate, large, or tension pneumothorax. All patients (except those with tension pneumothorax) had concurrent chest computed tomography (CT). Two radiologists reviewed the CXR and chest CT for pneumothorax on baseline CXR (ground truth). All baseline CXR were processed to generate bone-subtracted and enhanced images (ClearRead X-ray). Four radiologists (R1-R4) assessed the baseline, bone-subtracted, and enhanced images and recorded the presence of pneumothorax (side, size, and confidence for detection) for each image type. Area under the curve (AUC) was calculated with receiver operating characteristic analyses to determine the accuracy of pneumothorax detection. Results: Bone-subtracted images (AUC: 0.89-0.97) had the lowest accuracy for detection of pneumothorax compared to the baseline (AUC: 0.94-0.97) and enhanced (AUC: 0.96-0.99) radiographs ( P < .01). Most false-positive and false-negative pneumothoraces were detected on the bone-subtracted images and the least numbers on the enhanced radiographs. Highest detection rates and confidence were noted for the enhanced images (empiric AUC for R1-R4 0.96-0.99). Conclusion: Enhanced CXRs are superior to bone-subtracted and unprocessed radiographs for detection of pneumothorax. Clinical Relevance/Application: Enhanced CXRs improve detection of pneumothorax over unprocessed images; bone-subtracted images must be cautiously reviewed to avoid false negatives.
Collapse
Affiliation(s)
- Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Subba R. Digumarthy
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Jennifer A. Febbo
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Sherief Garrana
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Chayanin Nitiwarangkul
- Department of Diagnostic and Therapeutic Radiology, Ramathibodi Hospital, Mahidol University, Bangkok, Thailand
| | - Ramandeep Singh
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Ruhani Doda Khera
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Matthew Gilman
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Mannudeep K. Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| |
Collapse
|
39
|
Fang W, Wu D, Kim K, Kalra MK, Singh R, Li L, Li Q. Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior. Phys Med Biol 2021; 66. [PMID: 34126602 DOI: 10.1088/1361-6560/ac0afd] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2021] [Accepted: 06/14/2021] [Indexed: 11/11/2022]
Abstract
Compared to conventional computed tomography (CT), spectral CT can provide the capability of material decomposition, which can be used in many clinical diagnosis applications. However, the decomposed images can be very noisy due to the dose limit in CT scanning and the noise magnification of the material decomposition process. To alleviate this situation, we proposed an iterative one-step inversion material decomposition algorithm with a Noise2Noise prior. The algorithm estimated material images directly from projection data and used a Noise2Noise prior for denoising. In contrast to supervised deep learning methods, the designed Noise2Noise prior was built based on self-supervised learning and did not need external data for training. In our method, the data consistency term and the Noise2Noise network were alternatively optimized in the iterative framework, respectively, using a separable quadratic surrogate (SQS) and the Adam algorithm. The proposed iterative algorithm was validated and compared to other methods on simulated spectral CT data, preclinical photon-counting CT data and clinical dual-energy CT data. Quantitative analysis showed that our proposed method performs promisingly on noise suppression and structure detail recovery.
Collapse
Affiliation(s)
- Wei Fang
- Department of Engineering Physics, Tsinghua University, Beijing, 100084, People's Republic of China.,Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America
| | - Dufan Wu
- Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America.,Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America
| | - Kyungsang Kim
- Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America.,Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America
| | - Ramandeep Singh
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America
| | - Liang Li
- Department of Engineering Physics, Tsinghua University, Beijing, 100084, People's Republic of China
| | - Quanzheng Li
- Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America.,Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, United States of America
| |
Collapse
|
40
|
Homayounieh F, Yan P, Digumarthy SR, Kruger U, Wang G, Kalra MK. Prediction of Coronary Calcification and Stenosis: Role of Radiomics From Low-Dose CT. Acad Radiol 2021; 28:972-979. [PMID: 34217490 DOI: 10.1016/j.acra.2020.09.021] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2020] [Revised: 09/25/2020] [Accepted: 09/26/2020] [Indexed: 12/20/2022]
Abstract
RATIONALE AND OBJECTIVES We aimed to assess relationship between single-click, whole heart radiomics from low-dose computed tomography (LDCT) for lung cancer screening with coronary artery calcification and stenosis. MATERIALS AND METHODS The institutional review board-approved, retrospective study included all 106 patients (68 men, 38 women, mean age 64 ± 7 years) who underwent both LDCT for lung cancer screening and had calcium scoring and coronary computed tomography angiography in our institution. We recorded the clinical variables including patients' demographics, smoking history, family history, and lipid profiles. Coronary calcium scores and grading of coronary stenosis were recorded from the radiology information system. We calculated the multiethnic scores for atherosclerosis risk scores to obtain 10-year coronary heart disease (MESA 10-Y CHD) risk of cardiovascular disease for all patients. Deidentified LDCT exams were exported to a Radiomics prototype for automatic heart segmentation, and derivation of radiomics. Data were analyzed using multiple logistic regression and kernel Fisher discriminant analyses. RESULTS Whole heart radiomics were better than the clinical variables for differentiating subjects with different Agatston scores (≤400 and >400) (area under the curve [AUC] 0.92 vs 0.69). Prediction of coronary stenosis and MESA 10-Y CHD risk was better on whole heart radiomics (AUC:0.86-0.87) than with clinical variables (AUC:0.69-0.79). Addition of clinical variables or visual assessment of coronary calcification from LDCT to whole heart radiomics resulted in a modest change in the AUC. CONCLUSION Single-click, whole heart radiomics obtained from LDCT for lung cancer screening can differentiate patients with different Agatston and MESA risk scores for cardiovascular diseases.
Collapse
Affiliation(s)
- Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Room 248, Boston, MA 02114.
| | - Pingkun Yan
- Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Tory, New York
| | - Subba R Digumarthy
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Room 248, Boston, MA 02114
| | - Uwe Kruger
- Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Tory, New York
| | - Ge Wang
- Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Tory, New York
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Room 248, Boston, MA 02114
| |
Collapse
|
41
|
Arru C, Ebrahimian S, Falaschi Z, Hansen JV, Pasche A, Lyhne MD, Zimmermann M, Durlak F, Mitschke M, Carriero A, Nielsen-Kudsk JE, Kalra MK, Saba L. Comparison of deep learning, radiomics and subjective assessment of chest CT findings in SARS-CoV-2 pneumonia. Clin Imaging 2021; 80:58-66. [PMID: 34246044 PMCID: PMC8247202 DOI: 10.1016/j.clinimag.2021.06.036] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2021] [Revised: 06/23/2021] [Accepted: 06/28/2021] [Indexed: 12/20/2022]
Abstract
Purpose Comparison of deep learning algorithm, radiomics and subjective assessment of chest CT for predicting outcome (death or recovery) and intensive care unit (ICU) admission in patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Methods The multicenter, ethical committee-approved, retrospective study included non-contrast-enhanced chest CT of 221 SARS-CoV-2 positive patients from Italy (n = 196 patients; mean age 64 ± 16 years) and Denmark (n = 25; mean age 69 ± 13 years). A thoracic radiologist graded presence, type and extent of pulmonary opacities and severity of motion artifacts in each lung lobe on all chest CTs. Thin-section CT images were processed with CT Pneumonia Analysis Prototype (Siemens Healthineers) which yielded segmentation masks from a deep learning (DL) algorithm to derive features of lung abnormalities such as opacity scores, mean HU, as well as volume and percentage of all-attenuation and high-attenuation (opacities >−200 HU) opacities. Separately, whole lung radiomics were obtained for all CT exams. Analysis of variance and multiple logistic regression were performed for data analysis. Results Moderate to severe respiratory motion artifacts affected nearly one-quarter of chest CTs in patients. Subjective severity assessment, DL-based features and radiomics predicted patient outcome (AUC 0.76 vs AUC 0.88 vs AUC 0.83) and need for ICU admission (AUC 0.77 vs AUC 0.0.80 vs 0.82). Excluding chest CT with motion artifacts, the performance of DL-based and radiomics features improve for predicting ICU admission. Conclusion DL-based and radiomics features of pulmonary opacities from chest CT were superior to subjective assessment for differentiating patients with favorable and adverse outcomes.
Collapse
Affiliation(s)
- Chiara Arru
- Massachusetts General Hospital, 55 Fruit Street, Boston, MA, USA
| | - Shadi Ebrahimian
- Massachusetts General Hospital, 55 Fruit Street, Boston, MA, USA.
| | | | - Jacob Valentin Hansen
- Department of Cardiology, Department of Clinical Medicine, Aarhus University Hospital, Palle Juul Jensens Boulevard 99, 8200 Aarhus N, Denmark.
| | | | - Mads Dam Lyhne
- Department of Cardiology, Department of Clinical Medicine, Aarhus University Hospital, Palle Juul Jensens Boulevard 99, 8200 Aarhus N, Denmark.
| | | | - Felix Durlak
- Siemens Healthcare GmbH, Diagnostic Imaging, Erlangen, Germany.
| | | | | | - Jens Erik Nielsen-Kudsk
- Department of Cardiology, Department of Clinical Medicine, Aarhus University Hospital, Palle Juul Jensens Boulevard 99, 8200 Aarhus N, Denmark
| | | | - Luca Saba
- Azienda Ospedaliera Universitaria di Cagliari, Cagliari, Italy
| |
Collapse
|
42
|
Moore CL, Bhargavan-Chatfield M, Shaw MM, Weisenthal K, Kalra MK. Radiation Dose Reduction in Kidney Stone CT: A Randomized, Facility-Based Intervention. J Am Coll Radiol 2021; 18:1394-1404. [PMID: 34115990 DOI: 10.1016/j.jacr.2021.05.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2021] [Revised: 05/05/2021] [Accepted: 05/11/2021] [Indexed: 10/21/2022]
Abstract
OBJECTIVE Kidney stones are common, tend to recur, and afflict a young population. Despite evidence and recommendations, adoption of reduced-radiation dose CT (RDCT) for kidney stone CT (KSCT) is slow. We sought to design and test an intervention to improve adoption of RDCT protocols for KSCT using a randomized facility-based intervention. METHODS Facilities contributing at least 40 KSCTs to the American College of Radiology dose index registry (DIR) during calendar year 2015 were randomized to intervention or control groups. The Dose Optimization for Stone Evaluation intervention included customized CME modules, personalized consultation, and protocol recommendations for RDCT. Dose length product (DLP) of all KSCTs was recorded at baseline (2015) and compared with 2017, 2018, and 2019. Change in mean DLP was compared between facilities that participated (intervened-on), facilities randomized to intervention that did not participate (intervened-off), and control facilities. Difference-in-difference between intervened-on and control facilities is reported before and after intervention. RESULTS Of 314 eligible facilities, 155 were randomized to intervention and 159 to control. There were 25 intervened-on facilities, 71 intervened-off facilities, and 96 control facilities. From 2015 to 2017, there was a drop of 110 mGy ∙ cm (a 16% reduction) in the mean DLP in the intervened-on group, which was significantly lower compared with the control group (P < .05). The proportion of RDCTs increased for each year in the intervened-on group relative to the other groups for all 3 years (P < .01). DISCUSSION The Dose Optimization for Stone Evaluation intervention resulted in a significant (P < .05) and persistent reduction in mean radiation doses for engaged facilities performing KSCTs.
Collapse
Affiliation(s)
- Christopher L Moore
- Chief, Ultrasound Section, Department of Emergency Medicine, Yale University School of Medicine, New Haven, Connecticut.
| | | | - Melissa M Shaw
- Yale University School of Medicine, New Haven, Connecticut
| | | | | |
Collapse
|
43
|
Kalra MK, Rehani MM. Five-star rating system for acceptable quality and dose in CT. Eur Radiol 2021; 31:9161-9163. [PMID: 34114057 DOI: 10.1007/s00330-021-08112-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2021] [Revised: 05/20/2021] [Accepted: 05/28/2021] [Indexed: 11/24/2022]
Abstract
KEY POINTS • Recent papers have shown examples of the methodology involved in integrating image quality with radiation dose and assessing acceptable quality dose (AQD).• As a further step in that direction, translating a 5-point score into a 5-star rating shall be helpful for wider and uniform application and shall be in line with the popular use of the 5-star rating.
Collapse
Affiliation(s)
- Mannudeep K Kalra
- Massachusetts General Hospital, 55 Fruit Str, Boston, MA, 02114, USA
| | - Madan M Rehani
- Massachusetts General Hospital, 55 Fruit Str, Boston, MA, 02114, USA. .,Radiology Department, Massachusetts General Hospital, 175 Cambridge Str., Suite 244, Boston, MA, 02114, USA.
| |
Collapse
|
44
|
Yoo H, Lee SH, Arru CD, Doda Khera R, Singh R, Siebert S, Kim D, Lee Y, Park JH, Eom HJ, Digumarthy SR, Kalra MK. AI-based improvement in lung cancer detection on chest radiographs: results of a multi-reader study in NLST dataset. Eur Radiol 2021; 31:9664-9674. [PMID: 34089072 DOI: 10.1007/s00330-021-08074-7] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2021] [Revised: 03/20/2021] [Accepted: 05/17/2021] [Indexed: 01/17/2023]
Abstract
OBJECTIVE Assess if deep learning-based artificial intelligence (AI) algorithm improves reader performance for lung cancer detection on chest X-rays (CXRs). METHODS This reader study included 173 images from cancer-positive patients (n = 98) and 346 images from cancer-negative patients (n = 196) selected from National Lung Screening Trial (NLST). Eight readers, including three radiology residents, and five board-certified radiologists, participated in the observer performance test. AI algorithm provided image-level probability of pulmonary nodule or mass on CXRs and a heatmap of detected lesions. Reader performance was compared with AUC, sensitivity, specificity, false-positives per image (FPPI), and rates of chest CT recommendations. RESULTS With AI, the average sensitivity of readers for the detection of visible lung cancer increased for residents, but was similar for radiologists compared to that without AI (0.61 [95% CI, 0.55-0.67] vs. 0.72 [95% CI, 0.66-0.77], p = 0.016 for residents, and 0.76 [95% CI, 0.72-0.81] vs. 0.76 [95% CI, 0.72-0.81, p = 1.00 for radiologists), while false-positive findings per image (FPPI) was similar for residents, but decreased for radiologists (0.15 [95% CI, 0.11-0.18] vs. 0.12 [95% CI, 0.09-0.16], p = 0.13 for residents, and 0.24 [95% CI, 0.20-0.29] vs. 0.17 [95% CI, 0.13-0.20], p < 0.001 for radiologists). With AI, the average rate of chest CT recommendation in patients positive for visible cancer increased for residents, but was similar for radiologists (54.7% [95% CI, 48.2-61.2%] vs. 70.2% [95% CI, 64.2-76.2%], p < 0.001 for residents and 72.5% [95% CI, 68.0-77.1%] vs. 73.9% [95% CI, 69.4-78.3%], p = 0.68 for radiologists), while that in cancer-negative patients was similar for residents, but decreased for radiologists (11.2% [95% CI, 9.6-13.1%] vs. 9.8% [95% CI, 8.0-11.6%], p = 0.32 for residents and 16.4% [95% CI, 14.7-18.2%] vs. 11.7% [95% CI, 10.2-13.3%], p < 0.001 for radiologists). CONCLUSIONS AI algorithm can enhance the performance of readers for the detection of lung cancers on chest radiographs when used as second reader. KEY POINTS • Reader study in the NLST dataset shows that AI algorithm had sensitivity benefit for residents and specificity benefit for radiologists for the detection of visible lung cancer. • With AI, radiology residents were able to recommend more chest CT examinations (54.7% vs 70.2%, p < 0.001) for patients with visible lung cancer. • With AI, radiologists recommended significantly less proportion of unnecessary chest CT examinations (16.4% vs. 11.7%, p < 0.001) in cancer-negative patients.
Collapse
Affiliation(s)
| | | | - Chiara Daniela Arru
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Boston, MA, 02114, USA.,Harvard Medical School, Boston, MA, USA
| | - Ruhani Doda Khera
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Boston, MA, 02114, USA.,Harvard Medical School, Boston, MA, USA
| | - Ramandeep Singh
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Boston, MA, 02114, USA.,Harvard Medical School, Boston, MA, USA
| | - Sean Siebert
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Boston, MA, 02114, USA.,Harvard Medical School, Boston, MA, USA
| | - Dohoon Kim
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | - Yuna Lee
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | - Ju Hyun Park
- Suwon Total Healthcare Center, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Youngin-si, Gyeongi-do, 16954, Korea
| | - Hye Joung Eom
- Cheju Halla General Hospital, 65 Doryeong-ro, Yeon-dong, Jeju-si, Jeju-do, Korea
| | - Subba R Digumarthy
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Boston, MA, 02114, USA.,Harvard Medical School, Boston, MA, USA
| | - Mannudeep K Kalra
- Division of Thoracic Imaging, Department of Radiology, Massachusetts General Hospital, 75 Blossom Court, Boston, MA, 02114, USA. .,Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
45
|
Gong K, Wu D, Arru CD, Homayounieh F, Neumark N, Guan J, Buch V, Kim K, Bizzo BC, Ren H, Tak WY, Park SY, Lee YR, Kang MK, Park JG, Carriero A, Saba L, Masjedi M, Talari H, Babaei R, Mobin HK, Ebrahimian S, Guo N, Digumarthy SR, Dayan I, Kalra MK, Li Q. A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records. Eur J Radiol 2021; 139:109583. [PMID: 33846041 PMCID: PMC7863774 DOI: 10.1016/j.ejrad.2021.109583] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2020] [Revised: 01/28/2021] [Accepted: 02/01/2021] [Indexed: 12/31/2022]
Abstract
PURPOSE As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease of 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based on their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients' electronic health records (EHR), which included vital signs and laboratory data, with deep learning- and CT-based severity prediction. METHOD We first developed a CT segmentation network using datasets from multiple institutions worldwide. Two biomarkers were extracted from the CT images: total opacity ratio (TOR) and consolidation ratio (CR). After obtaining TOR and CR, further prognosis analysis was conducted on datasets from INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3. For each data cohort, generalized linear model (GLM) was applied for prognosis prediction. RESULTS For the deep learning model, the correlation coefficient of the network prediction and manual segmentation was 0.755, 0.919, and 0.824 for the three cohorts, respectively. The AUC (95 % CI) of the final prognosis models was 0.85(0.77,0.92), 0.93(0.87,0.98), and 0.86(0.75,0.94) for INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3 cohorts, respectively. Either TOR or CR exist in all three final prognosis models. Age, white blood cell (WBC), and platelet (PLT) were chosen predictors in two cohorts. Oxygen saturation (SpO2) was a chosen predictor in one cohort. CONCLUSION The developed deep learning method can segment lung infection regions. Prognosis results indicated that age, SpO2, CT biomarkers, PLT, and WBC were the most important prognostic predictors of COVID-19 in our prognosis model.
Collapse
Affiliation(s)
- Kuang Gong
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Dufan Wu
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Chiara Daniela Arru
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Nir Neumark
- MGH & BWH Center for Clinical Data Science, Boston, United States
| | | | - Varun Buch
- MGH & BWH Center for Clinical Data Science, Boston, United States
| | - Kyungsang Kim
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | | | - Hui Ren
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Won Young Tak
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | - Soo Young Park
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | - Yu Rim Lee
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | - Min Kyu Kang
- Department of Internal Medicine, Yeungnam University College of Medicine, Daegu, South Korea
| | - Jung Gil Park
- Department of Internal Medicine, Yeungnam University College of Medicine, Daegu, South Korea
| | - Alessandro Carriero
- Radiologia, Azienda Ospedaliera Universitaria Maggiore della Carità, Novara, Italy
| | - Luca Saba
- Radiologia, Azienda Ospedaliera Universitaria Policlinico di Monserrato, Italy
| | - Mahsa Masjedi
- Department of Radiology, Kashan University of Medical Sciences, Kashan, Iran
| | - Hamidreza Talari
- Department of Radiology, Kashan University of Medical Sciences, Kashan, Iran
| | - Rosa Babaei
- Department of Radiology, Firoozgar Hospital, Iran University of Medical Sciences, Tehran, Iran
| | - Hadi Karimi Mobin
- Department of Radiology, Firoozgar Hospital, Iran University of Medical Sciences, Tehran, Iran
| | - Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Ning Guo
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Subba R Digumarthy
- Department of Radiology, Massachusetts General Hospital, Boston, United States
| | - Ittai Dayan
- MGH & BWH Center for Clinical Data Science, Boston, United States
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, United States.
| | - Quanzheng Li
- Department of Radiology, Massachusetts General Hospital, Boston, United States.
| |
Collapse
|
46
|
Chao H, Shan H, Homayounieh F, Singh R, Khera RD, Guo H, Su T, Wang G, Kalra MK, Yan P. Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography. Nat Commun 2021; 12:2963. [PMID: 34017001 PMCID: PMC8137697 DOI: 10.1038/s41467-021-23235-4] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2020] [Accepted: 04/20/2021] [Indexed: 12/14/2022] Open
Abstract
Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation.
Collapse
Affiliation(s)
- Hanqing Chao
- Department of Biomedical Engineering, Biomedical Imaging Center, Rensselaer Polytechnic Institute, Troy, NY, USA
| | - Hongming Shan
- Department of Biomedical Engineering, Biomedical Imaging Center, Rensselaer Polytechnic Institute, Troy, NY, USA
| | - Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Ramandeep Singh
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Ruhani Doda Khera
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Hengtao Guo
- Department of Biomedical Engineering, Biomedical Imaging Center, Rensselaer Polytechnic Institute, Troy, NY, USA
| | - Timothy Su
- Niskayuna High School, Niskayuna, NY, USA
| | - Ge Wang
- Department of Biomedical Engineering, Biomedical Imaging Center, Rensselaer Polytechnic Institute, Troy, NY, USA.
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
| | - Pingkun Yan
- Department of Biomedical Engineering, Biomedical Imaging Center, Rensselaer Polytechnic Institute, Troy, NY, USA.
| |
Collapse
|
47
|
Homayounieh F, Doda Khera R, Bizzo BC, Ebrahimian S, Primak A, Schmidt B, Saini S, Kalra MK. Prediction of burden and management of renal calculi from whole kidney radiomics: a multicenter study. Abdom Radiol (NY) 2021; 46:2097-2106. [PMID: 33242099 PMCID: PMC7690335 DOI: 10.1007/s00261-020-02865-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2020] [Revised: 11/06/2020] [Accepted: 11/11/2020] [Indexed: 12/19/2022]
Abstract
Purpose To assess if autosegmentation-assisted radiomics can predict disease burden, hydronephrosis, and treatment strategies in patients with renal calculi. Methods The local ethical committee-approved, retrospective study included 202 adult patients (mean age: 53 ± 17 years; male: 103; female: 99) who underwent clinically indicated, non-contrast abdomen-pelvis CT for suspected or known renal calculi. All CT examinations were reviewed to determine the presence (n = 123 patients) or absence (n = 79) of renal calculi. On CT images with renal calculi, each kidney stone was annotated and measured (maximum dimension, Hounsfield unit (HU), and combined and dominant stone volumes) using a HU threshold-based segmentation. We recorded the presence of hydronephrosis, number of renal calculi, and treatment strategies. Deidentified CT images were processed with the radiomics prototype (Radiomics, Frontier, Siemens Healthineers), which automatically segmented each kidney to obtain 1690 first-, shape-, and higher-order radiomics. Data were analyzed using multiple logistic regression analysis with areas under the curve (AUC) as output. Results Among 202 patients, only 28 patients (18%) needed procedural treatment (lithotripsy or ureteroscopic stone extraction). Gray-level co-occurrence matrix (GLCM) and gray-level run length matrix (GLRLM) differentiated patients with and without procedural treatment (AUC 0.91, 95% CI 0.85–0.92). Higher-order radiomics (gray-level size zone matrix – GLSZM) differentiated kidneys with and without hydronephrosis (AUC: 0.99, p < 0.001) as well those with different stone volumes (AUC up to 0.89, 95% CI 0.89–0.92). Conclusion Automated segmentation and radiomics of entire kidneys can assess hydronephrosis presence, stone burden, and treatment strategies for renal calculi with AUCs > 0.85.
Collapse
|
48
|
Ebrahimian S, Oliveira Bernardo M, Alberto Moscatelli A, Tapajos J, Leitão Tapajós L, Jamil Khoury H, Babaei R, Karimi Mobin H, Mohseni I, Arru C, Carriero A, Falaschi Z, Pasche A, Saba L, Homayounieh F, Bizzo BC, Vassileva J, Kalra MK. Investigating centering, scan length, and arm position impact on radiation dose across 4 countries from 4 continents during pandemic: Mitigating key radioprotection issues. Phys Med 2021; 84:125-131. [PMID: 33894582 PMCID: PMC8058535 DOI: 10.1016/j.ejmp.2021.04.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/09/2021] [Revised: 03/24/2021] [Accepted: 04/01/2021] [Indexed: 12/15/2022] Open
Abstract
Purpose Optimization of CT scan practices can help achieve and maintain optimal radiation protection. The aim was to assess centering, scan length, and positioning of patients undergoing chest CT for suspected or known COVID-19 pneumonia and to investigate their effect on associated radiation doses. Methods With respective approvals from institutional review boards, we compiled CT imaging and radiation dose data from four hospitals belonging to four countries (Brazil, Iran, Italy, and USA) on 400 adult patients who underwent chest CT for suspected or known COVID-19 pneumonia between April 2020 and August 2020. We recorded patient demographics and volume CT dose index (CTDIvol) and dose length product (DLP). From thin-section CT images of each patient, we estimated the scan length and recorded the first and last vertebral bodies at the scan start and end locations. Patient mis-centering and arm position were recorded. Data were analyzed with analysis of variance (ANOVA). Results The extent and frequency of patient mis-centering did not differ across the four CT facilities (>0.09). The frequency of patients scanned with arms by their side (11–40% relative to those with arms up) had greater mis-centering and higher CTDIvol and DLP at 2/4 facilities (p = 0.027–0.05). Despite lack of variations in effective diameters (p = 0.14), there were significantly variations in scan lengths, CTDIvol and DLP across the four facilities (p < 0.001). Conclusions Mis-centering, over-scanning, and arms by the side are frequent issues with use of chest CT in COVID-19 pneumonia and are associated with higher radiation doses.
Collapse
Affiliation(s)
- Shadi Ebrahimian
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, MA, USA
| | - Monica Oliveira Bernardo
- Hospital Miguel Soeiro - UNIMED, Pontificia University Catholic of São Paulo - PUC-SP, Sorocaba, São Paulo, Brazil
| | - Antônio Alberto Moscatelli
- Hospital Miguel Soeiro - UNIMED, Pontificia University Catholic of São Paulo - PUC-SP, Sorocaba, São Paulo, Brazil
| | - Juliana Tapajos
- Hospital Delphina Rinaldi Abdel Aziz, Manaus, Amazonas, Brazil
| | | | - Helen Jamil Khoury
- Nuclear Energy Department, Federal University of Pernambuco, Recife, Pernambuco, Brazil
| | - Rosa Babaei
- Department of Radiology, Firoozgar Hospital, Iran University of Medical Sciences, Tehran, Iran
| | - Hadi Karimi Mobin
- Department of Radiology, Firoozgar Hospital, Iran University of Medical Sciences, Tehran, Iran
| | - Iman Mohseni
- Department of Radiology, Firoozgar Hospital, Iran University of Medical Sciences, Tehran, Iran
| | - Chiara Arru
- Azienda Ospedaliera Universitaria di Cagliari, Cagliari, Italy
| | | | | | | | - Luca Saba
- Azienda Ospedaliera Universitaria di Cagliari, Cagliari, Italy
| | - Fatemeh Homayounieh
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, MA, USA
| | - Bernardo C Bizzo
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, MA, USA
| | - Jenia Vassileva
- Radiation Protection of Patients Unit, International Atomic Energy Agency, Vienna, Austria
| | - Mannudeep K Kalra
- Department of Radiology, Massachusetts General Hospital and the Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
49
|
Singh R, Kalra MK, Homayounieh F, Nitiwarangkul C, McDermott S, Little BP, Lennes IT, Shepard JAO, Digumarthy SR. Artificial intelligence-based vessel suppression for detection of sub-solid nodules in lung cancer screening computed tomography. Quant Imaging Med Surg 2021; 11:1134-1143. [PMID: 33816155 DOI: 10.21037/qims-20-630] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Background Lung cancer screening (LCS) with low-dose computed tomography (LDCT) helps early lung cancer detection, commonly presenting as small pulmonary nodules. Artificial intelligence (AI)-based vessel suppression (AI-VS) and automatic detection (AI-AD) algorithm can improve detection of subsolid nodules (SSNs) on LDCT. We assessed the impact of AI-VS and AI-AD in detection and classification of SSNs [ground-glass nodules (GGNs) and part-solid nodules (PSNs)], on LDCT performed for LCS. Methods Following regulatory approval, 123 LDCT examinations with sub-solid pulmonary nodules (average diameter ≥6 mm) were processed to generate three image series for each examination-unprocessed, AI-VS, and AI-AD series with annotated lung nodules. Two thoracic radiologists in consensus formed the standard of reference (SOR) for this study. Two other thoracic radiologists (R1 and R2; 5 and 10 years of experience in thoracic CT image interpretation) independently assessed the unprocessed images alone, then together with AI-VS series, and finally with AI-AD for detecting all ≥6 mm GGN and PSN. We performed receiver operator characteristics (ROC) and Cohen's Kappa analyses for statistical analyses. Results On unprocessed images, R1 and R2 detected 232/310 nodules (R1: 114 GGN, 118 PSN) and 255/310 nodules (R2: 122 GGN, 133 PSN), respectively (P>0.05). On AI-VS images, they detected 249/310 nodules (119 GGN, 130 PSN) and 277/310 nodules (128 GGN, 149 PSN), respectively (P≥0.12). When compared to the SOR, accuracy (AUC) for detection of PSN on the AI-VS images (AUC 0.80-0.81) was greater than on the unprocessed images (AUC 0.70-0.76). AI-VS images enabled detection of solid components in five nodules deemed as GGN on the unprocessed images. Accuracy of AI-AD was lower than both the radiologists (AUC 0.60-0.72). Conclusions AI-VS improved the detection and classification of SSN into GGN and PSN on LDCT of the chest for the two radiologist (R1 and R2) readers.
Collapse
Affiliation(s)
- Ramandeep Singh
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA
| | - Mannudeep K Kalra
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA
| | - Fatemeh Homayounieh
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA
| | - Chayanin Nitiwarangkul
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA.,Division of Diagnostic Radiology, Department of Diagnostic and Therapeutic Radiology, Faculty of Medicine, Ramathibodi Hospital, Mahidol University, Ratchathewi, Bangkok, Thailand
| | - Shaunagh McDermott
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA
| | - Brent P Little
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA
| | - Inga T Lennes
- Harvard Medical School, Boston, MA, USA.,Massachusetts General Hospital Cancer Center, Division of Thoracic Oncology, Massachusetts General Hospital, Boston, MA, USA
| | - Jo-Anne O Shepard
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA
| | - Subba R Digumarthy
- Division of Thoracic Imaging and Intervention, Massachusetts General Hospital, Boston, MA, USA.,Harvard Medical School, Boston, MA, USA
| |
Collapse
|
50
|
Kalra MK, Ebrahimian S. Quantitative Chest CT in COPD: Can Deep Learning Enable the Transition? Radiol Cardiothorac Imaging 2021; 3:e210044. [PMID: 33970150 PMCID: PMC8098084 DOI: 10.1148/ryct.2021210044] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2021] [Revised: 02/19/2021] [Accepted: 02/19/2021] [Indexed: 11/11/2022]
Affiliation(s)
- Mannudeep K. Kalra
- From the Division of Thoracic Imaging, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Ct, Boston, MA 02114
| | - Shadi Ebrahimian
- From the Division of Thoracic Imaging, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Ct, Boston, MA 02114
| |
Collapse
|