Artificial intelligence evaluating primary thoracic lesions has an overall lower error rate compared to veterinarians or veterinarians in conjunction with the artificial intelligence.
computer vision-based decision support system
convolutional neural networks
deep learning
small animal thoracic radiology
Journal
Veterinary radiology & ultrasound : the official journal of the American College of Veterinary Radiology and the International Veterinary Radiology Association
ISSN: 1740-8261
Titre abrégé: Vet Radiol Ultrasound
Pays: England
ID NLM: 9209635
Informations de publication
Date de publication:
Nov 2020
Nov 2020
Historique:
received:
13
04
2020
revised:
30
06
2020
accepted:
12
07
2020
pubmed:
1
10
2020
medline:
2
1
2021
entrez:
30
9
2020
Statut:
ppublish
Résumé
To date, deep learning technologies have provided powerful decision support systems to radiologists in human medicine. The aims of this retrospective, exploratory study were to develop and describe an artificial intelligence able to screen thoracic radiographs for primary thoracic lesions in feline and canine patients. Three deep learning networks using three different pretraining strategies to predict 15 types of primary thoracic lesions were created (including tracheal collapse, left atrial enlargement, alveolar pattern, pneumothorax, and pulmonary mass). Upon completion of pretraining, the algorithms were provided with over 22 000 thoracic veterinary radiographs for specific training. All radiographs had a report created by a board-certified veterinary radiologist used as the gold standard. The performances of all three networks were compared to one another. An additional 120 radiographs were then evaluated by three types of observers: the best performing network, veterinarians, and veterinarians aided by the network. The error rates for each of the observers was calculated as an overall and for the 15 labels and were compared using a McNemar's test. The overall error rate of the network was significantly better than the overall error rate of the veterinarians or the veterinarians aided by the network (10.7% vs 16.8% vs17.2%, P = .001). The network's error rate was significantly better to detect cardiac enlargement and for bronchial pattern. The current network only provides help in detecting various lesion types and does not provide a diagnosis. Based on its overall very good performance, this could be used as an aid to general practitioners while waiting for the radiologist's report.
Types de publication
Comparative Study
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
619-627Informations de copyright
© 2020 American College of Veterinary Radiology.
Références
Burns JE, Yao J, Muñoz H, Summers RM. Automated detection, localization, and classification of traumatic vertebral body fractures in the thoracic and lumbar spine at CT. Radiology. 2016;278(1):64-73.
Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284(2):574-582.
Maier O, Schröder C, Forkert ND, Martinetz T, Handels H. Classifiers for ischemic stroke lesion segmentation: a comparison study. PLoS One. 2015;10(12):e0145118.
Taylor AG, Mielke C, Mongan J. Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: a retrospective study. PLoS Med. 2018;15(11):e1002697.
Juliusson G, Thorvaldsdottir B, Kristjansson JM, Hannesson P. Diagnostic imaging trends in the emergency department: an extensive single-center experience. Acta Radiol Open. 2019;8(7):2058460119860404.
Rodriguez-Ruiz A, Lång K, Gubern-Merida A, et al. Stand-alone artificial intelligence for breast cancer detection in mammography: comparison with 101 radiologists. J Natl Cancer Inst. 2019;111(9):916-922. https://doi.org/10.1093/jnci/djy222
Yoon Y, Hwang T, Lee H. Prediction of radiographic abnormalities by the use of bag-of-features and convolutional neural networks. Vet J. 2018;237:43-48. https://doi.org/10.1016/j.tvjl.2018.05.009
Donald JJ, Barnard SA. Common patterns in 558 diagnostic radiology errors. J Med Imaging Radiat Oncol. 2012;56(2):173-178. https://doi.org/10.1111/j.1754-9485.2012.02348.x
Gaschen L. Pitfalls of thoracic radiography: don't let them trap you. WSAVA Proc. 2010. https://www.vin.com/apputil/content/defaultadv1.aspx?pId=11310&id=4516254&print=1
Thrall DE. Textbook of Veterinary Diagnostic Radiology. Amsterdam, the Netherlands: Elsevier Health Sciences; 2017.
Irvin J, Rajpurkar P, Ko M, et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. ArXiv190107031 Cs Eess. http://arxiv.org/abs/1901.07031. Accessed April 6, 2020.
Putha P, Tadepalli M, Reddy B, et al. Can artificial intelligence reliably report chest X-rays? Radiologist validation of an algorithm trained on 2.3 million X-rays. ArXiv180707455 Cs. http://arxiv.org/abs/1807.07455. Accessed April 7, 2020.
Giraldo Forero AF, Jaramillo-Garzón J, Ruiz-Muñoz J, Castellanos-Dominguez G. Managing imbalanced data sets in multi-label problems: a case study with the SMOTE algorithm. Lect Notes Comput Sci. 2013;8258:334-342.
Perez L, Wang J, The effectiveness of data augmentation in image classification using deep learning. ArXiv171204621 Cs. http://arxiv.org/abs/1712.04621. Accessed April 7, 2020.
Paszke A, Gross S, Chintala S, et al. Automatic differentiation in PyTorch.4. https://openreview.net/pdf/25b8eee6c373d48b84e5e9c6e10e7cbbbce4ac73.pdf
Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. ArXiv160806993 Cs. http://arxiv.org/abs/1608.06993. Accessed April 6, 2020.
He K, Girshick R, Dollár P, Rethinking ImageNet pre-training. ArXiv181108883 Cs. http://arxiv.org/abs/1811.08883. Accessed April 7, 2020.
Ling CX, Huang J, Zhang H, AUC: a Statistically Consistent and more Discriminating Measure than Accuracy.6.
Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif. 2000:10.
Tan C, Sun F, Kong T, Zhang W, Yang C, Liu C, A survey on deep transfer learning. ArXiv180801974 Cs Stat. http://arxiv.org/abs/1808.01974. Accessed April 7, 2020.
Raghu M, Kleinberg J, Zhang C, Bengio S, Transfusion: Understanding Transfer Learning for Medical Imaging. 11. https://papers.nips.cc/paper/8596-transfusion-understanding-transfer-learning-for-medical-imaging.pdf
Deng J, Dong W, Socher R, Li L-J, Li Kai, Fei-Fei Li, ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition.; 2009:248-255. https://ieeexplore.ieee.org/document/5206848
Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM, ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. 2017 IEEE Conf Comput Vis Pattern Recognit CVPR. 2017:3462-3471. https://arxiv.org/abs/1705.02315
McCloskey M, Cohen NJ. Catastrophic interference in connectionist networks: the sequential learning problem. In: Bower GH, ed. Psychology of Learning and Motivation. Cambridge, MA: Academic Press; 1989:109-165.
Dietterich TG. Ensemble methods in machine learning. Multiple Classifier Systems. Vol 1857. Lecture Notes in Computer Science. Berlin, Heidelberg: Springer; 2000:1-15.
Opitz D, Maclin R. Popular ensemble methods: an empirical study. J Artif Intell Res. 1999;11:169-198.
Shiraishi J, Li Q, Suzuki K, Engelmann R, Doi K. Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification. Med Phys. 2006;33(7):2642-2653.
Howard AG, Zhu M, Chen B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. ArXiv170404861 Cs. 2017. http://arxiv.org/abs/1704.04861. Accessed April 7, 2020.
Zoph B, Vasudevan V, Shlens J, Le QV, Learning transferable architectures for scalable image recognition. ArXiv170707012 Cs Stat. http://arxiv.org/abs/1707.07012. Accessed April 7, 2020.
He K, Zhang X, Ren S, Sun J, Deep residual learning for image recognition. ArXiv151203385 Cs. http://arxiv.org/abs/1512.03385. Accessed April 7, 2020.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017;60(6):84-90.
Maggiori E, Tarabalka Y, Charpiat G, Alliez P, High-resolution image classification with convolutional networks. In: 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS); 2017:5157-5160. https://ieeexplore.ieee.org/document/8128163
Huang Y, Chung AC. Improving high resolution histology image classification with deep spatial fusion network. ArXiv180710552 Cs. 2018;11039:19-26.
Iftene M, Qingjie L, Yunhong W. Very high resolution images classification by fusing deep convolutional neural networks. In: 2017. https://www.clausiuspress.com/conferences/ACSS/ACSAT%202017/GACS57.pdf
Kotsiantis S, Kanellopoulos D, Pintelas P. Handling imbalanced datasets: a review. GESTS Int Trans Comput Sci Eng. 2005;30:25-36.