1
|
Cabrera-León Y, Báez PG, Fernández-López P, Suárez-Araujo CP. Neural Computation-Based Methods for the Early Diagnosis and Prognosis of Alzheimer's Disease Not Using Neuroimaging Biomarkers: A Systematic Review. J Alzheimers Dis 2024:JAD231271. [PMID: 38489188 DOI: 10.3233/jad-231271] [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] [Indexed: 03/17/2024]
Abstract
Background The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too. Background Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future. Methods Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected. Results The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field. Conclusions The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged.
Collapse
Affiliation(s)
- Ylermi Cabrera-León
- Instituto Universitario de Cibernética, Empresa y Sociedad, Universidad de Las Palmas de Gran Canaria, Parque Científico Tecnológico, Campus Universitario de Tafira, Canary Islands, Spain
| | - Patricio García Báez
- Departamento de Ingeniería Informática y de Sistemas, Universidad de La Laguna, Escuela Superior de Ingeniería y Tecnología, San Cristóbal de La Laguna, Canary Islands, Spain
| | - Pablo Fernández-López
- Instituto Universitario de Cibernética, Empresa y Sociedad, Universidad de Las Palmas de Gran Canaria, Parque Científico Tecnológico, Campus Universitario de Tafira, Canary Islands, Spain
| | - Carmen Paz Suárez-Araujo
- Instituto Universitario de Cibernética, Empresa y Sociedad, Universidad de Las Palmas de Gran Canaria, Parque Científico Tecnológico, Campus Universitario de Tafira, Canary Islands, Spain
| |
Collapse
|
2
|
Li C. Editorial: Advances in neuroimaging and its applications on biomedical devices. Front Hum Neurosci 2024; 18:1374203. [PMID: 38454908 PMCID: PMC10917899 DOI: 10.3389/fnhum.2024.1374203] [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] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2024] [Accepted: 02/08/2024] [Indexed: 03/09/2024] Open
Affiliation(s)
- Chen Li
- Research Group for Microscopic Image and Medical Image Analysis, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| |
Collapse
|
3
|
Neff MC, Schaaf J, Noll R, Holtz S, Schütze D, Köhler SM, Müller B, Ahmadi N, von Wagner M, Storf H. Initial User-Centred Design of an AI-Based Clinical Decision Support System for Primary Care. Stud Health Technol Inform 2024; 310:1051-1055. [PMID: 38269975 DOI: 10.3233/shti231125] [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] [Indexed: 01/26/2024]
Abstract
A clinical decision support system based on different methods of artificial intelligence (AI) can support the diagnosis of patients with unclear diseases by providing tentative diagnoses as well as proposals for further steps. In a user-centred-design process, we aim to find out how general practitioners envision the user interface of an AI-based clinical decision support system for primary care. A first user-interface prototype was developed using the task model based on user requirements from preliminary work. Five general practitioners evaluated the prototype in two workshops. The discussion of the prototype resulted in categorized suggestions with key messages for further development of the AI-based clinical decision support system, such as the integration of intelligent parameter requests. The early inclusion of different user feedback facilitated the implementation of a user interface for a user-friendly decision support system.
Collapse
Affiliation(s)
| | - Jannik Schaaf
- Goethe University Frankfurt, University Hospital, Institute of Medical Informatics, Germany
| | - Richard Noll
- Goethe University Frankfurt, University Hospital, Institute of Medical Informatics, Germany
| | - Svea Holtz
- Goethe University Frankfurt, University Hospital, Institute of General Practice, Germany
| | - Dania Schütze
- Goethe University Frankfurt, University Hospital, Institute of General Practice, Germany
| | - Susanne Maria Köhler
- Goethe University Frankfurt, University Hospital, Institute of General Practice, Germany
| | - Beate Müller
- Institute of General Practice, University of Cologne, Germany
| | - Najia Ahmadi
- Institute for Medical Informatics and Biometry, Carl Gustav Carus Faculty of Medicine, Technical University of Dresden, Germany
| | - Michael von Wagner
- Goethe University Frankfurt, University Hospital, Executive Department for medical IT-Systems and digitalization, Germany
| | - Holger Storf
- Goethe University Frankfurt, University Hospital, Institute of Medical Informatics, Germany
| |
Collapse
|
4
|
Ying M, Wang Y, Yang K, Wang H, Liu X. A deep learning knowledge distillation framework using knee MRI and arthroscopy data for meniscus tear detection. Front Bioeng Biotechnol 2024; 11:1326706. [PMID: 38292305 PMCID: PMC10825958 DOI: 10.3389/fbioe.2023.1326706] [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: 10/23/2023] [Accepted: 12/22/2023] [Indexed: 02/01/2024] Open
Abstract
Purpose: To construct a deep learning knowledge distillation framework exploring the utilization of MRI alone or combing with distilled Arthroscopy information for meniscus tear detection. Methods: A database of 199 paired knee Arthroscopy-MRI exams was used to develop a multimodal teacher network and an MRI-based student network, which used residual neural networks architectures. A knowledge distillation framework comprising the multimodal teacher network T and the monomodal student network S was proposed. We optimized the loss functions of mean squared error (MSE) and cross-entropy (CE) to enable the student network S to learn arthroscopic information from the teacher network T through our deep learning knowledge distillation framework, ultimately resulting in a distilled student network S T. A coronal proton density (PD)-weighted fat-suppressed MRI sequence was used in this study. Fivefold cross-validation was employed, and the accuracy, sensitivity, specificity, F1-score, receiver operating characteristic (ROC) curves and area under the receiver operating characteristic curve (AUC) were used to evaluate the medial and lateral meniscal tears detection performance of the models, including the undistilled student model S, the distilled student model S T and the teacher model T. Results: The AUCs of the undistilled student model S, the distilled student model S T, the teacher model T for medial meniscus (MM) tear detection and lateral meniscus (LM) tear detection are 0.773/0.672, 0.792/0.751 and 0.834/0.746, respectively. The distilled student model S T had higher AUCs than the undistilled model S. After undergoing knowledge distillation processing, the distilled student model demonstrated promising results, with accuracy (0.764/0.734), sensitivity (0.838/0.661), and F1-score (0.680/0.754) for both medial and lateral tear detection better than the undistilled one with accuracy (0.734/0.648), sensitivity (0.733/0.607), and F1-score (0.620/0.673). Conclusion: Through the knowledge distillation framework, the student model S based on MRI benefited from the multimodal teacher model T and achieved an improved meniscus tear detection performance.
Collapse
Affiliation(s)
- Mengjie Ying
- Department of Orthopedics, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yufan Wang
- Engineering Research Center for Digital Medicine of the Ministry of Education, Shanghai, China
- School of Biomedical Engineering and Med-X Research Institute, Shanghai Jiao Tong University, Shanghai, China
| | - Kai Yang
- Department of Radiology, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Haoyuan Wang
- Department of Orthopedics, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xudong Liu
- Department of Orthopedics, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| |
Collapse
|
5
|
Eida S, Fukuda M, Katayama I, Takagi Y, Sasaki M, Mori H, Kawakami M, Nishino T, Ariji Y, Sumi M. Metastatic Lymph Node Detection on Ultrasound Images Using YOLOv7 in Patients with Head and Neck Squamous Cell Carcinoma. Cancers (Basel) 2024; 16:274. [PMID: 38254765 PMCID: PMC10813890 DOI: 10.3390/cancers16020274] [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] [Received: 11/23/2023] [Revised: 12/28/2023] [Accepted: 01/04/2024] [Indexed: 01/24/2024] Open
Abstract
Ultrasonography is the preferred modality for detailed evaluation of enlarged lymph nodes (LNs) identified on computed tomography and/or magnetic resonance imaging, owing to its high spatial resolution. However, the diagnostic performance of ultrasonography depends on the examiner's expertise. To support the ultrasonographic diagnosis, we developed YOLOv7-based deep learning models for metastatic LN detection on ultrasonography and compared their detection performance with that of highly experienced radiologists and less experienced residents. We enrolled 462 B- and D-mode ultrasound images of 261 metastatic and 279 non-metastatic histopathologically confirmed LNs from 126 patients with head and neck squamous cell carcinoma. The YOLOv7-based B- and D-mode models were optimized using B- and D-mode training and validation images and their detection performance for metastatic LNs was evaluated using B- and D-mode testing images, respectively. The D-mode model's performance was comparable to that of radiologists and superior to that of residents' reading of D-mode images, whereas the B-mode model's performance was higher than that of residents but lower than that of radiologists on B-mode images. Thus, YOLOv7-based B- and D-mode models can assist less experienced residents in ultrasonographic diagnoses. The D-mode model could raise the diagnostic performance of residents to the same level as experienced radiologists.
Collapse
Affiliation(s)
- Sato Eida
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| | - Motoki Fukuda
- Department of Oral Radiology, Osaka Dental University, 1-5-17 Otemae, Chuo-ku, Osaka 540-0008, Japan; (M.F.); (Y.A.)
| | - Ikuo Katayama
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| | - Yukinori Takagi
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| | - Miho Sasaki
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| | - Hiroki Mori
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| | - Maki Kawakami
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| | - Tatsuyoshi Nishino
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| | - Yoshiko Ariji
- Department of Oral Radiology, Osaka Dental University, 1-5-17 Otemae, Chuo-ku, Osaka 540-0008, Japan; (M.F.); (Y.A.)
| | - Misa Sumi
- Department of Radiology and Biomedical Informatics, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8588, Japan; (S.E.); (I.K.); (Y.T.); (M.S.); (H.M.); (M.K.); (T.N.)
| |
Collapse
|
6
|
Lee SE, Yoon JH, Son NH, Han K, Moon HJ. Screening in Patients With Dense Breasts: Comparison of Mammography, Artificial Intelligence, and Supplementary Ultrasound. AJR Am J Roentgenol 2024; 222:e2329655. [PMID: 37493324 DOI: 10.2214/ajr.23.29655] [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] [Indexed: 07/27/2023]
Abstract
BACKGROUND. Screening mammography has decreased performance in patients with dense breasts. Supplementary screening ultrasound is a recommended option in such patients, although it has yielded mixed results in prior investigations. OBJECTIVE. The purpose of this article is to compare the performance characteristics of screening mammography alone, standalone artificial intelligence (AI), ultrasound alone, and mammography in combination with AI and/or ultrasound in patients with dense breasts. METHODS. This retrospective study included 1325 women (mean age, 53 years) with dense breasts who underwent both screening mammography and supplementary breast ultrasound within a 1-month interval from January 2017 to December 2017; prior mammography and prior ultrasound examinations were available for comparison in 91.2% and 91.8%, respectively. Mammography and ultrasound examinations were interpreted by one of 15 radiologists (five staff; 10 fellows); clinical reports were used for the present analysis. A commercial AI tool was used to retrospectively evaluate mammographic examinations for presence of cancer. Screening performances were compared among mammography, AI, ultrasound, and test combinations, using generalized estimating equations. Benign diagnoses required 24 months or longer of imaging stability. RESULTS. Twelve cancers (six invasive ductal carcinoma; six ductal carcinoma in situ) were diagnosed. Mammography, standalone AI, and ultrasound showed cancer detection rates (per 1000 patients) of 6.0, 6.8, and 6.0 (all p > .05); recall rates of 4.4%, 11.9%, and 9.2% (all p < .05); sensitivity of 66.7%, 75.0%, and 66.7% (all p > .05); specificity of 96.2%, 88.7%, and 91.3% (all p < .05); and accuracy of 95.9%, 88.5%, and 91.1% (all p < .05). Mammography with AI, mammography with ultrasound, and mammography with both ultrasound and AI showed cancer detection rates of 7.5, 9.1, and 9.1 (all p > .05); recall rates of 14.9, 11.7, and 21.4 (all p < .05); sensitivity of 83.3%, 100.0%, and 100.0% (all p > .05); specificity of 85.8%, 89.1%, and 79.4% (all p < .05); and accuracy of 85.7%, 89.2%, and 79.5% (all p < .05). CONCLUSION. Mammography with supplementary ultrasound showed higher accuracy, higher specificity, and lower recall rate in comparison with mammography with AI and in comparison with mammography with both ultrasound and AI. CLINICAL IMPACT. The findings fail to show benefit of AI with respect to screening mammography performed with supplementary breast ultrasound in patients with dense breasts.
Collapse
Affiliation(s)
- Si Eun Lee
- Department of Radiology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Korea
| | - Jung Hyun Yoon
- Department of Radiology, Research Institute of Radiologic Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| | - Nak-Hoon Son
- Department of Statistics, Keimyung University, Daegu, South Korea
| | - Kyunghwa Han
- Department of Radiology, Research Institute of Radiologic Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| | - Hee Jung Moon
- Department of Radiology, Wonju Severance Christian Hospital, Yonsei University Wonju College of Medicine, 20 Ilsan-ro, Wonju 220-701, Korea
| |
Collapse
|
7
|
Tagami M, Nishio M, Katsuyama-Yoshikawa A, Misawa N, Sakai A, Haruna Y, Azumi A, Honda S. Machine Learning Model with Texture Analysis for Automatic Classification of Histopathological Images of Ocular Adnexal Mucosa-associated Lymphoid Tissue Lymphoma of Two Different Origins. Curr Eye Res 2023; 48:1195-1202. [PMID: 37566457 DOI: 10.1080/02713683.2023.2246696] [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: 05/13/2023] [Revised: 08/03/2023] [Accepted: 08/05/2023] [Indexed: 08/12/2023]
Abstract
PURPOSE The purpose of this study was to develop artificial intelligence algorithms that can distinguish between orbital and conjunctival mucosa-associated lymphoid tissue (MALT) lymphomas in pathological images. METHODS Tissue blocks with residual MALT lymphoma and data from histological and flow cytometric studies and molecular genetic analyses such as gene rearrangement were procured for 129 patients treated between April 2008 and April 2020. We collected pathological hematoxylin and eosin-stained (HE) images of lymphoma from these patients and cropped 10 different image patches at a resolution of 2048 × 2048 from pathological images from each patient. A total of 990 images from 99 patients were used to create and evaluate machine-learning models. Each image patch of three different magnification rates at ×4, ×20, and ×40 underwent texture analysis to extract features, and then seven different machine-learning algorithms were applied to the results to create models. Cross-validation on a patient-by-patient basis was used to create and evaluate models, and then 300 images from the remaining 30 cases were used to evaluate the average accuracy rate. RESULTS Ten-fold cross-validation using the support vector machine with linear kernel algorithm was identified as the best algorithm for discriminating between conjunctival mucosa-associated lymphoid tissue and orbital MALT lymphomas, with an average accuracy rate under cross-validation of 85%. There were ×20 magnification HE images that were more accurate in distinguishing orbital and conjunctival MALT lymphomas among ×4, ×20, and ×40. CONCLUSION Artificial intelligence algorithms can successfully distinguish HE images between orbital and conjunctival MALT lymphomas.
Collapse
Affiliation(s)
- Mizuki Tagami
- Department of Ophthalmology and Visual Sciences, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
- Ophthalmology Department and Eye Center, Kobe Kaisei Hospital, Kobe, Japan
| | - Mizuho Nishio
- Department of Radiology, Kobe University Graduate School of Medicine, Kobe, Japan
| | | | - Norihiko Misawa
- Department of Ophthalmology and Visual Sciences, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Atsushi Sakai
- Department of Ophthalmology and Visual Sciences, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Yusuke Haruna
- Department of Ophthalmology and Visual Sciences, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Atsushi Azumi
- Ophthalmology Department and Eye Center, Kobe Kaisei Hospital, Kobe, Japan
| | - Shigeru Honda
- Department of Ophthalmology and Visual Sciences, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| |
Collapse
|
8
|
Kindt S, Surmont M. Manual censoring of impedance tracings by the Wingate consensus reduces the number of impedance episodes, impacting on reflux categorization. Neurogastroenterol Motil 2023; 35:e14683. [PMID: 37793130 DOI: 10.1111/nmo.14683] [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: 07/06/2023] [Revised: 09/14/2023] [Accepted: 09/19/2023] [Indexed: 10/06/2023]
Abstract
BACKGROUND The Lyon consensus classifies the evidence of gastroesophageal reflux (GERD) based on endoscopic features and results of pH/impedance monitoring (pH-MII) including the post-reflux swallow-induced peristaltic wave index (PSPWI) and mean nocturnal baseline impedance (MNBI). The Wingate consensus established criteria to reduce inter-reviewer variability when assessing reflux episodes and PSPWI by impedance. This study aims to assess the influence of the Wingate criteria on the different pH-MII parameters obtained by automated analysis. METHODS Thirty consecutive pH-MII off PPI were reviewed according to Wingate criteria. Number of impedance episodes and PSPWI were compared before and after censoring from automatic analysis. Reflux categorization according to Lyon consensus between censored and uncensored data was compared. Pearson correlations between impedance parameters and censored episodes were calculated. KEY RESULTS Censoring the tracings significantly reduced the number of reflux episodes (66 [42-90.25] vs. 44.5 [21.5-61.5], p = 0.0105). Reasons for censoring were as follows: 1/ anterograde episode: 9.5 [6-13], 2/ impedance drop <50%: 1 [0-3], 3/ duration <4 s: 1 [0-2], 4/ <2 distal channels: 2.5 [1-4], and 5/ artifacts: 2 [1-5]. Censored episodes were in majority non-acid (16.5 [13-26.5] vs. 2 [0-4], p < 0.00001). Censoring altered the categorization of impedance episodes (<40 episodes, 6 vs. 13 for resp. uncensored vs. censored tracings, 40-80 episodes: 13 vs. 13, and >80 episodes: 11 vs. 4, p = 0.0264), but not the symptom index, the symptom association probability, or the categorization according to the Lyon consensus. Nevertheless, individual tracings were affected. The percentage of censored episodes was inversely correlated with the number of acidic impedance episodes (r = -0.62, p = 0.0002). CONCLUSION AND INFERENCES Manual interpretation of impedance tracings based on the Wingate consensus reduces the number of impedance episodes, impacting on reflux categorization. Acidic reflux episodes are less likely to be censored, harboring a potential at improving automatic pH-MII analysis.
Collapse
Affiliation(s)
- Sébastien Kindt
- Department of Gastroenterology and Hepatology, UZ Brussel, Vrije Universiteit Brussel, Brussels, Belgium
| | - Magali Surmont
- Department of Gastroenterology and Hepatology, UZ Brussel, Vrije Universiteit Brussel, Brussels, Belgium
| |
Collapse
|
9
|
Dick K, Humber J, Ducharme R, Dingwall-Harvey A, Armour CM, Hawken S, Walker MC. The Transformative Potential of AI in Obstetrics and Gynaecology. J Obstet Gynaecol Can 2023:102277. [PMID: 37951574 DOI: 10.1016/j.jogc.2023.102277] [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: 08/24/2023] [Revised: 10/24/2023] [Accepted: 10/25/2023] [Indexed: 11/14/2023]
Abstract
The transformative power of artificial intelligence (AI) is reshaping diverse domains of medicine. Recent progress, catalyzed by computing advancements, has seen commensurate adoption of AI technologies within obstetrics and gynaecology. We explore the use and potential of AI in three focus areas: predictive modelling for pregnancy complications, Deep learning-based image interpretation for precise diagnoses, and large language models enabling intelligent health care assistants. We also provide recommendations for the ethical implementation, governance of AI, and promote research into AI explainability, which are crucial for responsible AI integration and deployment. AI promises a revolutionary era of personalized health care in obstetrics and gynaecology.
Collapse
Affiliation(s)
- Kevin Dick
- Children's Hospital of Eastern Ontario Research Institute, Ottawa, ON
| | - James Humber
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON
| | - Robin Ducharme
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON
| | - Alysha Dingwall-Harvey
- Children's Hospital of Eastern Ontario Research Institute, Ottawa, ON; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON
| | - Christine M Armour
- Children's Hospital of Eastern Ontario Research Institute, Ottawa, ON; Department of Pediatrics, University of Ottawa, Ottawa, ON; Prenatal Screening Ontario, Better Outcomes Registry and Network, Ottawa, ON
| | - Steven Hawken
- Children's Hospital of Eastern Ontario Research Institute, Ottawa, ON; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON; School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON; ICES, Toronto, ON
| | - Mark C Walker
- Children's Hospital of Eastern Ontario Research Institute, Ottawa, ON; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON; School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON; ICES, Toronto, ON; Department of Obstetrics and Gynecology, University of Ottawa, Ottawa, ON; International and Global Health Office, University of Ottawa, Ottawa, ON; BORN Ontario, Children's Hospital of Eastern Ontario, Ottawa, ON; Department of Obstetrics, Gynecology and Newborn Care, The Ottawa Hospital, Ottawa, ON.
| |
Collapse
|
10
|
Van Dieren L, Amar JZ, Geurs N, Quisenaerts T, Gillet C, Delforge B, D'heysselaer LDC, Filip Thiessen EF, Cetrulo CL, Lellouch AG. Unveiling the power of convolutional neural networks in melanoma diagnosis. Eur J Dermatol 2023; 33:495-505. [PMID: 38297925 DOI: 10.1684/ejd.2023.4559] [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] [Indexed: 02/02/2024]
Abstract
Convolutional neural networks are a type of deep learning algorithm. They are mostly applied in visual recognition and can be used for the identification of melanomas. Multiple studies have evaluated the performance of convolutional neural networks, and most algorithms match or even surpass the accuracy of dermatologists. However, only 23.8% of dermatologists have good or excellent knowledge of the topic. We believe that the lack of knowledge physicians experience regarding artificial intelligence is an obstacle to its clinical implementation. We describe how a convolutional neural network differentiates a benign from a malignant lesion. We systematically searched the Web of Science, Medline (PubMed), and The Cochrane Library on the 9th February, 2022. We focused on articles describing the role and use of artificial intelligence in melanoma recognition between 2017 and 2022, using the following MeSH terms: "melanoma," "diagnosis," and "artificial intelligence". Traditional machine learning algorithms comprise different parts which must preprocess, segment, extract features and classify the lesion into benign or malignant. Deep learning algorithms can perform these steps simultaneously, which significantly enhances efficiency. Convolutional neural networks include a convolutional layer, a pooling layer, and a fully connected layer. Convolutional and pooling layers extract features from the lesion and reduce computational power, whereas fully connected layers classify the image into two or more categories. Additionally, we suggest that further studies should be performed to accelerate the clinical implementation of artificial intelligence, to create comprehensive datasets and to generate explainable algorithms.
Collapse
Affiliation(s)
- Loïc Van Dieren
- Faculty of Medicine and Health Sciences, University of Antwerp, Wilrijk, Belgium
| | - Jonathan Z Amar
- Operations Research Center, Massachusetts Institute of Technology, Boston, Massachusetts, USA
| | - Naomi Geurs
- Faculty of Medicine and Health Sciences, University of Antwerp, Wilrijk, Belgium
| | - Tom Quisenaerts
- Faculty of Medicine and Health Sciences, University of Antwerp, Wilrijk, Belgium
| | - Clément Gillet
- Faculty of Electrical Engineering and Computer Science, Technical University of Berlin, Berlin, Germany
| | - Benoit Delforge
- Faculty of Medicine, Katholieke Universiteit Leuven, Leuven, Belgium
| | | | - E F Filip Thiessen
- Department of Plastic, Reconstructive and Aesthetic Surgery, Antwerp University Hospital, Antwerp, Belgium
| | - Curtis L Cetrulo
- Vascularized Composite Allotransplantation Laboratory, Center for Transplantation Sciences, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA, Division of Plastic and Reconstructive Surgery, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Alexandre G Lellouch
- Vascularized Composite Allotransplantation Laboratory, Center for Transplantation Sciences, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA, Division of Plastic and Reconstructive Surgery, Massachusetts General Hospital, Boston, Massachusetts, USA
| |
Collapse
|
11
|
Polat G, Kani HT, Ergenc I, Ozen Alahdab Y, Temizel A, Atug O. Improving the Computer-Aided Estimation of Ulcerative Colitis Severity According to Mayo Endoscopic Score by Using Regression-Based Deep Learning. Inflamm Bowel Dis 2023; 29:1431-1439. [PMID: 36382800 DOI: 10.1093/ibd/izac226] [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: 06/06/2022] [Indexed: 11/18/2022]
Abstract
BACKGROUND Assessment of endoscopic activity in ulcerative colitis (UC) is important for treatment decisions and monitoring disease progress. However, substantial inter- and intraobserver variability in grading impairs the assessment. Our aim was to develop a computer-aided diagnosis system using deep learning to reduce subjectivity and improve the reliability of the assessment. METHODS The cohort comprises 11 276 images from 564 patients who underwent colonoscopy for UC. We propose a regression-based deep learning approach for the endoscopic evaluation of UC according to the Mayo endoscopic score (MES). Five state-of-the-art convolutional neural network (CNN) architectures were used for the performance measurements and comparisons. Ten-fold cross-validation was used to train the models and objectively benchmark them. Model performances were assessed using quadratic weighted kappa and macro F1 scores for full Mayo score classification and kappa statistics and F1 score for remission classification. RESULTS Five classification-based CNNs used in the study were in excellent agreement with the expert annotations for all Mayo subscores and remission classification according to the kappa statistics. When the proposed regression-based approach was used, (1) the performance of most of the models statistically significantly increased and (2) the same model trained on different cross-validation folds produced more robust results on the test set in terms of deviation between different folds. CONCLUSIONS Comprehensive experimental evaluations show that commonly used classification-based CNN architectures have successful performance in evaluating endoscopic disease activity of UC. Integration of domain knowledge into these architectures further increases performance and robustness, accelerating their translation into clinical use.
Collapse
Affiliation(s)
- Gorkem Polat
- Graduate School of Informatics, Middle East Technical University, Ankara, Turkey
- Neuroscience and Neurotechnology Center of Excellence, Middle East Technical University, Ankara, Turkey
| | - Haluk Tarik Kani
- Department of Gastroenterology, School of Medicine, Marmara University, Istanbul, Turkey
| | - Ilkay Ergenc
- Department of Gastroenterology, School of Medicine, Marmara University, Istanbul, Turkey
| | - Yesim Ozen Alahdab
- Department of Gastroenterology, School of Medicine, Marmara University, Istanbul, Turkey
| | - Alptekin Temizel
- Graduate School of Informatics, Middle East Technical University, Ankara, Turkey
- Neuroscience and Neurotechnology Center of Excellence, Middle East Technical University, Ankara, Turkey
| | - Ozlen Atug
- Department of Gastroenterology, School of Medicine, Marmara University, Istanbul, Turkey
| |
Collapse
|
12
|
Zhang J, Li Z, Lin H, Xue M, Wang H, Fang Y, Liu S, Huo T, Zhou H, Yang J, Xie Y, Xie M, Lu L, Liu P, Ye Z. Deep learning assisted diagnosis system: improving the diagnostic accuracy of distal radius fractures. Front Med (Lausanne) 2023; 10:1224489. [PMID: 37663656 PMCID: PMC10471443 DOI: 10.3389/fmed.2023.1224489] [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: 05/17/2023] [Accepted: 08/04/2023] [Indexed: 09/05/2023] Open
Abstract
Objectives To explore an intelligent detection technology based on deep learning algorithms to assist the clinical diagnosis of distal radius fractures (DRFs), and further compare it with human performance to verify the feasibility of this method. Methods A total of 3,240 patients (fracture: n = 1,620, normal: n = 1,620) were included in this study, with a total of 3,276 wrist joint anteroposterior (AP) X-ray films (1,639 fractured, 1,637 normal) and 3,260 wrist joint lateral X-ray films (1,623 fractured, 1,637 normal). We divided the patients into training set, validation set and test set in a ratio of 7:1.5:1.5. The deep learning models were developed using the data from the training and validation sets, and then their effectiveness were evaluated using the data from the test set. Evaluate the diagnostic performance of deep learning models using receiver operating characteristic (ROC) curves and area under the curve (AUC), accuracy, sensitivity, and specificity, and compare them with medical professionals. Results The deep learning ensemble model had excellent accuracy (97.03%), sensitivity (95.70%), and specificity (98.37%) in detecting DRFs. Among them, the accuracy of the AP view was 97.75%, the sensitivity 97.13%, and the specificity 98.37%; the accuracy of the lateral view was 96.32%, the sensitivity 94.26%, and the specificity 98.37%. When the wrist joint is counted, the accuracy was 97.55%, the sensitivity 98.36%, and the specificity 96.73%. In terms of these variables, the performance of the ensemble model is superior to that of both the orthopedic attending physician group and the radiology attending physician group. Conclusion This deep learning ensemble model has excellent performance in detecting DRFs on plain X-ray films. Using this artificial intelligence model as a second expert to assist clinical diagnosis is expected to improve the accuracy of diagnosing DRFs and enhance clinical work efficiency.
Collapse
Affiliation(s)
- Jiayao Zhang
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Zhimin Li
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
| | - Heng Lin
- Department of Orthopedics, Nanzhang People’s Hospital, Nanzhang, China
| | - Mingdi Xue
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Honglin Wang
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Ying Fang
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Songxiang Liu
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Tongtong Huo
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
| | - Hong Zhou
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jiaming Yang
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Yi Xie
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Mao Xie
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lin Lu
- Department of Orthopedics, Renmin Hospital of Wuhan University, Wuhan, China
| | - Pengran Liu
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Zhewei Ye
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Intelligent Medical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|
13
|
Ambrosetti MC, Grecchi A, Ambrosetti A, Amodio A, Mansueto G, Montemezzi S, Zamboni GA. Quantitative Edge Analysis of Pancreatic Margins in Patients with Chronic Pancreatitis: A Correlation with Exocrine Function. Diagnostics (Basel) 2023; 13:2272. [PMID: 37443666 DOI: 10.3390/diagnostics13132272] [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: 05/15/2023] [Revised: 06/23/2023] [Accepted: 06/27/2023] [Indexed: 07/15/2023] Open
Abstract
BACKGROUND Many efforts have been made to improve accuracy and sensitivity in diagnosing chronic pancreatitis (CP), obtaining quantitative assessments related to functional data. Our purpose was to correlate a computer-assisted analysis of pancreatic morphology, focusing on glandular margins, with exocrine function-measured by fecal elastase values-in chronic pancreatitis patients. METHODS We retrospectively reviewed chronic pancreatitis patients who underwent fecal elastase assessment and abdominal MRI in our institute within 1 year. We identified 123 patients divided into three groups based on the fecal elastase value: group A with fecal elastase > 200 μg/g; group B with fecal elastase between 100 and 200 μg/g; and group C with fecal elastase < 100 μg/g. Computer-assisted quantitative edge analysis of pancreatic margins was made on non-contrast-enhanced water-only Dixon T1-weighted images, obtaining the pancreatic margin score (PMS). PMS values were compared across groups using a Kruskal-Wallis test and the correlation between PMS and fecal elastase values was tested with the Spearman's test. RESULTS A significant difference in PMS was observed between the three groups (p < 0.0001), with a significant correlation between PMS and elastase values (r = 0.6080). CONCLUSIONS Quantitative edge analysis may stratify chronic pancreatitis patients according to the degree of exocrine insufficiency, potentially contributing to the morphological and functional staging of this pathology.
Collapse
Affiliation(s)
- Maria Chiara Ambrosetti
- Radiology Unit, Department of Pathology and Diagnostics, Azienda Ospedaliera Universitaria Integrata, 37126 Verona, Italy
| | - Annamaria Grecchi
- Institute of Radiology, Department of Diagnostics and Public Health, Policlinico GB Rossi, University of Verona, 37134 Verona, Italy
| | - Alberto Ambrosetti
- Department of Physics and Astronomy "Galileo Galilei", University of Padova, 35131 Padova, Italy
| | - Antonio Amodio
- Gastroenterology and Digestive Endoscopy Unit, The Pancreas Institute, Department of Medicine, G.B. Rossi University Hospital, 37134 Verona, Italy
| | - Giancarlo Mansueto
- Institute of Radiology, Department of Diagnostics and Public Health, Policlinico GB Rossi, University of Verona, 37134 Verona, Italy
| | - Stefania Montemezzi
- Radiology Unit, Department of Pathology and Diagnostics, Azienda Ospedaliera Universitaria Integrata, 37126 Verona, Italy
| | - Giulia A Zamboni
- Institute of Radiology, Department of Diagnostics and Public Health, Policlinico GB Rossi, University of Verona, 37134 Verona, Italy
| |
Collapse
|
14
|
Dos Santos CEO, Malaman D, Arciniegas Sanmartin ID, Leão ABS, Leão GS, Pereira-Lima JC. Performance of artificial intelligence in the characterization of colorectal lesions. Saudi J Gastroenterol 2023; 29:219-224. [PMID: 37203122 PMCID: PMC10445495 DOI: 10.4103/sjg.sjg_316_22] [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: 07/14/2022] [Accepted: 04/10/2023] [Indexed: 05/20/2023] Open
Abstract
Background Image-enhanced endoscopy (IEE) has been used in the differentiation between neoplastic and non-neoplastic colorectal lesions through microvasculature analysis. This study aimed to evaluate the computer-aided diagnosis (CADx) mode of the CAD EYE system for the optical diagnosis of colorectal lesions and compare it with the performance of an expert, in addition to evaluating the computer-aided detection (CADe) mode in terms of polyp detection rate (PDR) and adenoma detection rate (ADR). Methods A prospective study was conducted to evaluate the performance of CAD EYE using blue light imaging (BLI), dichotomizing lesions into hyperplastic and neoplastic, and of an expert based on the Japan Narrow-Band Imaging Expert Team (JNET) classification for the characterization of lesions. After white light imaging (WLI) diagnosis, magnification was used on all lesions, which were removed and examined histologically. Diagnostic criteria were evaluated, and PDR and ADR were calculated. Results A total of 110 lesions (80 (72.7%) dysplastic lesions and 30 (27.3%) nondysplastic lesions) were evaluated in 52 patients, with a mean lesion size of 4.3 mm. Artificial intelligence (AI) analysis showed 81.8% accuracy, 76.3% sensitivity, 96.7% specificity, 98.5% positive predictive value (PPV), and 60.4% negative predictive value (NPV). The kappa value was 0.61, and the area under the receiver operating characteristic curve (AUC) was 0.87. Expert analysis showed 93.6% accuracy, 92.5% sensitivity, 96.7% specificity, 98.7% PPV, and 82.9% NPV. The kappa value was 0.85, and the AUC was 0.95. Overall, PDR was 67.6% and ADR was 45.9%. Conclusions The CADx mode showed good accuracy in characterizing colorectal lesions, but the expert assessment was superior in almost all diagnostic criteria. PDR and ADR were high.
Collapse
Affiliation(s)
- Carlos E. O. Dos Santos
- Department of Endoscopy, Santa Casa de Caridade Hospital, Bagé, RS, Brazil
- Department of Endoscopy, Pontifícia Universidade Católica do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | - Daniele Malaman
- Department of Endoscopy, Santa Casa de Caridade Hospital, Bagé, RS, Brazil
| | | | - Ari B. S. Leão
- Department of Endoscopy, Pontifícia Universidade Católica do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | - Gabriel S. Leão
- Department of Endoscopy, Pontifícia Universidade Católica do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | - Júlio C. Pereira-Lima
- Department of Gastroenterology and Endoscopy, Santa Casa Hospital, Porto Alegre, RS, Brazil
| |
Collapse
|
15
|
Haugsten ER, Vestergaard T, Trettin B. Experiences Regarding Use and Implementation of Artificial Intelligence-Supported Follow-Up of Atypical Moles at a Dermatological Outpatient Clinic: Qualitative Study. JMIR Dermatol 2023; 6:e44913. [PMID: 37632937 PMCID: PMC10335120 DOI: 10.2196/44913] [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] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2022] [Revised: 04/19/2023] [Accepted: 05/16/2023] [Indexed: 08/28/2023] Open
Abstract
BACKGROUND Artificial intelligence (AI) is increasingly used in numerous medical fields. In dermatology, AI can be used in the form of computer-assisted diagnosis (CAD) systems when assessing and diagnosing skin lesions suspicious of melanoma, a potentially lethal skin cancer with rising incidence all over the world. In particular, CAD may be a valuable tool in the follow-up of patients with high risk of developing melanoma, such as patients with multiple atypical moles. One such CAD system, ATBM Master (FotoFinder), can execute total body dermoscopy (TBD). This process comprises automatically photographing a patient´s entire body and then neatly displaying moles on a computer screen, grouped according to their clinical relevance. Proprietary FotoFinder algorithms underlie this organized presentation of moles. In addition, ATBM Master's optional convoluted neural network (CNN)-based Moleanalyzer Pro software can be used to further assess moles and estimate their probability of malignancy. OBJECTIVE Few qualitative studies have been conducted on the implementation of AI-supported procedures in dermatology. Therefore, the purpose of this study was to investigate how health care providers experience the use and implementation of a CAD system like ATBM Master, in particular its TBD module. In this way, the study aimed to elucidate potential barriers to the application of such new technology. METHODS We conducted a thematic analysis based on 2 focus group interviews with 14 doctors and nurses regularly working in an outpatient pigmented lesions clinic. RESULTS Surprisingly, the study revealed that only 3 participants had actual experience using the TBD module. Even so, all participants were able to provide many notions and anticipations about its use, resulting in 3 major themes emerging from the interviews. First, several organizational matters were revealed to be a barrier to consistent use of the ATBM Master's TBD module, namely lack of guidance, time pressure, and insufficient training. Second, the study found that the perceived benefits of TBD were the ability to objectively detect and monitor subtle lesion changes and unbiasedness of the procedure. Imprecise identification of moles, inability to photograph certain areas, and substandard technical aspects were the perceived weaknesses. Lastly, the study found that clinicians were open to use AI-powered technology and that the TBD module was considered a supplementary tool to aid the medical staff, rather than a replacement of the clinician. CONCLUSIONS Demonstrated by how few of the participants had actual experience with the TBD module, this study showed that implementation of new technology does not occur automatically. It highlights the importance of having a strategy for implementation to ensure the optimized application of CAD tools. The study identified areas that could be improved when implementing AI-powered technology, as well as providing insight on how medical staff anticipated and experienced the use of a CAD device in dermatology.
Collapse
Affiliation(s)
- Elisabeth Rygvold Haugsten
- Department of Dermatology and Allergy Centre, Odense University Hospital, Odense, Denmark
- Faculty of Health Sciences, University of Southern Denmark, Odense, Denmark
| | - Tine Vestergaard
- Department of Dermatology and Allergy Centre, Odense University Hospital, Odense, Denmark
| | - Bettina Trettin
- Department of Dermatology and Allergy Centre, Odense University Hospital, Odense, Denmark
- Faculty of Health Sciences, University of Southern Denmark, Odense, Denmark
| |
Collapse
|
16
|
Lewandowski N, Koller B. Transforming medical sciences with high-performance computing, high-performance data analytics and AI. Technol Health Care 2023:THC237000. [PMID: 37355917 DOI: 10.3233/thc-237000] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/26/2023]
Abstract
The advance of high-performance computing (HPC), high-performance data analytics (HPDA) and AI and their synergetic integration into workflows has revolutionized numerous industries, amongst others the medical and pharmaceutical sectors. In this special section of Technology and Health Care, we delve into the remarkable advancements and potential of HPC, HPDA and AI (together termed HPC+) in driving innovation, improving patient outcomes, and accelerating drug discovery. The articles in this issue shed light onto the potential of HPC+ in addressing several critical areas, including medical imaging, personalized medicine, drug discovery, and clinical as well as political decision support.
Collapse
|
17
|
Taylor AT, Fazlur Rahman A, Folks RD, Moncayo V, Savir-Baruch B, Plaxton N, Polsani A, Halkar RK, Dubovsky EV, Garcia EV, Manatunga A. Computer assisted interpretation of Tc-99m mercaptoacetyltriglycine diuretic scintigraphy enhances resident performance. Nucl Med Commun 2023; 44:427-433. [PMID: 37038959 PMCID: PMC10171298 DOI: 10.1097/mnm.0000000000001691] [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] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2023] [Accepted: 03/12/2023] [Indexed: 04/12/2023]
Abstract
OBJECTIVE iRENEX is a software module that incorporates scintigraphic and clinical data to interpret 99m Tc- mercaptoacetyltriglycine (MAG3) diuretic studies and provide reasons for their conclusions. Our objectives were to compare iRENEX interpretations with those of expert physicians, use iRENEX to evaluate resident performance and determine if iRENEX could improve the diagnostic accuracy of experienced residents. METHODS Baseline and furosemide 99m Tc-MAG3 acquisitions of 50 patients with suspected obstruction (mean age ± SD, 58.7 ± 15.8 years, 60% female) were randomly selected from an archived database and independently interpreted by iRENEX, three expert readers and four nuclear medicine residents with one full year of residency. All raters had access to scintigraphic data and a text file containing clinical information and scored each kidney on a scale from +1.0 to -1.0. Scores ≥0.20 represented obstruction with higher scores indicating greater confidence. Scores +0.19 to -0.19 were indeterminate; scores ≤-0.20 indicated no obstruction. Several months later, residents reinterpreted the studies with access to iRENEX. Receiver operating characteristic (ROC) analysis and concordance correlation coefficient (CCC) quantified agreement. RESULTS The CCC among experts was higher than that among residents, 0.84, versus 0.39, respectively, P < 0.001. When residents reinterpreted the studies with iRENEX, their CCC improved from 0.39 to 0.73, P < 0.001. ROC analysis showed significant improvement in the ability of residents to distinguish between obstructed and non-obstructed kidneys using iRENEX ( P = 0.036). CONCLUSION iRENEX interpretations were comparable to those of experts. iRENEX reduced interobserver variability among experienced residents and led to better agreement between resident and expert interpretations.
Collapse
Affiliation(s)
- Andrew T. Taylor
- Department of Radiology and Imaging Sciences, School of Medicine, Emory University, Atlanta, Georgia
| | | | - Russell D. Folks
- Department of Radiology and Imaging Sciences, School of Medicine, Emory University, Atlanta, Georgia
| | - Valeria Moncayo
- Department of Radiology and Imaging Sciences, School of Medicine, Emory University, Atlanta, Georgia
| | - Bital Savir-Baruch
- Department of Radiology and Imaging Sciences, School of Medicine, Emory University, Atlanta, Georgia
| | | | | | - Raghuveer K. Halkar
- Department of Radiology and Imaging Sciences, School of Medicine, Emory University, Atlanta, Georgia
| | - Eva V. Dubovsky
- Department of Radiology, University of Alabama, Birmingham, Alabama
| | - Ernest V. Garcia
- Department of Radiology and Imaging Sciences, School of Medicine, Emory University, Atlanta, Georgia
| | - Amita Manatunga
- Department of Biostatistics and Bioinformatics, School of Public Health, Emory University, Atlanta Georgia, USA
| |
Collapse
|
18
|
Amin MS, Ahn H. FabNet: A Features Agglomeration-Based Convolutional Neural Network for Multiscale Breast Cancer Histopathology Images Classification. Cancers (Basel) 2023; 15:cancers15041013. [PMID: 36831359 PMCID: PMC9954749 DOI: 10.3390/cancers15041013] [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: 01/12/2023] [Revised: 01/31/2023] [Accepted: 01/31/2023] [Indexed: 02/08/2023] Open
Abstract
The definitive diagnosis of histology specimen images is largely based on the radiologist's comprehensive experience; however, due to the fine to the coarse visual appearance of such images, experts often disagree with their assessments. Sophisticated deep learning approaches can help to automate the diagnosis process of the images and reduce the analysis duration. More efficient and accurate automated systems can also increase the diagnostic impartiality by reducing the difference between the operators. We propose a FabNet model that can learn the fine-to-coarse structural and textural features of multi-scale histopathological images by using accretive network architecture that agglomerate hierarchical feature maps to acquire significant classification accuracy. We expand on a contemporary design by incorporating deep and close integration to finely combine features across layers. Our deep layer accretive model structure combines the feature hierarchy in an iterative and hierarchically manner that infers higher accuracy and fewer parameters. The FabNet can identify malignant tumors from images and patches from histopathology images. We assessed the efficiency of our suggested model standard cancer datasets, which included breast cancer as well as colon cancer histopathology images. Our proposed avant garde model significantly outperforms existing state-of-the-art models in respect of the accuracy, F1 score, precision, and sensitivity, with fewer parameters.
Collapse
|
19
|
Aloupogianni E, Ishikawa M, Ichimura T, Hamada M, Murakami T, Sasaki A, Nakamura K, Kobayashi N, Obi T. Effects of dimension reduction of hyperspectral images in skin gross pathology. Skin Res Technol 2023; 29:e13270. [PMID: 36823506 PMCID: PMC10155843 DOI: 10.1111/srt.13270] [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] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Accepted: 12/17/2022] [Indexed: 02/05/2023]
Abstract
BACKGROUND Hyperspectral imaging (HSI) is an emerging modality for the gross pathology of the skin. Spectral signatures of HSI could discriminate malignant from benign tissue. Because of inherent redundancies in HSI and in order to facilitate the use of deep-learning models, dimension reduction is a common preprocessing step. The effects of dimension reduction choice, training scope, and number of retained dimensions have not been evaluated on skin HSI for segmentation tasks. MATERIALS AND METHODS An in-house dataset of HSI signatures from pigmented skin lesions was prepared and labeled with histology. Eleven different dimension reduction methods were used as preprocessing for tumor margin detection with support vector machines. Cluster-wise principal component analysis (ClusterPCA), a new variant of PCA, was proposed. The scope of application for dimension reduction was also investigated. RESULTS The components produced by ClusterPCA show good agreement with the expected optical properties of skin chromophores. Random forest importance performed best during classification. However, all methods suffered from low sensitivity and generalization. CONCLUSION Investigation of more complex reduction and segmentation schemes with emphasis on the nature of HSI and optical properties of the skin is necessary. Insights on dimension reduction for skin tissue could facilitate the development of HSI-based systems for cancer margin detection at gross level.
Collapse
Affiliation(s)
- Eleni Aloupogianni
- Department of Information and Communications EngineeringTokyo Institute of TechnologyYokohamaJapan
| | - Masahiro Ishikawa
- Faculty of Health and Medical CareSaitama Medical University Hidaka CampusHidakaJapan
| | - Takaya Ichimura
- Department of PathologyFaculty of MedicineSaitama Medical University Moroyama CampusMoroyamaJapan
| | - Mei Hamada
- Department of PathologyFaculty of MedicineSaitama Medical University Moroyama CampusMoroyamaJapan
| | - Takuo Murakami
- Department of DermatologyFaculty of MedicineSaitama Medical University Moroyama CampusMoroyamaJapan
| | - Atsushi Sasaki
- Department of PathologyFaculty of MedicineSaitama Medical University Moroyama CampusMoroyamaJapan
| | - Koichiro Nakamura
- Department of DermatologyFaculty of MedicineSaitama Medical University Moroyama CampusMoroyamaJapan
| | - Naoki Kobayashi
- Department of Information and Communications EngineeringTokyo Institute of TechnologyYokohamaJapan
| | - Takashi Obi
- Department of Information and Communications EngineeringTokyo Institute of TechnologyYokohamaJapan
- Institute of Innovative Research, Tokyo Institute of TechnologyTokyoJapan
| |
Collapse
|
20
|
Stanley AL, Edwards TC, Jaere MD, Lex JR, Jones GG. An automated, web-based triage tool may optimise referral pathways in elective orthopaedic surgery: A proof-of-concept study. Digit Health 2023; 9:20552076231152177. [PMID: 36762026 PMCID: PMC9903022 DOI: 10.1177/20552076231152177] [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: 07/19/2022] [Accepted: 01/03/2023] [Indexed: 01/28/2023] Open
Abstract
Introduction Knee pain is caused by various pathologies, making evaluation in primary-care challenging. Subsequently, an over-reliance on imaging, such as radiographs and MRI exists. Electronic-triage tools represent an innovative solution to this problem. The aims of this study were to establish the magnitude of unnecessary knee imaging prior to orthopaedic surgeon referral, and ascertain whether an e-triage tool outperforms existing clinical pathways to recommend correct imaging. Methods Patients ≥18 years presenting with knee pain treated with arthroscopy or arthroplasty at a single academic hospital between 2015 and 2020 were retrospectively identified. The timing and appropriateness of imaging were assessed according to national guidelines, and classified as 'necessary', 'unnecessary' or 'required MRI'. Based on an eDelphi consensus study, a symptom-based e-triage tool was developed and piloted to preliminarily diagnose five common knee pathologies and suggest appropriate imaging. Results 1462 patients were identified. 17.2% (n = 132) of arthroplasty patients received an 'unnecessary MRI', 27.6% (n = 192) of arthroscopy patients did not have a 'necessary MRI', requiring follow-up. Forty-one patients trialled the e-triage pilot (mean age: 58.4 years, 58.5% female). Preliminary diagnoses were available for 33 patients. The e-triage tool correctly identified three of the four knee pathologies (one pathology did not present). 79.2% (n = 19) of participants would use the tool again. Conclusion A substantial number of knee pain patients receive incorrect imaging, incurring delays and unnecessary costs. A symptom-based e-triage tool was developed, with promising performance and user feedback. With refinement using larger datasets, this tool has the potential to improve wait-times, referral quality and reduce cost.
Collapse
Affiliation(s)
| | - Thomas C. Edwards
- Faculty of Medicine, Imperial College London, London, UK,MSk Lab, Imperial College London, London, UK
| | - Martin D. Jaere
- Faculty of Medicine, Imperial College London, London, UK,MSk Lab, Imperial College London, London, UK
| | - Johnathan R. Lex
- Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, Canada
| | - Gareth G. Jones
- Faculty of Medicine, Imperial College London, London, UK,MSk Lab, Imperial College London, London, UK,Gareth G. Jones, MSk Lab, Sir Michael Uren Hub, Imperial College London, White City Campus, 86 Wood Lane, London W12 0BZ, UK.
| |
Collapse
|
21
|
Negev M, Magal T, Kaphzan H. Attitudes of psychiatrists toward telepsychiatry: A policy Delphi study. Digit Health 2023; 9:20552076231177132. [PMID: 37312951 PMCID: PMC10259121 DOI: 10.1177/20552076231177132] [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] [Received: 11/10/2022] [Accepted: 05/04/2023] [Indexed: 06/15/2023] Open
Abstract
Objectives To delineate areas of consensus and disagreements among practicing psychiatrists from various levels of clinical experience, hierarchy and organizations, and to test their ability to converge toward agreement, which will enable better integration of telepsychiatry into mental health services. Methods To study attitudes of Israeli public health psychiatrists, we utilized a policy Delphi method, during the early stages of the COVID pandemic. In-depth interviews were conducted and analyzed, and a questionnaire was generated. The questionnaire was disseminated amongst 49 psychiatrists, in two succeeding rounds, and areas of consensus and controversies were identified. Results Psychiatrists showed an overall consensus regarding issues of economic and temporal advantages of telepsychiatry. However, the quality of diagnosis and treatment and the prospect of expanding the usage of telepsychiatry to normal circumstances-beyond situations of pandemic or emergency were disputed. Nonetheless, efficiency and willingness scales slightly improved during the 2nd round of the Delphi process. Prior experience with telepsychiatry had a strong impact on the attitude of psychiatrists, and those who were familiar with this practice were more favorable toward its usage in their clinic. Conclusions We have delineated experience as a major impact on the attitudes toward telepsychiatry and the willingness for its assimilation in clinical practice as a legitimate and trustworthy method. We have also observed that the organizational affiliation significantly affected psychiatrists' attitude, when those working at local clinics were more positive toward telepsychiatry compared with employees of governmental institutions. This might be related to experience and differences in organizational environment. Taken together, we recommend to include hands-on training of telepsychiatry in medical education curriculum during residency, as well as refresher exercises for attending practitioners.
Collapse
Affiliation(s)
- Maya Negev
- School of Public Health, Faculty of Social Welfare and Health Sciences, University of Haifa, Haifa, Israel
| | - Tamir Magal
- School of Public Health, Faculty of Social Welfare and Health Sciences, University of Haifa, Haifa, Israel
| | - Hanoch Kaphzan
- Department of Neurobiology, Faculty of Natural Sciences, University of Haifa, Haifa, Israel
| |
Collapse
|
22
|
Boissin C. Clinical decision-support for acute burn referral and triage at specialized centres - Contribution from routine and digital health tools. Glob Health Action 2022; 15:2067389. [PMID: 35762795 PMCID: PMC9246103 DOI: 10.1080/16549716.2022.2067389] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
Abstract
BACKGROUND Specialized care is crucial for severe burn injuries whereas minor burns should be handled at point-of-care. Misdiagnosis is common which leads to overburdening the system and to a lack of treatment for others due to resources shortage. OBJECTIVES The overarching aim was to evaluate four decision-support tools for diagnosis, referral, and triage of acute burns injuries in South Africa and Sweden: referral criteria, mortality prediction scores, image-based remote consultation and automated diagnosis. METHODS Study I retrospectively assessed adherence to referral criteria of 1165 patients admitted to the paediatric burns centre of the Western Cape of South Africa. Study II assessed mortality prediction of 372 patients admitted to the adults burns centre by evaluating an existing score (ABSI), and by using logistic regression. In study III, an online survey was used to assess the diagnostic accuracy of burn experts' image-based estimations using their smartphone or tablet. In study IV, two deep-learning algorithms were developed using 1105 acute burn images in order to identify the burn, and to classify burn depth. RESULTS Adherence to referral criteria was of 93.4%, and the age and severity criteria were associated with patient care. In adults, the ABSI score was a good predictor of mortality which affected a fifth of the patients and which was associated with gender, burn size and referral status. Experts were able to diagnose burn size, and burn depth using handheld devices. Finally, both a wound identifier and a depth classifier algorithm could be developed with relatively high accuracy. CONCLUSIONS Altogether the findings inform on the use of four tools along the care trajectory of patients with acute burns by assisting with the diagnosis, referral and triage from point-of-care to burns centres. This will assist with reducing inequities by improving access to the most appropriate care for patients.
Collapse
Affiliation(s)
- Constance Boissin
- Department of Global Public Health, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
23
|
Petty HR. Using Machine Vision of Glycolytic Elements to Predict Breast Cancer Recurrences: Design and Implementation. Metabolites 2022; 13:metabo13010041. [PMID: 36676966 PMCID: PMC9866082 DOI: 10.3390/metabo13010041] [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: 12/03/2022] [Revised: 12/19/2022] [Accepted: 12/23/2022] [Indexed: 12/28/2022] Open
Abstract
A major goal of biomedical research has been the early and quantitative identification of patients who will subsequently experience a cancer recurrence. In this review, I discuss the ability of glycolytic enzyme and transporter patterns within tissues to detect sub-populations of cells within ductal carcinoma in situ (DCIS) lesions that specifically precede cancer recurrences. The test uses conventional formalin fixed paraffin embedded tissue samples. The accuracy of this machine vision test rests on the identification of relevant glycolytic components that promote enhanced glycolysis (phospho-Ser226-glucose transporter type 1 (phospho-Ser226-GLUT1) and phosphofructokinase type L (PFKL)), their trafficking in tumor cells and tissues as judged by computer vision, and their high signal-to-noise levels. For each patient, machine vision stratifies micrographs from each lesion as the probability that the lesion originated from a recurrent sample. This stratification method removes overlap between the predicted recurrent and non-recurrent patients, which eliminates distribution-dependent false positives and false negatives. The method identifies computationally negative samples as non-recurrent and computationally positive samples are recurrent; computationally positive non-recurrent samples are likely due to mastectomies. The early phosphorylation and isoform switching events, spatial locations and clustering constitute important steps in metabolic reprogramming. This work also illuminates mechanistic steps occurring prior to a recurrence, which may contribute to the development of new drugs.
Collapse
Affiliation(s)
- Howard R Petty
- Department of Ophthalmology and Visual Sciences, University of Michigan Medical School, 1000 Wall Street, Ann Arbor, MI 48105, USA
| |
Collapse
|
24
|
Waldenberg C, Eriksson S, Brisby H, Hebelka H, Lagerstrand KM. Detection of Imperceptible Intervertebral Disc Fissures in Conventional MRI-An AI Strategy for Improved Diagnostics. J Clin Med 2022; 12:jcm12010011. [PMID: 36614812 PMCID: PMC9821245 DOI: 10.3390/jcm12010011] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [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: 10/25/2022] [Revised: 11/29/2022] [Accepted: 12/19/2022] [Indexed: 12/24/2022] Open
Abstract
Annular fissures in the intervertebral discs are believed to be closely related to back pain. However, no sensitive non-invasive method exists to detect annular fissures. This study aimed to propose and test a method capable of detecting the presence and position of annular fissures in conventional magnetic resonance (MR) images non-invasively. The method utilizes textural features calculated from conventional MR images combined with attention mapping and artificial intelligence (AI)-based classification models. As ground truth, reference standard computed tomography (CT) discography was used. One hundred twenty-three intervertebral discs in 43 patients were examined with MR imaging followed by discography and CT. The fissure classification model determined the presence of fissures with 100% sensitivity and 97% specificity. Moreover, the true position of the fissures was correctly determined in 90 (87%) of the analyzed discs. Additionally, the proposed method was significantly more accurate at identifying fissures than the conventional radiological high-intensity zone marker. In conclusion, the findings suggest that the proposed method is a promising diagnostic tool to detect annular fissures of importance for back pain and might aid in clinical practice and allow for new non-invasive research related to the presence and position of individual fissures.
Collapse
Affiliation(s)
- Christian Waldenberg
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 413 45 Gothenburg, Sweden
- Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 405 30 Gothenburg, Sweden
- Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, 413 45 Gothenburg, Sweden
- Correspondence:
| | - Stefanie Eriksson
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 413 45 Gothenburg, Sweden
- Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 405 30 Gothenburg, Sweden
- Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, 413 45 Gothenburg, Sweden
| | - Helena Brisby
- Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 405 30 Gothenburg, Sweden
- Department of Orthopaedics, Sahlgrenska University Hospital, 413 45 Gothenburg, Sweden
| | - Hanna Hebelka
- Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 405 30 Gothenburg, Sweden
- Department of Radiology, Sahlgrenska University Hospital, 413 45 Gothenburg, Sweden
| | - Kerstin Magdalena Lagerstrand
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 413 45 Gothenburg, Sweden
- Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, 405 30 Gothenburg, Sweden
- Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, 413 45 Gothenburg, Sweden
| |
Collapse
|
25
|
Ambros-Antemate JF, Reyes-Flores A, Argueta-Figueroa L, Ramírez-Ramírez R, Vargas-Treviño M, Gutiérrez-Gutiérrez J, Mayoral EPC, Pérez-Campos E, Flores-Mejía LA, Torres-Rosas R. Accuracy of machine learning algorithms for the assessment of upper-limb motor impairments in patients with post-stroke hemiparesis: A systematic review and meta-analysis. ADV CLIN EXP MED 2022; 31:1309-1318. [PMID: 36047897 DOI: 10.17219/acem/152596] [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: 03/31/2022] [Revised: 05/25/2022] [Accepted: 08/03/2022] [Indexed: 11/24/2022]
Abstract
BACKGROUND The assessment of motor function is vital in post-stroke rehabilitation protocols, and it is imperative to obtain an objective and quantitative measurement of motor function. There are some innovative machine learning algorithms that can be applied in order to automate the assessment of upper extremity motor function. OBJECTIVES To perform a systematic review and meta-analysis of the efficacy of machine learning algorithms for assessing upper limb motor function in post-stroke patients and compare these algorithms to clinical assessment. MATERIAL AND METHODS The protocol was registered in the International Prospective Register of Systematic Reviews (PROSPERO) database. The review was carried out according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and the Cochrane Handbook for Systematic Reviews of Interventions. The search was performed using 6 electronic databases. The meta-analysis was performed with the data from the correlation coefficients using a random model. RESULTS The initial search yielded 1626 records, but only 8 studies fully met the eligibility criteria. The studies reported strong and very strong correlations between the algorithms tested and clinical assessment. The meta-analysis revealed a lack of homogeneity (I2 = 85.29%, Q = 48.15), which is attributable to the heterogeneity of the included studies. CONCLUSION Automated systems using machine learning algorithms could support therapists in assessing upper extremity motor function in post-stroke patients. However, to draw more robust conclusions, methodological designs that minimize the risk of bias and increase the quality of the methodology of future studies are required.
Collapse
Affiliation(s)
| | - Adriana Reyes-Flores
- School of Medicine and Surgery, Benito Juárez Autonomous University of Oaxaca, Mexico
| | | | | | - Marciano Vargas-Treviño
- School of Biological Systems and Technological Innovation, Benito Juárez Autonomous University of Oaxaca, Mexico
| | - Jaime Gutiérrez-Gutiérrez
- School of Biological Systems and Technological Innovation, Benito Juárez Autonomous University of Oaxaca, Mexico
| | | | - Eduardo Pérez-Campos
- Center for Research UNAM-UABJO, Benito Juárez Autonomous University of Oaxaca, Mexico
| | | | - Rafael Torres-Rosas
- Immunology Laboratory, Cencer for Health and Diseases Sciences Research, School of Dentistry, Benito Juárez Autonomous University of Oaxaca, Mexico
| |
Collapse
|
26
|
Escalé-Besa A, Fuster-Casanovas A, Börve A, Yélamos O, Fustà-Novell X, Esquius Rafat M, Marin-Gomez FX, Vidal-Alaball J. Using Artificial Intelligence as a Diagnostic Decision Support Tool in Skin Disease: Protocol for an Observational Prospective Cohort Study. JMIR Res Protoc 2022. [PMID: 36044249 PMCID: PMC9475422 DOI: 10.2196/37531 ] [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] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/06/2023] Open
Abstract
BACKGROUND Dermatological conditions are a relevant health problem. Each person has an average of 1.6 skin diseases per year, and consultations for skin pathology represent 20% of the total annual visits to primary care and around 35% are referred to a dermatology specialist. Machine learning (ML) models can be a good tool to help primary care professionals, as it can analyze and optimize complex sets of data. In addition, ML models are increasingly being applied to dermatology as a diagnostic decision support tool using image analysis, especially for skin cancer detection and classification. OBJECTIVE This study aims to perform a prospective validation of an image analysis ML model as a diagnostic decision support tool for the diagnosis of dermatological conditions. METHODS In this prospective study, 100 consecutive patients who visit a participant general practitioner (GP) with a skin problem in central Catalonia were recruited. Data collection was planned to last 7 months. Anonymized pictures of skin diseases were taken and introduced to the ML model interface (capable of screening for 44 different skin diseases), which returned the top 5 diagnoses by probability. The same image was also sent as a teledermatology consultation following the current stablished workflow. The GP, ML model, and dermatologist's assessments will be compared to calculate the precision, sensitivity, specificity, and accuracy of the ML model. The results will be represented globally and individually for each skin disease class using a confusion matrix and one-versus-all methodology. The time taken to make the diagnosis will also be taken into consideration. RESULTS Patient recruitment began in June 2021 and lasted for 5 months. Currently, all patients have been recruited and the images have been shown to the GPs and dermatologists. The analysis of the results has already started. CONCLUSIONS This study will provide information about ML models' effectiveness and limitations. External testing is essential for regulating these diagnostic systems to deploy ML models in a primary care practice setting.
Collapse
Affiliation(s)
- Anna Escalé-Besa
- Centre d'Atenció Primària Navàs-Balsareny, Institut Català de la Salut, Navàs, Spain
| | - Aïna Fuster-Casanovas
- Unitat de Suport a la Recerca de la Catalunya Central, Fundació Institut Universitari per a la Recerca a l'Atenció Primària de Salut Jordi Gol i Gurina, Sant Fruitós de Bages, Spain
- Health Promotion in Rural Areas Research Group, Gerència Territorial de la Catalunya Central, Institut Català de la Salut, Sant Fruitós de Bages, Spain
| | - Alexander Börve
- iDoc24 Inc, San Francisco, CA, United States
- Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Oriol Yélamos
- Dermatology Department, Hospital de la Santa Creu i Sant Pau, Universitat Autònoma de Barcelona, Barcelona, Spain
| | | | | | - Francesc X Marin-Gomez
- Servei d'Atenció Primària Osona, Gerència Territorial de Barcelona, Institut Català de la Salut, Vic, Spain
| | - Josep Vidal-Alaball
- Unitat de Suport a la Recerca de la Catalunya Central, Fundació Institut Universitari per a la Recerca a l'Atenció Primària de Salut Jordi Gol i Gurina, Sant Fruitós de Bages, Spain
- Health Promotion in Rural Areas Research Group, Gerència Territorial de la Catalunya Central, Institut Català de la Salut, Sant Fruitós de Bages, Spain
- Faculty of Medicine, University of Vic-Central University of Catalonia, Vic, Spain
| |
Collapse
|
27
|
Hu H, Xiao D, Rhodin H, Murphy TH. Towards a Visualizable, De-identified Synthetic Biomarker of Human Movement Disorders. J Parkinsons Dis 2022; 1:2085-2096. [PMID: 36057831 PMCID: PMC10473142 DOI: 10.3233/jpd-223351] [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] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 08/10/2022] [Indexed: 12/15/2022]
Abstract
Human motion analysis has been a common thread across modern and early medicine. While medicine evolves, analysis of movement disorders is mostly based on clinical presentation and trained observers making subjective assessments using clinical rating scales. Currently, the field of computer vision has seen exponential growth and successful medical applications. While this has been the case, neurology, for the most part, has not embraced digital movement analysis. There are many reasons for this including: the limited size of labeled datasets, accuracy and nontransparent nature of neural networks, and potential legal and ethical concerns. We hypothesize that a number of opportunities are made available by advancements in computer vision that will enable digitization of human form, movements, and will represent them synthetically in 3D. Representing human movements within synthetic body models will potentially pave the way towards objective standardized digital movement disorder diagnosis and building sharable open-source datasets from such processed videos. We provide a perspective of this emerging field and describe how clinicians and computer scientists can navigate this new space. Such digital movement capturing methods will be important for both machine learning-based diagnosis and computer vision-aided clinical assessment. It would also supplement face-to-face clinical visits and be used for longitudinal monitoring and remote diagnosis.
Collapse
Affiliation(s)
- Hao Hu
- University of British Columbia, Department of Psychiatry, Kinsmen Laboratory of Neurological Research, Detwiller Pavilion, Vancouver, BC, Canada
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, BC, Canada
| | - Dongsheng Xiao
- University of British Columbia, Department of Psychiatry, Kinsmen Laboratory of Neurological Research, Detwiller Pavilion, Vancouver, BC, Canada
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, BC, Canada
| | - Helge Rhodin
- Department of Computer Science, University of British Columbia, Vancouver, BC, Canada
| | - Timothy H. Murphy
- University of British Columbia, Department of Psychiatry, Kinsmen Laboratory of Neurological Research, Detwiller Pavilion, Vancouver, BC, Canada
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, BC, Canada
| |
Collapse
|
28
|
Liu XY, Song W, Mao T, Zhang Q, Zhang C, Li XY. Application of artificial intelligence in the diagnosis of subepithelial lesions using endoscopic ultrasonography: a systematic review and meta-analysis. Front Oncol 2022; 12:915481. [PMID: 36046054 PMCID: PMC9420906 DOI: 10.3389/fonc.2022.915481] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2022] [Accepted: 07/18/2022] [Indexed: 11/05/2022] Open
Abstract
Endoscopic ultrasonography (EUS) is the most common method for diagnosing gastrointestinal subepithelial lesions (SELs); however, it usually requires histopathological confirmation using invasive methods. Artificial intelligence (AI) algorithms have made significant progress in medical imaging diagnosis. The purpose of our research was to explore the application of AI in the diagnosis of SELs using EUS and to evaluate the diagnostic performance of AI-assisted EUS. Three databases, PubMed, EMBASE, and the Cochrane Library, were comprehensively searched for relevant literature. RevMan 5.4.1 and Stata 17.0, were used to calculate and analyze the combined sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver-operating characteristic curve (SROC). Eight studies were selected from 380 potentially relevant studies for the meta-analysis of AI-aided EUS diagnosis of SELs. The combined sensitivity, specificity, and DOR of AI-aided EUS were 0.92 (95% CI, 0.85-0.96), 0.80 (95% CI, 0.70-0.87), and 46.27 (95% CI, 19.36-110.59), respectively). The area under the curve (AUC) was 0.92 (95% CI, 0.90-0.94). The AI model in differentiating GIST from leiomyoma had a pooled AUC of 0.95, sensitivity of 0.93, specificity of 0.88, PLR of 8.04, and NLR of 0.08. The combined sensitivity, specificity, and AUC of the AI-aided EUS diagnosis in the convolutional neural network (CNN) model were 0.93, 0.81, and 0.94, respectively. AI-aided EUS diagnosis using conventional brightness mode (B-mode) EUS images had a combined sensitivity of 0.92, specificity of 0.79, and AUC of 0.92. AI-aided EUS diagnosis based on patients had a combined sensitivity, specificity, and AUC of 0.95, 0.83, and 0.96, respectively. Additionally, AI-aided EUS was superior to EUS by experts in terms of sensitivity (0.93 vs. 0.71), specificity (0.81 vs. 0.69), and AUC (0.94 vs. 0.75). In conclusion, AI-assisted EUS is a promising and reliable method for distinguishing SELs, with excellent diagnostic performance. More multicenter cohort and prospective studies are expected to be conducted to further develop AI-assisted real-time diagnostic systems and validate the superiority of AI systems. Systematic Review Registration: PROSPERO (https://www.crd.york.ac.uk/PROSPERO/), identifier CRD42022303990.
Collapse
|
29
|
Morishita T, Muramatsu C, Seino Y, Takahashi R, Hayashi T, Nishiyama W, Zhou X, Hara T, Katsumata A, Fujita H. Tooth recognition of 32 tooth types by branched single shot multibox detector and integration processing in panoramic radiographs. J Med Imaging (Bellingham) 2022; 9:034503. [PMID: 35756973 DOI: 10.1117/1.jmi.9.3.034503] [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: 08/27/2021] [Accepted: 06/02/2022] [Indexed: 11/14/2022] Open
Abstract
Purpose: The purpose of our study was to analyze dental panoramic radiographs and contribute to dentists' diagnosis by automatically extracting the information necessary for reading them. As the initial step, we detected teeth and classified their tooth types in this study. Approach: We propose single-shot multibox detector (SSD) networks with a side branch for 1-class detection without distinguishing the tooth type and for 16-class detection (i.e., the central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, and third molar, distinguished by the upper and lower jaws). In addition, post-processing was conducted to integrate the results of the two networks and categorize them into 32 classes, differentiating between the left and right teeth. The proposed method was applied to 950 dental panoramic radiographs obtained at multiple facilities, including a university hospital and dental clinics. Results: The recognition performance of the SSD with a side branch was better than that of the original SSD. In addition, the detection rate was improved by the integration process. As a result, the detection rate was 99.03%, the number of false detections was 0.29 per image, and the classification rate was 96.79% for 32 tooth types. Conclusions: We propose a method for tooth recognition using object detection and post-processing. The results show the effectiveness of network branching on the recognition performance and the usefulness of post-processing for neural network output.
Collapse
Affiliation(s)
- Takumi Morishita
- Gifu University, Graduate School of Natural Science and Technology, Department of Intelligence Science and Engineering, Gifu, Japan
| | | | - Yuta Seino
- Gifu University, Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu, Japan
| | | | | | - Wataru Nishiyama
- Asahi University, School of Dentistry, Department of Oral Radiology, Mizuho, Japan
| | - Xiangrong Zhou
- Gifu University, Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu, Japan
| | - Takeshi Hara
- Gifu University, Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu, Japan
| | - Akitoshi Katsumata
- Asahi University, School of Dentistry, Department of Oral Radiology, Mizuho, Japan
| | - Hiroshi Fujita
- Gifu University, Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu, Japan
| |
Collapse
|
30
|
Song F, Song L, Xing T, Feng Y, Song X, Zhang P, Zhang T, Zhu Z, Song W, Zhang G. A Multi-Classification Model for Predicting the Invasiveness of Lung Adenocarcinoma Presenting as Pure Ground-Glass Nodules. Front Oncol 2022; 12:800811. [PMID: 35574301 PMCID: PMC9096139 DOI: 10.3389/fonc.2022.800811] [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] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2021] [Accepted: 04/04/2022] [Indexed: 11/28/2022] Open
Abstract
Objectives To establish a multi-classification model for precisely predicting the invasiveness (pre-invasive adenocarcinoma, PIA; minimally invasive adenocarcinoma, MIA; invasive adenocarcinoma, IAC) of lung adenocarcinoma manifesting as pure ground-glass nodules (pGGNs). Methods By the inclusion and exclusion criteria, this retrospective study enrolled 346 patients (female, 297, and male, 49; age, 55.79 ± 10.53 (24-83)) presenting as pGGNs from 1292 consecutive patients with pathologically confirmed lung adenocarcinoma. A total of 27 clinical were collected and 1409 radiomics features were extracted by PyRadiomics package on python. After feature selection with L2,1-norm minimization, logistic regression (LR), extra w(ET) and gradient boosting decision tree (GBDT) were used to construct the three-classification model. Then, an ensemble model of the three algorithms based on model ensemble strategy was established to further improve the classification performance. Results After feature selection, a hybrid of 166 features consisting of 1 clinical (short-axis diameter, ranked 27th) and 165 radiomics (4 shape, 71 intensity and 90 texture) features were selected. The three most important features are wavelet-HLL_firstorder_Minimum, wavelet-HLL_ngtdm_Busyness and square_firstorder_Kurtosis. The hybrid-ensemble model based on hybrid clinical-radiomics features and the ensemble strategy showed more accurate predictive performance than other models (hybrid-LR, hybrid-ET, hybrid-GBDT, clinical-ensemble and radiomics-ensemble). On the training set and test set, the model can obtain the accuracy values of 0.918 ± 0.022 and 0.841, and its F1-scores respectively were 0.917 ± 0.024 and 0.824. Conclusion The multi-classification of invasive pGGNs can be precisely predicted by our proposed hybrid-ensemble model to assist patients in the early diagnosis of lung adenocarcinoma and prognosis.
Collapse
Affiliation(s)
- Fan Song
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China
| | - Lan Song
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Tongtong Xing
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China
| | - Youdan Feng
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China
| | - Xiao Song
- School of Medical Imaging, Shanxi Medical University, Taiyuan, China
| | - Peng Zhang
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China
| | - Tianyi Zhang
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China
| | - Zhenchen Zhu
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
- 4 + 4 MD Program, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Wei Song
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Guanglei Zhang
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China
| |
Collapse
|
31
|
Idrees M, Shearston K, Farah CS, Kujan O. Immunoexpression of oral brush biopsy enhances the accuracy of diagnosis for oral lichen planus and lichenoid lesions. J Oral Pathol Med 2022; 51:563-572. [PMID: 35460123 PMCID: PMC9542982 DOI: 10.1111/jop.13301] [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] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Accepted: 04/14/2022] [Indexed: 11/27/2022]
Abstract
Background This study assessed the efficacy of using oral liquid‐based brush cytology (OLBC) coupled with immunostained cytology‐derived cell‐blocks, quantified using machine‐learning, in the diagnosis of oral lichen planus (OLP). Methods Eighty‐two patients diagnosed clinically with either OLP or oral lichenoid lesion (OLL) were included. OLBC samples were obtained from all patients before undergoing surgical biopsy. Liquid‐based cytology slides and cell‐blocks were prepared and assessed by cytomorphology and immunocytochemistry for four antibodies (Ki‐67, BAX, NF‐κB‐p65, and AMACR). For comparison purposes, a sub‐group of 31 matched surgical biopsy samples were selected randomly and assessed by immunohistochemistry. Patients were categorized according to their definitive diagnoses into OLP, OLL, and clinically lichenoid, but histopathologically dysplastic lesions (OEDL). Machine‐learning was utilized to provide automated quantification of positively stained protein expression. Results Cytomorphological assessment was associated with an accuracy of 77.27% in the distinction between OLP/OLL and OEDL. A strong concordance of 92.5% (κ = 0.84) of immunostaining patterns was evident between cell‐blocks and tissue sections using machine‐learning. A diagnostic index using a Ki‐67‐based model was 100% accurate in detecting lichenoid cases with epithelial dysplasia. A BAX‐based model demonstrated an accuracy of 92.16%. The accuracy of cytomorphological assessment was greatly improved when it was combined with BAX immunoreactivity (95%). Conclusions Cell‐blocks prepared from OLBC are reliable and minimally‐invasive alternatives to surgical biopsies to diagnose OLLs with epithelial dysplasia when combined with Ki‐67 immunostaining. Machine‐learning has a promising role in the automated quantification of immunostained protein expression.
Collapse
Affiliation(s)
- Majdy Idrees
- UWA Dental School, The University of Western Australia, Perth, Western Australia, Australia
| | - Kate Shearston
- UWA Dental School, The University of Western Australia, Perth, Western Australia, Australia
| | - Camile S Farah
- Australian Centre for Oral Oncology Research and Education, Nedlands, Western Australia, Australia.,Oral, Maxillofacial and Dental Surgery, Fiona Stanley Hospital, Murdoch, Western Australia, Australia.,Anatomical Pathology, Australian Clinical Labs, Subiaco, Western Australia, Australia.,CQ University, Rockhampton, Queensland, Australia
| | - Omar Kujan
- UWA Dental School, The University of Western Australia, Perth, Western Australia, Australia
| |
Collapse
|
32
|
Prasoppokakorn T, Tiyarattanachai T, Chaiteerakij R, Decharatanachart P, Mekaroonkamol P, Ridtitid W, Kongkam P, Rerknimitr R. Application of artificial intelligence for diagnosis of pancreatic ductal adenocarcinoma by EUS: A systematic review and meta-analysis. Endosc Ultrasound 2021; 11:17-26. [PMID: 34937308 PMCID: PMC8887033 DOI: 10.4103/eus-d-20-00219] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [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] [Indexed: 12/24/2022] Open
Abstract
EUS-guided tissue acquisition carries certain risks from unnecessary needle puncture in the low-likelihood lesions. Artificial intelligence (AI) system may enable us to resolve these limitations. We aimed to assess the performance of AI-assisted diagnosis of pancreatic ductal adenocarcinoma (PDAC) by off-line evaluating the EUS images from different modes. The databases PubMed, EMBASE, SCOPUS, ISI, IEEE, and Association for Computing Machinery were systematically searched for relevant studies. The pooled sensitivity, specificity, diagnostic odds ratio (DOR), and summary receiver operating characteristic curve were estimated using R software. Of 369 publications, 8 studies with a total of 870 PDAC patients were included. The pooled sensitivity and specificity of AI-assisted EUS were 0.91 (95% confidence interval [CI], 0.87-0.93) and 0.90 (95% CI, 0.79-0.96), respectively, with DOR of 81.6 (95% CI, 32.2-207.3), for diagnosis of PDAC. The area under the curve was 0.923. AI-assisted B-mode EUS had pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 0.91, 0.90, 0.94, and 0.84, respectively; while AI-assisted contrast-enhanced EUS and AI-assisted EUS elastography had sensitivity, specificity, PPV, and NPV of 0.95, 0.95, 0.97, and 0.90; and 0.88, 0.83, 0.96 and 0.57, respectively. AI-assisted EUS has a high accuracy rate and may potentially enhance the performance of EUS by aiding the endosonographers to distinguish PDAC from other solid lesions. Validation of these findings in other independent cohorts and improvement of AI function as a real-time diagnosis to guide for tissue acquisition are warranted.
Collapse
Affiliation(s)
- Thaninee Prasoppokakorn
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | | | - Roongruedee Chaiteerakij
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society; Center of Excellence for Innovation and Endoscopy in Gastrointestinal Oncology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Pakanat Decharatanachart
- Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Parit Mekaroonkamol
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Wiriyaporn Ridtitid
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Pradermchai Kongkam
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Rungsun Rerknimitr
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society; Center of Excellence for Innovation and Endoscopy in Gastrointestinal Oncology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| |
Collapse
|
33
|
Xiao B, He N, Wang Q, Shi F, Cheng Z, Haacke EM, Yan F, Shen D. Stability of AI-Enabled Diagnosis of Parkinson's Disease: A Study Targeting Substantia Nigra in Quantitative Susceptibility Mapping Imaging. Front Neurosci 2021; 15:760975. [PMID: 34887722 PMCID: PMC8650720 DOI: 10.3389/fnins.2021.760975] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2021] [Accepted: 10/18/2021] [Indexed: 11/13/2022] Open
Abstract
Purpose: Parkinson's disease (PD) diagnosis algorithms based on quantitative susceptibility mapping (QSM) and image algorithms rely on substantia nigra (SN) labeling. However, the difference between SN labels from different experts (or segmentation algorithms) will have a negative impact on downstream diagnostic tasks, such as the decrease of the accuracy of the algorithm or different diagnostic results for the same sample. In this article, we quantify the accuracy of the algorithm on different label sets and then improve the convolutional neural network (CNN) model to obtain a high-precision and highly robust diagnosis algorithm. Methods: The logistic regression model and CNN model were first compared for classification between PD patients and healthy controls (HC), given different sets of SN labeling. Then, based on the CNN model with better performance, we further proposed a novel "gated pooling" operation and integrated it with deep learning to attain a joint framework for image segmentation and classification. Results: The experimental results show that, with different sets of SN labeling that mimic different experts, the CNN model can maintain a stable classification accuracy at around 86.4%, while the conventional logistic regression model yields a large fluctuation ranging from 78.9 to 67.9%. Furthermore, the "gated pooling" operation, after being integrated for joint image segmentation and classification, can improve the diagnosis accuracy to 86.9% consistently, which is statistically better than the baseline. Conclusion: The CNN model, compared with the conventional logistic regression model using radiomics features, has better stability in PD diagnosis. Furthermore, the joint end-to-end CNN model is shown to be suitable for PD diagnosis from the perspectives of accuracy, stability, and convenience in actual use.
Collapse
Affiliation(s)
- Bin Xiao
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.,Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Naying He
- Department of Radiology, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Qian Wang
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
| | - Feng Shi
- Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Zenghui Cheng
- Department of Radiology, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Ewart Mark Haacke
- Department of Radiology, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.,Department of Radiology, Wayne State University, Detroit, MI, United States
| | - Fuhua Yan
- Department of Radiology, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Dinggang Shen
- Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China.,School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
| |
Collapse
|
34
|
Abstract
OBJECTIVE Machine learning (ML) is expected to play an increasing role within primary health care (PHC) in coming years. No peer-reviewed studies exist that evaluate the diagnostic accuracy of ML models compared to general practitioners (GPs). The aim of this study was to evaluate the diagnostic accuracy of an ML classifier on primary headache diagnoses in PHC, compare its performance to GPs, and examine the most impactful signs and symptoms when making a prediction. DESIGN A retrospective study on diagnostic accuracy, using electronic health records from the database of the Primary Health Care Service of the Capital Area (PHCCA) in Iceland. SETTING Fifteen primary health care centers of the PHCCA. SUBJECTS All patients that consulted a physician, from 1 January 2006 to 30 April 2020, and received one of the selected diagnoses. MAIN OUTCOME MEASURES Sensitivity, Specificity, Positive Predictive Value, Matthews Correlation Coefficient, Receiver Operating Characteristic (ROC) curve, and Area under the ROC curve (AUROC) score for primary headache diagnoses, as well as Shapley Additive Explanations (SHAP) values of the ML classifier. RESULTS The classifier outperformed the GPs on all metrics except specificity. The SHAP values indicate that the classifier uses the same signs and symptoms (features) as a physician would, when distinguishing between headache diagnoses. CONCLUSION In a retrospective comparison, the diagnostic accuracy of the ML classifier for primary headache diagnoses is superior to GPs. According to SHAP values, the ML classifier relies on the same signs and symptoms as a physician when making a diagnostic prediction.KeypointsLittle is known about the diagnostic accuracy of machine learning (ML) in the context of primary health care, despite its considerable potential to aid in clinical work. This novel research sheds light on the diagnostic accuracy of ML in a clinical context, as well as the interpretation of its predictions. If the vast potential of ML is to be utilized in primary health care, its performance, safety, and inner workings need to be understood by clinicians.
Collapse
Affiliation(s)
- Steindor Ellertsson
- Primary Health Care Service of the Capital Area, Reykjavik, Iceland
- CONTACT Steindor Ellertsson Primary Health Care Service of the Capital Area, Grenimelur 44, 107, Reykjavik, Iceland
| | - Hrafn Loftsson
- Department of Computer Science, Reykjavik University, Reykjavik, Iceland
| | - Emil L. Sigurdsson
- Primary Health Care Service of the Capital Area, Reykjavik, Iceland
- Development Centre for Primary Health Care in Iceland, Reykjavik, Iceland
- Department of Family Medicine, University of Iceland, Reykjavik, Iceland
| |
Collapse
|
35
|
Zhou J, Liu YL, Zhang Y, Chen JH, Combs FJ, Parajuli R, Mehta RS, Liu H, Chen Z, Zhao Y, Pan Z, Wang M, Yu R, Su MY. BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning. Front Oncol 2021; 11:728224. [PMID: 34790569 PMCID: PMC8591227 DOI: 10.3389/fonc.2021.728224] [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] [Subscribe] [Scholar Register] [Received: 06/21/2021] [Accepted: 10/11/2021] [Indexed: 11/24/2022] Open
Abstract
Background A wide variety of benign and malignant processes can manifest as non-mass enhancement (NME) in breast MRI. Compared to mass lesions, there are no distinct features that can be used for differential diagnosis. The purpose is to use the BI-RADS descriptors and models developed using radiomics and deep learning to distinguish benign from malignant NME lesions. Materials and Methods A total of 150 patients with 104 malignant and 46 benign NME were analyzed. Three radiologists performed reading for morphological distribution and internal enhancement using the 5th BI-RADS lexicon. For each case, the 3D tumor mask was generated using Fuzzy-C-Means segmentation. Three DCE parametric maps related to wash-in, maximum, and wash-out were generated, and PyRadiomics was applied to extract features. The radiomics model was built using five machine learning algorithms. ResNet50 was implemented using three parametric maps as input. Approximately 70% of earlier cases were used for training, and 30% of later cases were held out for testing. Results The diagnostic BI-RADS in the original MRI report showed that 104/104 malignant and 36/46 benign lesions had a BI-RADS score of 4A–5. For category reading, the kappa coefficient was 0.83 for morphological distribution (excellent) and 0.52 for internal enhancement (moderate). Segmental and Regional distribution were the most prominent for the malignant group, and focal distribution for the benign group. Eight radiomics features were selected by support vector machine (SVM). Among the five machine learning algorithms, SVM yielded the highest accuracy of 80.4% in training and 77.5% in testing datasets. ResNet50 had a better diagnostic performance, 91.5% in training and 83.3% in testing datasets. Conclusion Diagnosis of NME was challenging, and the BI-RADS scores and descriptors showed a substantial overlap. Radiomics and deep learning may provide a useful CAD tool to aid in diagnosis.
Collapse
Affiliation(s)
- Jiejie Zhou
- Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.,Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Yan-Lin Liu
- Department of Radiological Sciences, University of California, Irvine, Irvine, CA, United States
| | - Yang Zhang
- Department of Radiological Sciences, University of California, Irvine, Irvine, CA, United States.,Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, NJ, United States
| | - Jeon-Hor Chen
- Department of Radiological Sciences, University of California, Irvine, Irvine, CA, United States.,Department of Radiology, E-DA Hospital and I-Shou University, Kaohsiung, Taiwan
| | - Freddie J Combs
- Department of Radiological Sciences, University of California, Irvine, Irvine, CA, United States
| | - Ritesh Parajuli
- Department of Medicine, University of California, Irvine, Irvine, CA, United States
| | - Rita S Mehta
- Department of Medicine, University of California, Irvine, Irvine, CA, United States
| | - Huiru Liu
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Zhongwei Chen
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Youfan Zhao
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Zhifang Pan
- Zhejiang Engineering Research Center of Intelligent Medicine, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Meihao Wang
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Risheng Yu
- Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Min-Ying Su
- Department of Radiological Sciences, University of California, Irvine, Irvine, CA, United States.,Department of Medical Imaging and Radiological Sciences, Kaohsiung Medical University, Kaohsiung, Taiwan
| |
Collapse
|
36
|
Roehl JC, Jakstat HA, Becker K, Wetselaar P, Ahlers MO. Tooth Wear Evaluation System (TWES) 2.0-Reliability of diagnosis with and without computer-assisted evaluation. J Oral Rehabil 2021; 49:81-91. [PMID: 34719055 DOI: 10.1111/joor.13277] [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: 04/22/2021] [Revised: 09/09/2021] [Accepted: 10/25/2021] [Indexed: 10/19/2022]
Abstract
BACKGROUND Tooth wear is a multifactorial process, leading to the loss of dental hard tissues. Therefore, it is important to detect the level of tooth wear at an early stage, so monitoring can be initiated. The Tooth Wear Evaluation System (TWES) enables such a multistage diagnosis of tooth wear. The further developed TWES 2.0 contains a complete taxonomy of tooth wear, but its reliability has not yet been validated. OBJECTIVES The aim of the study was to examine in a randomised controlled trial (RCT) whether diagnoses made based on the TWES 2.0 are reproducible and whether this reproducibility is also achieved with computer-assisted diagnostics. METHODS 44 dental students received extensive training in TWES 2.0 assessment and taxonomy. The students each evaluated at least 10 (of the present 14) anonymised patient cases using gypsum models and high-resolution intra-oral photographs according to TWES 2.0. One half initially evaluated on paper; the other half used dedicated software (CMDfact / CMDbrux). After half of the patient cases (5), the evaluation methods were switched (AB/BA crossover design). The diagnoses were then evaluated for agreement with the predefined sample solution. RESULTS Evaluation of agreement with the sample solution according to Cohen's kappa indicated a value of 0.46 for manual (traditional) evaluation; and 0.44 for computer-assisted evaluation. Evaluation of agreement between examiners was 0.38 for manual and 0.48 for computer-assisted evaluation (Fleiss' kappa). CONCLUSION The results of this study proved that the taxonomy of the TWES 2.0 has acceptable reliability and can thus be used by dentists. Accordingly, the system can be learned quickly even by untrained practitioners. Comparable results are achieved with computer-assisted evaluation.
Collapse
Affiliation(s)
- Jakob C Roehl
- Department of Prosthetic Dentistry, Center for Dental and Oral Medicine, University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany.,CMD-Center Hamburg-Eppendorf, Hamburg, Germany
| | - Holger A Jakstat
- Department of Prosthetic Dentistry and Dental Materials and Special Care, Center for Dental and Oral Medicine, University of Leipzig, Leipzig, Germany
| | | | - Peter Wetselaar
- Department of Orofacial Pain and Dysfunction, Academic Centre for Dentistry Amsterdam (ACTA), University of Amsterdam and Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
| | - M Oliver Ahlers
- Department of Prosthetic Dentistry, Center for Dental and Oral Medicine, University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany.,CMD-Center Hamburg-Eppendorf, Hamburg, Germany
| |
Collapse
|
37
|
Collins T, Maktabi M, Barberio M, Bencteux V, Jansen-Winkeln B, Chalopin C, Marescaux J, Hostettler A, Diana M, Gockel I. Automatic Recognition of Colon and Esophagogastric Cancer with Machine Learning and Hyperspectral Imaging. Diagnostics (Basel) 2021; 11:diagnostics11101810. [PMID: 34679508 PMCID: PMC8535008 DOI: 10.3390/diagnostics11101810] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [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: 07/22/2021] [Revised: 09/18/2021] [Accepted: 09/23/2021] [Indexed: 01/23/2023] Open
Abstract
There are approximately 1.8 million diagnoses of colorectal cancer, 1 million diagnoses of stomach cancer, and 0.6 million diagnoses of esophageal cancer each year globally. An automatic computer-assisted diagnostic (CAD) tool to rapidly detect colorectal and esophagogastric cancer tissue in optical images would be hugely valuable to a surgeon during an intervention. Based on a colon dataset with 12 patients and an esophagogastric dataset of 10 patients, several state-of-the-art machine learning methods have been trained to detect cancer tissue using hyperspectral imaging (HSI), including Support Vector Machines (SVM) with radial basis function kernels, Multi-Layer Perceptrons (MLP) and 3D Convolutional Neural Networks (3DCNN). A leave-one-patient-out cross-validation (LOPOCV) with and without combining these sets was performed. The ROC-AUC score of the 3DCNN was slightly higher than the MLP and SVM with a difference of 0.04 AUC. The best performance was achieved with the 3DCNN for colon cancer and esophagogastric cancer detection with a high ROC-AUC of 0.93. The 3DCNN also achieved the best DICE scores of 0.49 and 0.41 on the colon and esophagogastric datasets, respectively. These scores were significantly improved using a patient-specific decision threshold to 0.58 and 0.51, respectively. This indicates that, in practical use, an HSI-based CAD system using an interactive decision threshold is likely to be valuable. Experiments were also performed to measure the benefits of combining the colorectal and esophagogastric datasets (22 patients), and this yielded significantly better results with the MLP and SVM models.
Collapse
Affiliation(s)
- Toby Collins
- Institute for Research against Digestive Cancer (IRCAD), 67091 Strasbourg, France; (M.B.); (J.M.); (A.H.); (M.D.)
- Correspondence:
| | - Marianne Maktabi
- Innovation Center Computer-Assisted Surgery (ICCAS), University of Leipzig, 04103 Leipzig, Germany; (M.M.); (C.C.)
| | - Manuel Barberio
- Institute for Research against Digestive Cancer (IRCAD), 67091 Strasbourg, France; (M.B.); (J.M.); (A.H.); (M.D.)
- General Surgery Department, Card. G. Panico, 73039 Tricase, Italy
| | - Valentin Bencteux
- ICUBE Laboratory, Photonics Instrumentation for Health, University of Strasbourg, 67400 Strasbourg, France;
| | - Boris Jansen-Winkeln
- Department of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of Leipzig, 04103 Leipzig, Germany; (B.J.-W.); (I.G.)
| | - Claire Chalopin
- Innovation Center Computer-Assisted Surgery (ICCAS), University of Leipzig, 04103 Leipzig, Germany; (M.M.); (C.C.)
| | - Jacques Marescaux
- Institute for Research against Digestive Cancer (IRCAD), 67091 Strasbourg, France; (M.B.); (J.M.); (A.H.); (M.D.)
| | - Alexandre Hostettler
- Institute for Research against Digestive Cancer (IRCAD), 67091 Strasbourg, France; (M.B.); (J.M.); (A.H.); (M.D.)
| | - Michele Diana
- Institute for Research against Digestive Cancer (IRCAD), 67091 Strasbourg, France; (M.B.); (J.M.); (A.H.); (M.D.)
- ICUBE Laboratory, Photonics Instrumentation for Health, University of Strasbourg, 67400 Strasbourg, France;
- Department of General, Digestive, and Endocrine Surgery, University Hospital of Strasbourg, 67091 Strasbourg, France
- INSERM, Institute of Viral and Liver Disease, 67091 Strasbourg, France
- Mitochondrion, Oxidative Stress and Muscle Protection (MSP)-EA 3072, Institute of Physiology, Faculty of Medicine, University of Strasbourg, 67085 Strasbourg, France
| | - Ines Gockel
- Department of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of Leipzig, 04103 Leipzig, Germany; (B.J.-W.); (I.G.)
| |
Collapse
|
38
|
Van Adrichem LNA, Kronig SAJ, Kronig ODM. Validation of Skully Care as a Fast Method for Quantifying Positional Cranial Deformities. Cleft Palate Craniofac J 2021; 59:1107-1113. [PMID: 34559019 PMCID: PMC9411692 DOI: 10.1177/10556656211035022] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
Objective Craniofacial measuring is valuable for diagnosis and evaluation of growth and treatment of positional skull deformities. Plagiocephalometry (PCM) quantifies skull deformities and is proven to be reliable and valid. However, PCM needs direct skin contact with thermoplastic material, is laborious and time-consuming. Therefore, Skully Care (SC) was developed to measure positional skull deformities with a smartphone application. Design SC is retrospectively compared to PCM. Setting Pediatric physiotherapy centers. Patients Age ≤1 year, analyzed or treated for positional skull deformities. Interventions A total of 60 skull shape analyses were performed. Main Outcome Measures The main outcome measures employed are Pearson correlation coefficient between cranial vault asymmetry index (CVAI; in SC) and oblique diameter difference index (ODDI; in PCM) and between cranial index (CI; in SC) and cranial proportional index (CPI; in PCM). Mann–Whitney U test determined difference of time consumption between PCM and SC. Results High correlation was found between CVAI and ODDI (r = 0.849; P < .01) in positional plagiocephaly and very high correlation between CI and CPI (r = 0.938; P < .01) in positional brachycephaly. SC is significantly faster than PCM (P < .001). Conclusions SC is valid in analyzing positional skull deformities and strongly correlates to PCM, the gold standard in daily physiotherapy practice. The combination of simplicity, validity, speed, and user and child convenience makes SC a promising craniofacial measuring method in daily practice. SC has potential to be the modern successor for analyzing positional skull deformities.
Collapse
Affiliation(s)
- Léon N A Van Adrichem
- Department of Plastic and Reconstructive Surgery and Hand Surgery, 8124University Medical Center Utrecht, the Netherlands
| | - Sophia A J Kronig
- Department of Plastic and Reconstructive Surgery and Hand Surgery, 8124University Medical Center Utrecht, the Netherlands
| | - Otto D M Kronig
- Department of Plastic and Reconstructive Surgery and Hand Surgery, 8124University Medical Center Utrecht, the Netherlands
| |
Collapse
|
39
|
Lazăr DC, Avram MF, Faur AC, Romoşan I, Goldiş A. The role of computer-assisted systems for upper-endoscopy quality monitoring and assessment of gastric lesions. Gastroenterol Rep (Oxf) 2021; 9:185-204. [PMID: 34316369 PMCID: PMC8309682 DOI: 10.1093/gastro/goab008] [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] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/26/2020] [Revised: 12/05/2020] [Accepted: 12/20/2020] [Indexed: 12/24/2022] Open
Abstract
This article analyses the literature regarding the value of computer-assisted systems in esogastroduodenoscopy-quality monitoring and the assessment of gastric lesions. Current data show promising results in upper-endoscopy quality control and a satisfactory detection accuracy of gastric premalignant and malignant lesions, similar or even exceeding that of experienced endoscopists. Moreover, artificial systems enable the decision for the best treatment strategies in gastric-cancer patient care, namely endoscopic vs surgical resection according to tumor depth. In so doing, unnecessary surgical interventions would be avoided whilst providing a better quality of life and prognosis for these patients. All these performance data have been revealed by numerous studies using different artificial intelligence (AI) algorithms in addition to white-light endoscopy or novel endoscopic techniques that are available in expert endoscopy centers. It is expected that ongoing clinical trials involving AI and the embedding of computer-assisted diagnosis systems into endoscopic devices will enable real-life implementation of AI endoscopic systems in the near future and at the same time will help to overcome the current limits of the computer-assisted systems leading to an improvement in performance. These benefits should lead to better diagnostic and treatment strategies for gastric-cancer patients. Furthermore, the incorporation of AI algorithms in endoscopic tools along with the development of large electronic databases containing endoscopic images might help in upper-endoscopy assistance and could be used for telemedicine purposes and second opinion for difficult cases.
Collapse
Affiliation(s)
- Daniela Cornelia Lazăr
- Department V of Internal Medicine I, Discipline of Internal Medicine IV, “Victor Babeș” University of Medicine and Pharmacy Timișoara, Romania,Timișoara, Romania
| | - Mihaela Flavia Avram
- Department of Surgery X, 1st Surgery Discipline, “Victor Babeș” University of Medicine and Pharmacy Timișoara, Romania, Timișoara, Romania
| | - Alexandra Corina Faur
- Department I, Discipline of Anatomy and Embriology, “Victor Babeș” University of Medicine and Pharmacy Timișoara, Romania, Timișoara, Romania
| | - Ioan Romoşan
- Department V of Internal Medicine I, Discipline of Internal Medicine IV, “Victor Babeș” University of Medicine and Pharmacy Timișoara, Romania,Timișoara, Romania
| | - Adrian Goldiş
- Department VII of Internal Medicine II, Discipline of Gastroenterology and Hepatology, “Victor Babeș” University of Medicine and Pharmacy Timișoara, Romania, Timișoara, Romania
| |
Collapse
|
40
|
Costa ALF, de Souza Carreira B, Fardim KAC, Nussi AD, da Silva Lima VC, Miguel MMV, Jardini MAN, Santamaria MP, de Castro Lopes SLP. Texture analysis of cone beam computed tomography images reveals dental implant stability. Int J Oral Maxillofac Surg 2021; 50:1609-1616. [PMID: 33962826 DOI: 10.1016/j.ijom.2021.04.009] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [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: 08/04/2020] [Revised: 02/10/2021] [Accepted: 04/19/2021] [Indexed: 11/28/2022]
Abstract
The aim of this study was to characterize the alveolar bone of edentulous maxillary sites using texture analysis (TA) of cone beam computed tomography (CBCT) images and to correlate the results to the insertion torque, thus verifying whether TA is a predictive tool of final implant treatment. This study was conducted on patients who had received single implants in the maxilla (46 implants) 1year earlier and whose torque values were properly recorded. Three cross-sections of the sites were selected on CBCT scans. Two regions of interest (ROIs) corresponding to the implant bone site and peri-implant bone were also outlined, according to virtual planning. The CBCT scans were exported to MaZda software, where the two ROIs were delimited following the previously demarcated contours. Values for the co-occurrence matrix were calculated for TA. With regard to the insertion torque value, there was a direct correlation with the contrast of the peri-implant bone (P<0.001) and an inverse correlation with the entropy of the implant bone site (P=0.006). A greater contrast indicates a greater torque value for insertion of the implants, and there is a possible association with a lower entropy value of the implant-bone interface.
Collapse
Affiliation(s)
- A L F Costa
- Postgraduate Program in Dentistry, Cruzeiro do Sul University (UNICSUL), São Paulo, Brazil.
| | - B de Souza Carreira
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos, SP, Brazil
| | - K A C Fardim
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos, SP, Brazil
| | - A D Nussi
- Postgraduate Program in Dentistry, Cruzeiro do Sul University (UNICSUL), São Paulo, Brazil
| | - V C da Silva Lima
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos, SP, Brazil
| | - M M V Miguel
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos, SP, Brazil
| | - M A N Jardini
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos, SP, Brazil
| | - M P Santamaria
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos, SP, Brazil
| | - S L P de Castro Lopes
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos, SP, Brazil
| |
Collapse
|
41
|
Hwang Y, Lee HH, Park C, Tama BA, Kim JS, Cheung DY, Chung WC, Cho YS, Lee KM, Choi MG, Lee S, Lee BI. Improved classification and localization approach to small bowel capsule endoscopy using convolutional neural network. Dig Endosc 2021; 33:598-607. [PMID: 32640059 DOI: 10.1111/den.13787] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [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: 04/20/2020] [Revised: 06/29/2020] [Accepted: 07/01/2020] [Indexed: 12/13/2022]
Abstract
BACKGROUND Although great advances in artificial intelligence for interpreting small bowel capsule endoscopy (SBCE) images have been made in recent years, its practical use is still limited. The aim of this study was to develop a more practical convolutional neural network (CNN) algorithm for the automatic detection of various small bowel lesions. METHODS A total of 7556 images were collected for the training dataset from 526 SBCE videos. Abnormal images were classified into two categories: hemorrhagic lesions (red spot/angioectasia/active bleeding) and ulcerative lesions (erosion/ulcer/stricture). A CNN algorithm based on VGGNet was trained in two different ways: the combined model (hemorrhagic and ulcerative lesions trained separately) and the binary model (all abnormal images trained without discrimination). The detected lesions were visualized using a gradient class activation map (Grad-CAM). The two models were validated using 5,760 independent images taken at two other academic hospitals. RESULTS Both the combined and binary models acquired high accuracy for lesion detection, and the difference between the two models was not significant (96.83% vs 96.62%, P = 0.122). However, the combined model showed higher sensitivity (97.61% vs 95.07%, P < 0.001) and higher accuracy for individual lesions from the hemorrhagic and ulcerative categories than the binary model. The combined model also revealed more accurate localization of the culprit area on images evaluated by the Grad-CAM. CONCLUSIONS Diagnostic sensitivity and classification of small bowel lesions using a convolutional neural network are improved by the independent training for hemorrhagic and ulcerative lesions. Grad-CAM is highly effective in localizing the lesions.
Collapse
Affiliation(s)
- Yunseob Hwang
- Department of Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, Korea.,Postech-Catholic Biomedical Engineering Institute, Pohang University of Science and Technology (POSTECH), Pohang, Korea
| | - Han Hee Lee
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea.,Postech-Catholic Biomedical Engineering Institute, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Chunghyun Park
- Department of Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, Korea
| | - Bayu Adhi Tama
- Department of Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, Korea
| | - Jin Su Kim
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Dae Young Cheung
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Woo Chul Chung
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Young-Seok Cho
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Kang-Moon Lee
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Myung-Gyu Choi
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Seungchul Lee
- Department of Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, Korea.,Postech-Catholic Biomedical Engineering Institute, Pohang University of Science and Technology (POSTECH), Pohang, Korea.,Graduate School of Artificial Intelligence, Pohang University of Science and Technology (POSTECH), Pohang, Korea
| | - Bo-In Lee
- Division of Gastroenterology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
| |
Collapse
|
42
|
Kougia V, Pavlopoulos J, Papapetrou P, Gordon M. RTEX: A novel framework for ranking, tagging, and explanatory diagnostic captioning of radiography exams. J Am Med Inform Assoc 2021; 28:1651-1659. [PMID: 33880528 PMCID: PMC8324241 DOI: 10.1093/jamia/ocab046] [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] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2020] [Revised: 02/27/2021] [Accepted: 03/02/2021] [Indexed: 11/14/2022] Open
Abstract
OBJECTIVE The study sought to assist practitioners in identifying and prioritizing radiography exams that are more likely to contain abnormalities, and provide them with a diagnosis in order to manage heavy workload more efficiently (eg, during a pandemic) or avoid mistakes due to tiredness. MATERIALS AND METHODS This article introduces RTEx, a novel framework for (1) ranking radiography exams based on their probability to be abnormal, (2) generating abnormality tags for abnormal exams, and (3) providing a diagnostic explanation in natural language for each abnormal exam. Our framework consists of deep learning and retrieval methods and is assessed on 2 publicly available datasets. RESULTS For ranking, RTEx outperforms its competitors in terms of nDCG@k. The tagging component outperforms 2 strong competitor methods in terms of F1. Moreover, the diagnostic captioning component, which exploits the predicted tags to constrain the captioning process, outperforms 4 captioning competitors with respect to clinical precision and recall. DISCUSSION RTEx prioritizes abnormal exams toward the improvement of the healthcare workflow by introducing a ranking method. Also, for each abnormal radiography exam RTEx generates a set of abnormality tags alongside a diagnostic text to explain the tags and guide the medical expert. Human evaluation of the produced text shows that employing the generated tags offers consistency to the clinical correctness and that the sentences of each text have high clinical accuracy. CONCLUSIONS This is the first framework that successfully combines 3 tasks: ranking, tagging, and diagnostic captioning with focus on radiography exams that contain abnormalities.
Collapse
Affiliation(s)
- Vasiliki Kougia
- Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
| | - John Pavlopoulos
- Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
| | - Panagiotis Papapetrou
- Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
| | - Max Gordon
- Division of Orthopaedics, Department of Clinical Sciences, Danderyd Hospital, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
43
|
Tan MC, Bhushan S, Quang T, Schwarz R, Patel KH, Yu X, Li Z, Wang G, Zhang F, Wang X, Xu H, Richards-Kortum RR, Anandasabapathy S. Automated software-assisted diagnosis of esophageal squamous cell neoplasia using high-resolution microendoscopy. Gastrointest Endosc 2021; 93:831-838.e2. [PMID: 32682812 DOI: 10.1016/j.gie.2020.07.007] [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] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/17/2020] [Accepted: 07/02/2020] [Indexed: 12/11/2022]
Abstract
BACKGROUND AND AIMS High-resolution microendoscopy (HRME) is an optical biopsy technology that provides subcellular imaging of esophageal mucosa but requires expert interpretation of these histopathology-like images. We compared endoscopists with an automated software algorithm for detection of esophageal squamous cell neoplasia (ESCN) and evaluated the endoscopists' accuracy with and without input from the software algorithm. METHODS Thirteen endoscopists (6 experts, 7 novices) were trained and tested on 218 post-hoc HRME images from 130 consecutive patients undergoing ESCN screening/surveillance. The automated software algorithm interpreted all images as neoplastic (high-grade dysplasia, ESCN) or non-neoplastic. All endoscopists provided their interpretation (neoplastic or non-neoplastic) and confidence level (high or low) without and with knowledge of the software overlay highlighting abnormal nuclei and software interpretation. The criterion standard was histopathology consensus diagnosis by 2 pathologists. RESULTS The endoscopists had a higher mean sensitivity (84.3%, standard deviation [SD] 8.0% vs 76.3%, P = .004), lower specificity (75.0%, SD 5.2% vs 85.3%, P < .001) but no significant difference in accuracy (81.1%, SD 5.2% vs 79.4%, P = .26) of ESCN detection compared with the automated software algorithm. With knowledge of the software algorithm, the specificity of the endoscopists increased significantly (75.0% to 80.1%, P = .002) but not the sensitivity (84.3% to 84.8%, P = .75) or accuracy (81.1% to 83.1%, P = .13). The increase in specificity was among novices (P = .008) but not experts (P = .11). CONCLUSIONS The software algorithm had lower sensitivity but higher specificity for ESCN detection than endoscopists. Using computer-assisted diagnosis, the endoscopists maintained high sensitivity while increasing their specificity and accuracy compared with their initial diagnosis. Automated HRME interpretation would facilitate widespread usage in resource-poor areas where this portable, low-cost technology is needed.
Collapse
|
44
|
Wang J, Wood A, Gao C, Najarian K, Gryak J. Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning. Entropy (Basel) 2021; 23:382. [PMID: 33804831 DOI: 10.3390/e23040382] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/15/2021] [Revised: 03/20/2021] [Accepted: 03/22/2021] [Indexed: 12/18/2022]
Abstract
The spleen is one of the most frequently injured organs in blunt abdominal trauma. Computed tomography (CT) is the imaging modality of choice to assess patients with blunt spleen trauma, which may include lacerations, subcapsular or parenchymal hematomas, active hemorrhage, and vascular injuries. While computer-assisted diagnosis systems exist for other conditions assessed using CT scans, the current method to detect spleen injuries involves the manual review of scans by radiologists, which is a time-consuming and repetitive process. In this study, we propose an automated spleen injury detection method using machine learning. CT scans from patients experiencing traumatic injuries were collected from Michigan Medicine and the Crash Injury Research Engineering Network (CIREN) dataset. Ninety-nine scans of healthy and lacerated spleens were split into disjoint training and test sets, with random forest (RF), naive Bayes, SVM, k-nearest neighbors (k-NN) ensemble, and subspace discriminant ensemble models trained via 5-fold cross validation. Of these models, random forest performed the best, achieving an Area Under the receiver operating characteristic Curve (AUC) of 0.91 and an F1 score of 0.80 on the test set. These results suggest that an automated, quantitative assessment of traumatic spleen injury has the potential to enable faster triage and improve patient outcomes.
Collapse
|
45
|
Kronig ODM, Kronig SAJ, Vrooman HA, Veenland JF, Van Adrichem LNA. New method for quantification of the relative severity and (a)symmetry of isolated metopic synostosis. Int J Oral Maxillofac Surg 2021; 50:1477-1484. [PMID: 33744098 DOI: 10.1016/j.ijom.2021.03.003] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2020] [Revised: 01/17/2021] [Accepted: 03/03/2021] [Indexed: 11/16/2022]
Abstract
Trigonocephaly is the result of premature fusion of the metopic suture and its severity can vary widely. However, there is no gold standard for quantification of the severity. This study was performed to quantify severity using the Utrecht Cranial Shape Quantifier (UCSQ) and to assess forehead symmetry. Nineteen preoperative non-syndromic trigonocephaly patients (age ≤1 year) were included for the analysis of severity and symmetry. Severity according to the UCSQ was based on the following combined variables: forehead width and relative skull elongation. The UCSQ was compared to the most established quantification methods. A high correlation was found between the UCSQ and visual score (r=0.71). Moderate to negligible correlation was found between the UCSQ and frontal angle, binocular distance, inter-ocular distance, and frontal stenosis. Additionally, correlation between the visual score and these established quantification methods was negligible. Assessment of the frontal peak (a)symmetry (ratio of right to left triangle area in the curve) showed a mean right versus left triangle area ratio of 1.4 (range 0.9-2.4). The results suggest that the UCSQ is appropriate for the quantification of severity based on the high correlation with clinical judgement. Furthermore, a larger triangle area right than left was unexpectedly found, indicating forehead asymmetry.
Collapse
Affiliation(s)
- O D M Kronig
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Utrecht, The Netherlands.
| | - S A J Kronig
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - H A Vrooman
- Department of Radiology, Erasmus MC, Rotterdam, University Medical Center Rotterdam, Rotterdam, The Netherlands; Department of Medical Informatics, Erasmus MC, Rotterdam, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - J F Veenland
- Department of Radiology, Erasmus MC, Rotterdam, University Medical Center Rotterdam, Rotterdam, The Netherlands; Department of Medical Informatics, Erasmus MC, Rotterdam, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - L N A Van Adrichem
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Utrecht, The Netherlands
| |
Collapse
|
46
|
Boitsios G, De Leucio A, Preziosi M, Seidel L, Aparisi Gómez MP, Simoni P. Are Automated and Visual Greulich and Pyle-Based Methods Applicable to Caucasian European Children With a Moroccan Ethnic Origin When Assessing Bone Age? Cureus 2021; 13:e13478. [PMID: 33777566 PMCID: PMC7990004 DOI: 10.7759/cureus.13478] [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] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
Introduction To test the accuracy of the visual and automated bone age assessment base on the Greulich and Pyle (GP) method in healthy Caucasian European children with a Moroccan ethnic origin. Material and methods Moroccan Caucasian (MC) children were retrospectively and consecutively enrolled along with age- and sex-matched control group (CG) of European Caucasian (EC) children enrolled from the general population. The two groups included 423 children aged from 2 to 15 years with a normal left-hand radiograph performed to rule out a trauma between March 2008 and December 2017. One radiologist, blinded to the BoneXpert® (Visiana, Holte, Denmark) estimates, visually reviewed the radiographs using the GP atlas. The BoneXpert® automatically analysed all 423 radiographs. The intraclass correlation coefficient (ICC), linear regression and Bland-Altman plots were performed to describe the agreement between each method and the chronological age (CA) and the agreement between the two methods. Results Visual bone age assessment was related to the CA in both girls (MC ICC 0.97; EC ICC 0.97) and boys (MC ICC 0.95; EC ICC 0.96). Automated bone age assessment was related to the CA in both girls (MC ICC 0.97; EC ICC 0.96) and boys (MC ICC 0.88; EC ICC 0.96). Bland-Altman plots showed an excellent agreement between the two methods in both sexes and ethnicities before puberty especially in Moroccan boys. Conclusion Visual and automatic bone age assessment based on the GP method, previously validated in the general population of Caucasian European children, can be confidently used in healthy Caucasian European children with a Moroccan ethnic origin.
Collapse
Affiliation(s)
| | | | - Marco Preziosi
- Radiology, Queen Fabiola Children's University Hospital, Brussels, BEL
| | - Laurence Seidel
- Biostatistics, University Hospital (CHU) of Liège, Liège, BEL
| | - Maria P Aparisi Gómez
- Radiology, Auckland City Hospital, Auckland, NZL.,Radiology, Vithas Hospital October 9, Valencia, ESP
| | - Paolo Simoni
- Radiology, Queen Fabiola Children's University Hospital, Brussels, BEL
| |
Collapse
|
47
|
Blum AE, Murphy GF, Lee JJ. Digital dermatopathology: The time is now. J Cutan Pathol 2021; 48:469-471. [PMID: 33345364 DOI: 10.1111/cup.13944] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2020] [Revised: 12/02/2020] [Accepted: 12/13/2020] [Indexed: 12/16/2022]
Abstract
To continue to provide expert specialized care during the COVID-19 pandemic, our dermatopathology service transitioned to a secure virtual microscopy platform. In our experience, this digitally-enabled dermatopathology practice revealed myriad benefits, including an improved diagnostic workflow and increased access to teaching. Whole slide imaging (WSI) is a related system that digitizes glass slides with high resolution and has been clinically validated for primary diagnosis. While WSI requires an initial institutional investment, its benefits include expanded access to subspecialized expertise and collaborations, digital histopathologic data generation for research, unification of patient clinical and pathologic information, and archiving of educational resources. The switch to digitally-enabled remote dermatopathology at our institution and across the United States presents a rare opportunity to critically examine newly implemented systems and to develop permanent digital solutions, thereby taking a leap forward for the benefit of patient care, research, and medical education.
Collapse
Affiliation(s)
- Amy E Blum
- Harvard Medical School, Boston, Massachusetts, USA
| | - George F Murphy
- Harvard Medical School, Boston, Massachusetts, USA.,Program in Dermatopathology, Department of Pathology, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | - Jonathan J Lee
- Harvard Medical School, Boston, Massachusetts, USA.,Program in Dermatopathology, Department of Pathology, Brigham and Women's Hospital, Boston, Massachusetts, USA
| |
Collapse
|
48
|
Chen J, Han G, Cai H, Yang D, Laurienti PJ, Styner M, Wu G. Learning Common Harmonic Waves on Stiefel Manifold - A New Mathematical Approach for Brain Network Analyses. IEEE Trans Med Imaging 2021; 40:419-430. [PMID: 33021935 PMCID: PMC7838011 DOI: 10.1109/tmi.2020.3029063] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
Converging evidence shows that disease-relevant brain alterations do not appear in random brain locations, instead, their spatial patterns follow large-scale brain networks. In this context, a powerful network analysis approach with a mathematical foundation is indispensable to understand the mechanisms of neuropathological events as they spread through the brain. Indeed, the topology of each brain network is governed by its native harmonic waves, which are a set of orthogonal bases derived from the Eigen-system of the underlying Laplacian matrix. To that end, we propose a novel connectome harmonic analysis framework that provides enhanced mathematical insights by detecting frequency-based alterations relevant to brain disorders. The backbone of our framework is a novel manifold algebra appropriate for inference across harmonic waves. This algebra overcomes the limitations of using classic Euclidean operations on irregular data structures. The individual harmonic differences are measured by a set of common harmonic waves learned from a population of individual Eigen-systems, where each native Eigen-system is regarded as a sample drawn from the Stiefel manifold. Specifically, a manifold optimization scheme is tailored to find the common harmonic waves, which reside at the center of the Stiefel manifold. To that end, the common harmonic waves constitute a new set of neurobiological bases to understand disease progression. Each harmonic wave exhibits a unique propagation pattern of neuropathological burden spreading across brain networks. The statistical power of our novel connectome harmonic analysis approach is evaluated by identifying frequency-based alterations relevant to Alzheimer's disease, where our learning-based manifold approach discovers more significant and reproducible network dysfunction patterns than Euclidean methods.
Collapse
|
49
|
Morse KE, Ostberg NP, Jones VG, Chan AS. Use Characteristics and Triage Acuity of a Digital Symptom Checker in a Large Integrated Health System: Population-Based Descriptive Study. J Med Internet Res 2020; 22:e20549. [PMID: 33170799 PMCID: PMC7717918 DOI: 10.2196/20549] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [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: 05/21/2020] [Revised: 07/07/2020] [Accepted: 11/07/2020] [Indexed: 12/11/2022] Open
Abstract
Background Pressure on the US health care system has been increasing due to a combination of aging populations, rising health care expenditures, and most recently, the COVID-19 pandemic. Responses to this pressure are hindered in part by reliance on a limited supply of highly trained health care professionals, creating a need for scalable technological solutions. Digital symptom checkers are artificial intelligence–supported software tools that use a conversational “chatbot” format to support rapid diagnosis and consistent triage. The COVID-19 pandemic has brought new attention to these tools due to the need to avoid face-to-face contact and preserve urgent care capacity. However, evidence-based deployment of these chatbots requires an understanding of user demographics and associated triage recommendations generated by a large general population. Objective In this study, we evaluate the user demographics and levels of triage acuity provided by a symptom checker chatbot deployed in partnership with a large integrated health system in the United States. Methods This population-based descriptive study included all web-based symptom assessments completed on the website and patient portal of the Sutter Health system (24 hospitals in Northern California) from April 24, 2019, to February 1, 2020. User demographics were compared to relevant US Census population data. Results A total of 26,646 symptom assessments were completed during the study period. Most assessments (17,816/26,646, 66.9%) were completed by female users. The mean user age was 34.3 years (SD 14.4 years), compared to a median age of 37.3 years of the general population. The most common initial symptom was abdominal pain (2060/26,646, 7.7%). A substantial number of assessments (12,357/26,646, 46.4%) were completed outside of typical physician office hours. Most users were advised to seek medical care on the same day (7299/26,646, 27.4%) or within 2-3 days (6301/26,646, 23.6%). Over a quarter of the assessments indicated a high degree of urgency (7723/26,646, 29.0%). Conclusions Users of the symptom checker chatbot were broadly representative of our patient population, although they skewed toward younger and female users. The triage recommendations were comparable to those of nurse-staffed telephone triage lines. Although the emergence of COVID-19 has increased the interest in remote medical assessment tools, it is important to take an evidence-based approach to their deployment.
Collapse
Affiliation(s)
- Keith E Morse
- Department of Pediatrics, Stanford University School of Medicine, Palo Alto, CA, United States
| | - Nicolai P Ostberg
- Center for Biomedical Informatics Research, Stanford University School of Medicine, Palo Alto, CA, United States
| | - Veena G Jones
- Clinical Leadership Team, Sutter Health, Sacramento, CA, United States.,Palo Alto Medical Foundation Research Institute, Palo Alto, CA, United States
| | - Albert S Chan
- Clinical Leadership Team, Sutter Health, Sacramento, CA, United States.,Palo Alto Medical Foundation Research Institute, Palo Alto, CA, United States
| |
Collapse
|
50
|
Baker A, Perov Y, Middleton K, Baxter J, Mullarkey D, Sangar D, Butt M, DoRosario A, Johri S. A Comparison of Artificial Intelligence and Human Doctors for the Purpose of Triage and Diagnosis. Front Artif Intell 2020; 3:543405. [PMID: 33733203 PMCID: PMC7861270 DOI: 10.3389/frai.2020.543405] [Citation(s) in RCA: 35] [Impact Index Per Article: 8.8] [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: 03/16/2020] [Accepted: 11/04/2020] [Indexed: 11/18/2022] Open
Abstract
AI virtual assistants have significant potential to alleviate the pressure on overly burdened healthcare systems by enabling patients to self-assess their symptoms and to seek further care when appropriate. For these systems to make a meaningful contribution to healthcare globally, they must be trusted by patients and healthcare professionals alike, and service the needs of patients in diverse regions and segments of the population. We developed an AI virtual assistant which provides patients with triage and diagnostic information. Crucially, the system is based on a generative model, which allows for relatively straightforward re-parameterization to reflect local disease and risk factor burden in diverse regions and population segments. This is an appealing property, particularly when considering the potential of AI systems to improve the provision of healthcare on a global scale in many regions and for both developing and developed countries. We performed a prospective validation study of the accuracy and safety of the AI system and human doctors. Importantly, we assessed the accuracy and safety of both the AI and human doctors independently against identical clinical cases and, unlike previous studies, also accounted for the information gathering process of both agents. Overall, we found that the AI system is able to provide patients with triage and diagnostic information with a level of clinical accuracy and safety comparable to that of human doctors. Through this approach and study, we hope to start building trust in AI-powered systems by directly comparing their performance to human doctors, who do not always agree with each other on the cause of patients’ symptoms or the most appropriate triage recommendation.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | - Arnold DoRosario
- Northeast Medical Group, Yale New Haven Health, New Haven, CT, United States
| | | |
Collapse
|