1
|
Burti S, Banzato T, Coghlan S, Wodzinski M, Bendazzoli M, Zotti A. Artificial intelligence in veterinary diagnostic imaging: Perspectives and limitations. Res Vet Sci 2024; 175:105317. [PMID: 38843690 DOI: 10.1016/j.rvsc.2024.105317] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2024] [Revised: 05/22/2024] [Accepted: 05/29/2024] [Indexed: 06/17/2024]
Abstract
The field of veterinary diagnostic imaging is undergoing significant transformation with the integration of artificial intelligence (AI) tools. This manuscript provides an overview of the current state and future prospects of AI in veterinary diagnostic imaging. The manuscript delves into various applications of AI across different imaging modalities, such as radiology, ultrasound, computed tomography, and magnetic resonance imaging. Examples of AI applications in each modality are provided, ranging from orthopaedics to internal medicine, cardiology, and more. Notable studies are discussed, demonstrating AI's potential for improved accuracy in detecting and classifying various abnormalities. The ethical considerations of using AI in veterinary diagnostics are also explored, highlighting the need for transparent AI development, accurate training data, awareness of the limitations of AI models, and the importance of maintaining human expertise in the decision-making process. The manuscript underscores the significance of AI as a decision support tool rather than a replacement for human judgement. In conclusion, this comprehensive manuscript offers an assessment of the current landscape and future potential of AI in veterinary diagnostic imaging. It provides insights into the benefits and challenges of integrating AI into clinical practice while emphasizing the critical role of ethics and human expertise in ensuring the wellbeing of veterinary patients.
Collapse
Affiliation(s)
- Silvia Burti
- Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, Legnaro, 35020 Padua, Italy.
| | - Tommaso Banzato
- Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, Legnaro, 35020 Padua, Italy
| | - Simon Coghlan
- School of Computing and Information Systems, Centre for AI and Digital Ethics, Australian Research Council Centre of Excellence for Automated Decision-Making and Society, University of Melbourne, 3052 Melbourne, Australia
| | - Marek Wodzinski
- Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, 30059 Kraków, Poland; Information Systems Institute, University of Applied Sciences - Western Switzerland (HES-SO Valais), 3960 Sierre, Switzerland
| | - Margherita Bendazzoli
- Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, Legnaro, 35020 Padua, Italy
| | - Alessandro Zotti
- Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, Legnaro, 35020 Padua, Italy
| |
Collapse
|
2
|
Lee K, Goh J, Jang J, Hwang J, Kwak J, Kim J, Eom K. Feasibility study of computed tomography texture analysis for evaluation of canine primary adrenal gland tumors. Front Vet Sci 2023; 10:1126165. [PMID: 37711438 PMCID: PMC10499047 DOI: 10.3389/fvets.2023.1126165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2022] [Accepted: 08/01/2023] [Indexed: 09/16/2023] Open
Abstract
Objective This study aimed to investigate the feasibility of computed tomography (CT) texture analysis for distinguishing canine adrenal gland tumors and its usefulness in clinical decision-making. Materials and methods The medical records of 25 dogs with primary adrenal masses who underwent contrast CT and a histopathological examination were retrospectively reviewed, of which 12 had adenomas (AAs), 7 had adenocarcinomas (ACCs), and 6 had pheochromocytomas (PHEOs). Conventional CT evaluation of each adrenal gland tumor included the mean, maximum, and minimum attenuation values in Hounsfield units (HU), heterogeneity of the tumor parenchyma, and contrast enhancement (type, pattern, and degree), respectively, in each phase. In CT texture analysis, precontrast and delayed-phase images of 18 adrenal gland tumors, which could be applied for ComBat harmonization were used, and 93 radiomic features (18 first-order and 75 second-order statistics) were extracted. Then, ComBat harmonization was applied to compensate for the batch effect created by the different CT protocols. The area under the receiver operating characteristic curve (AUC) for each significant feature was used to evaluate the diagnostic performance of CT texture analysis. Results Among the conventional features, PHEO showed significantly higher mean and maximum precontrast HU values than ACC (p < 0.05). Eight second-order features on the precontrast images showed significant differences between the adrenal gland tumors (p < 0.05). However, none of them were significantly different between AA and PHEO, or between precontrast images and delayed-phase images. This result indicates that ACC exhibited more heterogeneous and complex textures and more variable intensities with lower gray-level values than AA and PHEO. The correlation, maximal correlation coefficient, and gray level non-uniformity normalized were significantly different between AA and ACC, and between ACC and PHEO. These features showed high AUCs in discriminating ACC and PHEO, which were comparable or higher than the precontrast mean and maximum HU (AUC = 0.865 and 0.860, respectively). Conclusion Canine primary adrenal gland tumor differentiation can be achieved with CT texture analysis on precontrast images and may have a potential role in clinical decision-making. Further prospective studies with larger populations and cross-validation are warranted.
Collapse
Affiliation(s)
- Kyungsoo Lee
- Department of Veterinary Medical Imaging, College of Veterinary Medicine, Konkuk University, Seoul, Republic of Korea
| | - Jinhyong Goh
- Department of Veterinary Medical Imaging, College of Veterinary Medicine, Konkuk University, Seoul, Republic of Korea
| | - Jaeyoung Jang
- Jang Jae Young Veterinary Surgery Center, Seong-nam, Gyunggi-do, Republic of Korea
| | | | - Jungmin Kwak
- Saram and Animal Medical Center, Yongin-si, Gyunggi-do, Republic of Korea
| | - Jaehwan Kim
- Department of Veterinary Medical Imaging, College of Veterinary Medicine, Konkuk University, Seoul, Republic of Korea
| | - Kidong Eom
- Department of Veterinary Medical Imaging, College of Veterinary Medicine, Konkuk University, Seoul, Republic of Korea
| |
Collapse
|
3
|
Barge P, Oevermann A, Maiolini A, Durand A. Machine learning predicts histologic type and grade of canine gliomas based on MRI texture analysis. Vet Radiol Ultrasound 2023. [PMID: 37133981 DOI: 10.1111/vru.13242] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2022] [Revised: 03/16/2023] [Accepted: 03/21/2023] [Indexed: 05/04/2023] Open
Abstract
Conventional MRI features of canine gliomas subtypes and grades significantly overlap. Texture analysis (TA) quantifies image texture based on spatial arrangement of pixel intensities. Machine learning (ML) models based on MRI-TA demonstrate high accuracy in predicting brain tumor types and grades in human medicine. The aim of this retrospective, diagnostic accuracy study was to investigate the accuracy of ML-based MRI-TA in predicting canine gliomas histologic types and grades. Dogs with histopathological diagnosis of intracranial glioma and available brain MRI were included. Tumors were manually segmented across their entire volume in enhancing part, non-enhancing part, and peri-tumoral vasogenic edema in T2-weighted (T2w), T1-weighted (T1w), FLAIR, and T1w postcontrast sequences. Texture features were extracted and fed into three ML classifiers. Classifiers' performance was assessed using a leave-one-out cross-validation approach. Multiclass and binary models were built to predict histologic types (oligodendroglioma vs. astrocytoma vs. oligoastrocytoma) and grades (high vs. low), respectively. Thirty-eight dogs with a total of 40 masses were included. Machine learning classifiers had an average accuracy of 77% for discriminating tumor types and of 75.6% for predicting high-grade gliomas. The support vector machine classifier had an accuracy of up to 94% for predicting tumor types and up to 87% for predicting high-grade gliomas. The most discriminative texture features of tumor types and grades appeared related to the peri-tumoral edema in T1w images and to the non-enhancing part of the tumor in T2w images, respectively. In conclusion, ML-based MRI-TA has the potential to discriminate intracranial canine gliomas types and grades.
Collapse
Affiliation(s)
- Pablo Barge
- Division of Clinical Radiology, Department of Clinical Veterinary Science, Vetsuisse Faculty, University of Bern, Bern, Switzerland
| | - Anna Oevermann
- Division of Neurological Sciences, Department of Clinical Research and Veterinary Public Health, Vetsuisse Faculty, University of Bern, Bern, Switzerland
| | - Arianna Maiolini
- Division of Clinical Neurology, Department of Clinical Veterinary Science, Vetsuisse Faculty, University of Bern, Bern, Switzerland
| | - Alexane Durand
- Division of Clinical Radiology, Department of Clinical Veterinary Science, Vetsuisse Faculty, University of Bern, Bern, Switzerland
| |
Collapse
|
4
|
Pereira AI, Franco-Gonçalo P, Leite P, Ribeiro A, Alves-Pimenta MS, Colaço B, Loureiro C, Gonçalves L, Filipe V, Ginja M. Artificial Intelligence in Veterinary Imaging: An Overview. Vet Sci 2023; 10:vetsci10050320. [PMID: 37235403 DOI: 10.3390/vetsci10050320] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2023] [Revised: 04/21/2023] [Accepted: 04/25/2023] [Indexed: 05/28/2023] Open
Abstract
Artificial intelligence and machine learning have been increasingly used in the medical imaging field in the past few years. The evaluation of medical images is very subjective and complex, and therefore the application of artificial intelligence and deep learning methods to automatize the analysis process would be very beneficial. A lot of researchers have been applying these methods to image analysis diagnosis, developing software capable of assisting veterinary doctors or radiologists in their daily practice. This article details the main methodologies used to develop software applications on machine learning and how veterinarians with an interest in this field can benefit from such methodologies. The main goal of this study is to offer veterinary professionals a simple guide to enable them to understand the basics of artificial intelligence and machine learning and the concepts such as deep learning, convolutional neural networks, transfer learning, and the performance evaluation method. The language is adapted for medical technicians, and the work already published in this field is reviewed for application in the imaging diagnosis of different animal body systems: musculoskeletal, thoracic, nervous, and abdominal.
Collapse
Affiliation(s)
- Ana Inês Pereira
- Department of Veterinary Science, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
| | - Pedro Franco-Gonçalo
- Department of Veterinary Science, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Veterinary and Animal Research Centre (CECAV), University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Associate Laboratory for Animal and Veterinary Sciences (AL4AnimalS), 5000-801 Vila Real, Portugal
| | - Pedro Leite
- Neadvance Machine Vision SA, 4705-002 Braga, Portugal
| | | | - Maria Sofia Alves-Pimenta
- Veterinary and Animal Research Centre (CECAV), University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Associate Laboratory for Animal and Veterinary Sciences (AL4AnimalS), 5000-801 Vila Real, Portugal
- Department of Animal Science, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
| | - Bruno Colaço
- Veterinary and Animal Research Centre (CECAV), University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Associate Laboratory for Animal and Veterinary Sciences (AL4AnimalS), 5000-801 Vila Real, Portugal
- Department of Animal Science, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
| | - Cátia Loureiro
- School of Science and Technology, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Department of Engineering, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
| | - Lio Gonçalves
- School of Science and Technology, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Department of Engineering, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Institute for Systems and Computer Engineering (INESC-TEC), Technology and Science, 4200-465 Porto, Portugal
| | - Vítor Filipe
- School of Science and Technology, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Department of Engineering, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Institute for Systems and Computer Engineering (INESC-TEC), Technology and Science, 4200-465 Porto, Portugal
| | - Mário Ginja
- Department of Veterinary Science, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Veterinary and Animal Research Centre (CECAV), University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal
- Associate Laboratory for Animal and Veterinary Sciences (AL4AnimalS), 5000-801 Vila Real, Portugal
| |
Collapse
|
5
|
Choi BK, Park S, Lee G, Chang D, Jeon S, Choi J. Can CT texture analysis parameters be used as imaging biomarkers for prediction of malignancy in canine splenic tumors? Vet Radiol Ultrasound 2023; 64:224-232. [PMID: 36285434 DOI: 10.1111/vru.13175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2022] [Revised: 08/16/2022] [Accepted: 08/16/2022] [Indexed: 11/29/2022] Open
Abstract
Splenic hemangiosarcoma has morphological similarities to benign nodular hyperplasia. Computed tomography (CT) texture analysis can analyze the texture of images that the naive human eye cannot detect. Recently, there have been attempts to incorporate CT texture analysis with artificial intelligence in human medicine. This retrospective, analytical design study aimed to assess the feasibility of CT texture analysis in splenic masses and investigate predictive biomarkers of splenic hemangiosarcoma in dogs. Parameters for dogs with hemangiosarcoma and nodular hyperplasia were compared, and an independent parameter that could differentiate between them was selected. Discriminant analysis was performed to assess the ability to discriminate the two splenic masses and compare the relative importance of the parameters. A total of 23 dogs were sampled, including 16 splenic nodular hyperplasia and seven hemangiosarcoma. In each dog, total 38 radiomic parameters were extracted from first-, second-, and higher-order matrices. Thirteen parameters had significant differences between hemangiosarcoma and nodular hyperplasia. Skewness in the first-order matrix and GLRLM_LGRE and GLZLM_ZLNU in the second, higher-order matrix were determined as independent parameters. A discriminant equation consisting of skewness, GLZLM_LGZE, and GLZLM_ZLNU was derived, and the cross-validation verification result showed an accuracy of 95.7%. Skewness was the most influential parameter for the discrimination of the two masses. The study results supported using CT texture analysis to help differentiate hemangiosarcoma from nodular hyperplasia in dogs. This new diagnostic approach can be used for developing future machine learning-based texture analysis tools.
Collapse
Affiliation(s)
- Bo-Kwon Choi
- College of Veterinary Medicine, Chonnam National University, Gwangju, Republic of Korea
| | - Seungjo Park
- College of Veterinary Medicine, Chonnam National University, Gwangju, Republic of Korea
| | - Gahyun Lee
- Haemaru Referral Animal Hospital, Seongnam, Republic of Korea
| | - Dongwoo Chang
- College of Veterinary Medicine, Chungbuk National University, Cheongju, Republic of Korea
| | - Sunghoon Jeon
- Haemaru Referral Animal Hospital, Seongnam, Republic of Korea
| | - Jihye Choi
- Department of Veterinary Medical Imaging, College of Veterinary Medicine and Research Institute for Veterinary Science, Seoul National University, Seoul, Republic of Korea
| |
Collapse
|
6
|
Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle. Vet Sci 2023; 10:vetsci10020113. [PMID: 36851417 PMCID: PMC9960640 DOI: 10.3390/vetsci10020113] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2023] [Revised: 01/27/2023] [Accepted: 01/31/2023] [Indexed: 02/05/2023] Open
Abstract
Bovine respiratory disease (BRD) and acute interstitial pneumonia (AIP) are the main reported respiratory syndromes (RSs) causing significant morbidity and mortality in feedlot cattle. Recently, bronchopneumonia with an interstitial pattern (BIP) was described as a concerning emerging feedlot lung disease. Necropsies are imperative to assist lung disease diagnosis and pinpoint feedlot management sectors that require improvement. However, necropsies can be logistically challenging due to location and veterinarians' time constraints. Technology advances allow image collection for veterinarians' asynchronous evaluation, thereby reducing challenges. This study's goal was to develop image classification models using machine learning to determine RS diagnostic accuracy in right lateral necropsied feedlot cattle lungs. Unaltered and cropped lung images were labeled using gross and histopathology diagnoses generating four datasets: unaltered lung images labeled with gross diagnoses, unaltered lung images labeled with histopathological diagnoses, cropped images labeled with gross diagnoses, and cropped images labeled with histopathological diagnoses. Datasets were exported to create image classification models, and a best trial was selected for each model based on accuracy. Gross diagnoses accuracies ranged from 39 to 41% for unaltered and cropped images. Labeling images with histopathology diagnoses did not improve average accuracies; 34-38% for unaltered and cropped images. Moderately high sensitivities were attained for BIP (60-100%) and BRD (20-69%) compared to AIP (0-23%). The models developed still require fine-tuning; however, they are the first step towards assisting veterinarians' lung diseases diagnostics in field necropsies.
Collapse
|
7
|
Hennessey E, DiFazio M, Hennessey R, Cassel N. Artificial intelligence in veterinary diagnostic imaging: A literature review. Vet Radiol Ultrasound 2022; 63 Suppl 1:851-870. [PMID: 36468206 DOI: 10.1111/vru.13163] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2022] [Revised: 05/05/2022] [Accepted: 07/07/2022] [Indexed: 12/09/2022] Open
Abstract
Artificial intelligence in veterinary medicine is an emerging field. Machine learning, a subfield of artificial intelligence, allows computer programs to analyze large imaging datasets and learn to perform tasks relevant to veterinary diagnostic imaging. This review summarizes the small, yet growing body of artificial intelligence literature in veterinary imaging, provides necessary background to understand these papers, and provides author commentary on the state of the field. To date, less than 40 peer-reviewed publications have utilized machine learning to perform imaging-associated tasks across multiple anatomic regions in veterinary clinical and biomedical research. Major challenges in this field include collection and cleaning of sufficient image data, selection of high-quality ground truth labels, formation of relationships between veterinary and machine learning professionals, and closure of the gap between academic uses of artificial intelligence and currently available commercial products. Further development of artificial intelligence has the potential to help meet the growing need for radiological services through applications in workflow, quality control, and image interpretation for both general practitioners and radiologists.
Collapse
Affiliation(s)
- Erin Hennessey
- Department of Clinical Sciences, College of Veterinary Medicine, Kansas State University, Manhattan, Kansas, USA.,Army Medical Department, Student Detachment, San Antonio, Texas, USA
| | - Matthew DiFazio
- Department of Clinical Sciences, College of Veterinary Medicine, Kansas State University, Manhattan, Kansas, USA
| | - Ryan Hennessey
- Department of Computer Science, College of Engineering, Kansas State University, Manhattan, Kansas, USA
| | - Nicky Cassel
- Department of Clinical Sciences, College of Veterinary Medicine, Kansas State University, Manhattan, Kansas, USA
| |
Collapse
|
8
|
Lisciandro GR, Puchot ML, Gambino JM, Lisciandro SC. The wedge sign: A possible lung ultrasound sign for pulmonary thromboembolism. J Vet Emerg Crit Care (San Antonio) 2022; 32:663-669. [PMID: 35522423 DOI: 10.1111/vec.13208] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2020] [Revised: 03/05/2021] [Accepted: 03/27/2021] [Indexed: 11/30/2022]
Abstract
OBJECTIVE To describe the finding of the lung ultrasound (LUS) "wedge sign" in dogs with presumptive pulmonary thromboembolism (PTE). CASE SERIES SUMMARY This case series describes 2 dogs with predisposing risk factors of (1) right transvenous pacemaker terminating in its right ventricle, severe protein-losing nephropathy, and glucocorticoid therapy, and (2) caval syndrome, each having the LUS "wedge sign" in upper lung regions, a sign consistent with pulmonary infarction and peripheral PTE. NEW OR UNIQUE INFORMATION PROVIDED Historically, the diagnosis of canine PTE has been made through supportive findings because the gold standard test, computed tomography pulmonary angiography (CTPA), poses limitations. The use of LUS has shown promise in people for detecting PTE, with the advantages of availability, being radiation- and contrast medium-sparing, rapid (<90 s), point-of-care, real-time information. Our cases suggest a possible new first-line approach for suspecting canine PTE by using LUS and the finding of the "wedge sign" in nongravity-dependent caudodorsal and perihilar lung regions.
Collapse
|
9
|
Pantic IV, Shakeel A, Petroianu GA, Corridon PR. Analysis of Vascular Architecture and Parenchymal Damage Generated by Reduced Blood Perfusion in Decellularized Porcine Kidneys Using a Gray Level Co-occurrence Matrix. Front Cardiovasc Med 2022; 9:797283. [PMID: 35360034 PMCID: PMC8963813 DOI: 10.3389/fcvm.2022.797283] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2021] [Accepted: 02/07/2022] [Indexed: 12/15/2022] Open
Abstract
There is no cure for kidney failure, but a bioartificial kidney may help address this global problem. Decellularization provides a promising platform to generate transplantable organs. However, maintaining a viable vasculature is a significant challenge to this technology. Even though angiography offers a valuable way to assess scaffold structure/function, subtle changes are overlooked by specialists. In recent years, various image analysis methods in radiology have been suggested to detect and identify subtle changes in tissue architecture. The aim of our research was to apply one of these methods based on a gray level co-occurrence matrix (Topalovic et al.) computational algorithm in the analysis of vascular architecture and parenchymal damage generated by hypoperfusion in decellularized porcine. Perfusion decellularization of the whole porcine kidneys was performed using previously established protocols. We analyzed and compared angiograms of kidneys subjected to pathophysiological arterial perfusion of whole blood. For regions of interest Santos et al. covering kidney medulla and the main elements of the vascular network, five major GLCM features were calculated: angular second moment as an indicator of textural uniformity, inverse difference moment as an indicator of textural homogeneity, GLCM contrast, GLCM correlation, and sum variance of the co-occurrence matrix. In addition to GLCM, we also performed discrete wavelet transform analysis of angiogram ROIs by calculating the respective wavelet coefficient energies using high and low-pass filtering. We report statistically significant changes in GLCM and wavelet features, including the reduction of the angular second moment and inverse difference moment, indicating a substantial rise in angiogram textural heterogeneity. Our findings suggest that the GLCM method can be successfully used as an addition to conventional fluoroscopic angiography analyses of micro/macrovascular integrity following in vitro blood perfusion to investigate scaffold integrity. This approach is the first step toward developing an automated network that can detect changes in the decellularized vasculature.
Collapse
Affiliation(s)
- Igor V Pantic
- Department of Medical Physiology, Faculty of Medicine, University of Belgrade, Belgrade, Serbia.,University of Haifa, Haifa, Israel
| | - Adeeba Shakeel
- Department of Pharmacology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates
| | - Georg A Petroianu
- Department of Immunology and Physiology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates
| | - Peter R Corridon
- Department of Pharmacology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.,Wake Forest Institute for Regenerative Medicine, Medical Center Boulevard, Winston-Salem, NC, United States.,Biomedical Engineering, Healthcare Engineering Innovation Center, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.,Center for Biotechnology, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates
| |
Collapse
|
10
|
Clinical Characteristics of Patients with Pulmonary Thromboembolism Based on Computer Statistical Analysis. JOURNAL OF HEALTHCARE ENGINEERING 2022; 2022:1112960. [PMID: 35242294 PMCID: PMC8888095 DOI: 10.1155/2022/1112960] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/11/2021] [Revised: 01/21/2022] [Accepted: 01/27/2022] [Indexed: 02/02/2023]
Abstract
In order to explore the reliable clinical characteristics of patients with pulmonary thromboembolism, this paper applies computer statistical analysis methods to the analysis of clinical characteristics of patients with pulmonary thromboembolism. Moreover, starting from the actual situation, this paper combines experiments to study the case, uses sample screening and sample processing to group samples freely, and conducts grouping reliability research through data statistics methods. After verifying the reliability of the grouping, this paper combines the samples to test the effectiveness of the computer statistical analysis method applied to the clinical characteristic analysis of patients with pulmonary thromboembolism and conducts numerical analysis in combination with the comparative analysis method. The results of the research show that the computer statistical method proposed in this paper has a good effect on the clinical characteristics of patients with pulmonary thromboembolism and meets the actual needs of clinical analysis.
Collapse
|
11
|
Able H, Wolf-Ringwall A, Rendahl A, Ober CP, Seelig DM, Wilke CT, Lawrence J. Computed tomography radiomic features hold prognostic utility for canine lung tumors: An analytical study. PLoS One 2021; 16:e0256139. [PMID: 34403435 PMCID: PMC8370631 DOI: 10.1371/journal.pone.0256139] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2021] [Accepted: 07/29/2021] [Indexed: 12/02/2022] Open
Abstract
Quantitative analysis of computed tomography (CT) radiomic features is an indirect measure of tumor heterogeneity, which has been associated with prognosis in human lung carcinoma. Canine lung tumors share similar features to human lung tumors and serve as a model in which to investigate the utility of radiomic features in differentiating tumor type and prognostication. The purpose of this study was to correlate first-order radiomic features from canine pulmonary tumors to histopathologic characteristics and outcome. Disease-free survival, overall survival time and tumor-specific survival were calculated as days from the date of CT scan. Sixty-seven tumors from 65 dogs were evaluated. Fifty-six tumors were classified as primary pulmonary adenocarcinomas and 11 were non-adenocarcinomas. All dogs were treated with surgical resection; 14 dogs received adjuvant chemotherapy. Second opinion histopathology in 63 tumors confirmed the histologic diagnosis in all dogs and further characterized 53 adenocarcinomas. The median overall survival time was longer (p = 0.004) for adenocarcinomas (339d) compared to non-adenocarcinomas (55d). There was wide variation in first-order radiomic statistics across tumors. Mean Hounsfield units (HU) ratio (p = 0.042) and median mean HU ratio (p = 0.042) were higher in adenocarcinomas than in non-adenocarcinomas. For dogs with adenocarcinoma, completeness of excision was associated with overall survival (p<0.001) while higher mitotic index (p = 0.007) and histologic score (p = 0.037) were associated with shorter disease-free survival. CT-derived tumor variables prognostic for outcome included volume, maximum axial diameter, and four radiomic features: integral total, integral total mean ratio, total HU, and max mean HU ratio. Tumor volume was also significantly associated with tumor invasion (p = 0.044). Further study of radiomic features in canine lung tumors is warranted as a method to non-invasively interrogate CT images for potential predictive and prognostic utility.
Collapse
Affiliation(s)
- Hannah Able
- Department of Veterinary Clinical Sciences, College of Veterinary Medicine, University of Minnesota, Saint Paul, Minnesota, United States of America
- * E-mail: (HA); (JL)
| | - Amber Wolf-Ringwall
- Department of Veterinary Clinical Sciences, College of Veterinary Medicine, University of Minnesota, Saint Paul, Minnesota, United States of America
- Masonic Cancer Center, University of Minnesota, Minneapolis, Minnesota, United States of America
| | - Aaron Rendahl
- Department of Veterinary and Biomedical Sciences, College of Veterinary Medicine, University of Minnesota, Minneapolis, Minnesota, United States of America
| | - Christopher P. Ober
- Department of Veterinary Clinical Sciences, College of Veterinary Medicine, University of Minnesota, Saint Paul, Minnesota, United States of America
| | - Davis M. Seelig
- Department of Veterinary Clinical Sciences, College of Veterinary Medicine, University of Minnesota, Saint Paul, Minnesota, United States of America
- Masonic Cancer Center, University of Minnesota, Minneapolis, Minnesota, United States of America
| | - Chris T. Wilke
- Masonic Cancer Center, University of Minnesota, Minneapolis, Minnesota, United States of America
- Department of Radiation Oncology, Medical School, University of Minnesota, Minneapolis, Minnesota, United States of America
| | - Jessica Lawrence
- Department of Veterinary Clinical Sciences, College of Veterinary Medicine, University of Minnesota, Saint Paul, Minnesota, United States of America
- Masonic Cancer Center, University of Minnesota, Minneapolis, Minnesota, United States of America
- * E-mail: (HA); (JL)
| |
Collapse
|
12
|
Burti S, Longhin Osti V, Zotti A, Banzato T. Use of deep learning to detect cardiomegaly on thoracic radiographs in dogs. Vet J 2020; 262:105505. [PMID: 32792095 DOI: 10.1016/j.tvjl.2020.105505] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2019] [Revised: 07/04/2020] [Accepted: 07/06/2020] [Indexed: 12/31/2022]
Abstract
The purpose of this study was to develop a computer-aided detection (CAD) device based on convolutional neural networks (CNNs) to detect cardiomegaly from plain radiographs in dogs. Right lateral chest radiographs (n = 1465) were retrospectively selected from archives. The radiographs were classified as having a normal cardiac silhouette (No-vertebral heart scale [VHS]-Cardiomegaly) or an enlarged cardiac silhouette (VHS-Cardiomegaly) based on the breed-specific VHS. The database was divided into a training set (1153 images) and a test set (315 images). The diagnostic accuracy of four different CNN models in the detection of cardiomegaly was calculated using the test set. All tested models had an area under the curve >0.9, demonstrating high diagnostic accuracy. There was a statistically significant difference between Model C and the remainder models (Model A vs. Model C, P = 0.0298; Model B vs. Model C, P = 0.003; Model C vs. Model D, P = 0.0018), but there were no significant differences between other combinations of models (Model A vs. Model B, P = 0.395; Model A vs. Model D, P = 0.128; Model B vs. Model D, P = 0.373). Convolutional neural networks could therefore assist veterinarians in detecting cardiomegaly in dogs from plain radiographs.
Collapse
Affiliation(s)
- S Burti
- Department of Animal Medicine, Productions and Health, University of Padua, Viale Dell'Università 16, 35020 Legnaro, Padua, Italy
| | - V Longhin Osti
- Department of Animal Medicine, Productions and Health, University of Padua, Viale Dell'Università 16, 35020 Legnaro, Padua, Italy
| | - A Zotti
- Department of Animal Medicine, Productions and Health, University of Padua, Viale Dell'Università 16, 35020 Legnaro, Padua, Italy
| | - T Banzato
- Department of Animal Medicine, Productions and Health, University of Padua, Viale Dell'Università 16, 35020 Legnaro, Padua, Italy.
| |
Collapse
|
13
|
An Exploratory Radiomics Approach to Quantifying Pulmonary Function in CT Images. Sci Rep 2019; 9:11509. [PMID: 31395937 PMCID: PMC6687824 DOI: 10.1038/s41598-019-48023-5] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2018] [Accepted: 07/26/2019] [Indexed: 01/04/2023] Open
Abstract
Contemporary medical imaging is becoming increasingly more quantitative. The emerging field of radiomics is a leading example. By translating unstructured data (i.e., images) into structured data (i.e., imaging features), radiomics can potentially characterize clinically useful imaging phenotypes. In this paper, an exploratory radiomics approach is used to investigate the potential association between quantitative imaging features and pulmonary function in CT images. Thirty-nine radiomic features were extracted from the lungs of 64 patients as potential imaging biomarkers for pulmonary function. Collectively, these features capture the morphology of the lungs, as well as intensity variations, fine-texture, and coarse-texture of the pulmonary tissue. The extracted lung radiomics data was compared to conventional pulmonary function tests. In general, patients with larger lungs of homogeneous, low attenuating pulmonary tissue (as measured via radiomics) were found to be associated with poor spirometry performance and a lower diffusing capacity for carbon monoxide. Unsupervised dynamic data clustering revealed subsets of patients with similar lung radiomic patterns that were found to be associated with similar forced expiratory volume in one second (FEV1) measurements. This implies that patients with similar radiomic feature vectors also presented with comparable spirometry performance, and were separable by varying degrees of pulmonary function as measured by imaging.
Collapse
|
14
|
Banzato T, Bernardini M, Cherubini GB, Zotti A. A methodological approach for deep learning to distinguish between meningiomas and gliomas on canine MR-images. BMC Vet Res 2018; 14:317. [PMID: 30348148 PMCID: PMC6196418 DOI: 10.1186/s12917-018-1638-2] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2018] [Accepted: 10/01/2018] [Indexed: 01/12/2023] Open
Abstract
Background Distinguishing between meningeal-based and intra-axial lesions by means of magnetic resonance (MR) imaging findings may occasionally be challenging. Meningiomas and gliomas account for most of the total primary brain neoplasms in dogs, and differentiating between these two forms is mandatory in choosing the correct therapy. The aims of the present study are: 1) to determine the accuracy of a deep convolutional neural network (CNN, GoogleNet) in discriminating between meningiomas and gliomas in pre- and post-contrast T1 images and T2 images; 2) to develop an image classifier, based on the combination of CNN and MRI sequence displaying the highest accuracy, to predict whether a lesion is a meningioma or a glioma. Results Eighty cases with a final diagnosis of meningioma (n = 56) and glioma (n = 24) from two different institutions were included in the study. A pre-trained CNN was retrained on our data through a process called transfer learning. To evaluate CNN accuracy in the different imaging sequences, the dataset was divided into a training, a validation and a test set. The accuracy of the CNN was calculated on the test set. The combination between post-contrast T1 images and CNN was chosen in developing the image classifier (trCNN). Ten images from challenging cases were excluded from the database in order to test trCNN accuracy; the trCNN was trained on the remainder of the dataset of post-contrast T1 images, and correctly classified all the selected images. To compensate for the imbalance between meningiomas and gliomas in the dataset, the Matthews correlation coefficient (MCC) was also calculated. The trCNN showed an accuracy of 94% (MCC = 0.88) on post-contrast T1 images, 91% (MCC = 0.81) on pre-contrast T1-images and 90% (MCC = 0.8) on T2 images. Conclusions The developed trCNN could be a reliable tool in distinguishing between different meningiomas and gliomas from MR images.
Collapse
Affiliation(s)
- Tommaso Banzato
- Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, AGRIPOLIS, Legnaro, 35020, Padua, Italy
| | - Marco Bernardini
- Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, AGRIPOLIS, Legnaro, 35020, Padua, Italy.,Portoni Rossi Veterinary Hospital, Via Roma 57, Zola Predosa, 40069, Bologna, Italy
| | | | - Alessandro Zotti
- Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, AGRIPOLIS, Legnaro, 35020, Padua, Italy.
| |
Collapse
|
15
|
Aoki K, Izumi Y, Watanabe W, Shimizu Y, Osada H, Honda N, Itoh T, Nakayama M. Generation of ventilation/perfusion ratio map in surgical patients by dual-energy CT after xenon inhalation and intravenous contrast media. J Cardiothorac Surg 2018; 13:43. [PMID: 29776385 PMCID: PMC5960088 DOI: 10.1186/s13019-018-0737-2] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2018] [Accepted: 05/10/2018] [Indexed: 11/15/2022] Open
Abstract
Background While many studies have evaluated the change in lung volume before and after lung resection and correlated this with pulmonary function test results, there is very little evidence on the changes in ventilation perfusion ratio (V/Q) before versus after lung resection. In the present pilot study, we evaluated if V/Q mapping can be constructed using dual energy CT images. Methods Thirty-one lung cancer patients planned for pulmonary resection were included in this study. To evaluate ventilation, Xenon-enhanced CT was performed. This was immediately followed by perfusion CT. The two images were registered manually as well as using dedicated softwares, and division between ventilation pixels and perfusion pixels were done to produce the V/Q map. Also, in order to characterize the distribution of the V/Q, the following numerical indices were calculated; mean, median, mode, standard deviation (SD), coefficient of variation (CV), skewness, kurtosis, and fractal dimension (FD). Pulmonary function tests and blood gas parameters were measured using standard institutional procedures. Results In the whole group, VC, %VC, and FEV1 decreased significantly after resection. FEV1.0% was increased significantly after resection. No significant changes were seen in PaO2, PaCO2, and DLCO/VA before and after resection. The mean, median, mode, SD, skewness, kurtosis and FD of the V/Q did not change significantly before and after resection. A marginal but significant decrease in CV was seen before versus after resection. Conclusions Overall, it was considered that the V/Q maps could be adequately generated in this study. With further accumulation of data, V/Q map generated by dual energy CT may become one of the potentially useful tools for functional lung imaging. Trial registration This trial was registered in University Medical Information Network in Japan (UMIN000010023) on 13Feb2013.
Collapse
Affiliation(s)
- Kohei Aoki
- Department of General Thoracic Surgery, Saitama Medical University, Medical Center, 1981 Kamoda, Kawagoeshi, Saitama, 350-8550, Japan
| | - Yotaro Izumi
- Department of General Thoracic Surgery, Saitama Medical University, Medical Center, 1981 Kamoda, Kawagoeshi, Saitama, 350-8550, Japan.
| | - Wataru Watanabe
- Department of Radiology, Saitama Medical University, Medical Center, 1981 Kamoda, Kawagoeshi, Saitama, 350-8550, Japan
| | - Yuji Shimizu
- Department of Radiology, Saitama Medical University, Medical Center, 1981 Kamoda, Kawagoeshi, Saitama, 350-8550, Japan
| | - Hisato Osada
- Department of Radiology, Saitama Medical University, Medical Center, 1981 Kamoda, Kawagoeshi, Saitama, 350-8550, Japan
| | - Norinari Honda
- Department of Radiology, Saitama Medical University, Medical Center, 1981 Kamoda, Kawagoeshi, Saitama, 350-8550, Japan
| | - Toshihide Itoh
- Research and Collaboration Department, Siemens Healthcare, 1-11-1 Osaki, Shinagawa-ku, Tokyo, 141-8644, Japan
| | - Mitsuo Nakayama
- Department of General Thoracic Surgery, Saitama Medical University, Medical Center, 1981 Kamoda, Kawagoeshi, Saitama, 350-8550, Japan
| |
Collapse
|
16
|
Banzato T, Bonsembiante F, Aresu L, Gelain M, Burti S, Zotti A. Use of transfer learning to detect diffuse degenerative hepatic diseases from ultrasound images in dogs: A methodological study. Vet J 2018; 233:35-40. [DOI: 10.1016/j.tvjl.2017.12.026] [Citation(s) in RCA: 20] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2017] [Revised: 12/27/2017] [Accepted: 12/31/2017] [Indexed: 02/07/2023]
|