Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs

Investigative Radiology

Volumn 52, Issue 5, 2017, Pages 281-287

  Cicero, Mark ^a   Bilbily, Alexander ^a   Colak, Errol ^a   Dowdell, Tim ^a   Gray, Bruce ^a   Perampaladas, Kuhan ^b   Barfett, Joseph ^a  

^a ST MICHAEL'S HOSPITAL   (Canada)

^b UNIVERSITY OF TORONTO   (Canada)

Author keywords

cardiomegaly; machine learning; neural network; pleural effusion; pneumonia; pneumothorax; pulmonary edema; x ray

Indexed keywords

ACCURACY; ADULT; ARTICLE; ARTIFICIAL NEURAL NETWORK; CARDIOMEGALY; COMPUTER ASSISTED DIAGNOSIS; CONGENITAL MALFORMATION; DIAGNOSTIC IMAGING; EMERGENCY WARD; FEMALE; HOSPITAL PATIENT; HUMAN; LUNG EDEMA; MAJOR CLINICAL STUDY; MALE; MEDICAL RECORD REVIEW; MIDDLE AGED; OUTPATIENT; PLEURA EFFUSION; PNEUMOTHORAX; PREDICTIVE VALUE; PRIORITY JOURNAL; RADIOLOGIST; SENSITIVITY AND SPECIFICITY; THORAX RADIOGRAPHY; TRAINING; VALIDATION PROCESS; HEART; HEART DISEASE; LUNG; LUNG DISEASE; PROCEDURES; REPRODUCIBILITY; RETROSPECTIVE STUDY; VALIDATION STUDY;

DIAGNOSIS, COMPUTER-ASSISTED; FEMALE; HEART; HEART DISEASES; HUMANS; LUNG; LUNG DISEASES; MALE; MIDDLE AGED; NEURAL NETWORKS (COMPUTER); RADIOGRAPHY, THORACIC; REPRODUCIBILITY OF RESULTS; RETROSPECTIVE STUDIES; SENSITIVITY AND SPECIFICITY;

EID: 85001976294     PISSN: 00209996     EISSN: 15360210     Source Type: Journal    
DOI: 10.1097/RLI.0000000000000341     Document Type: Article

References (16)

1. Krishevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1106-1114.
2. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. arXiv preprint arXiv. 2015; 1512.03385.
3. Szegedy C, LiuW, Jia Y, et al. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015:1-9.
4. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by backpropagating errors. Cogn Model. 1988;5:1.
5. Groves P, Kayyali B, Knott D, et al. The 'big data' revolution in healthcare - accelerating value and innovation. Center for US Health System Reform Business Technology Office. 2013:1-17.
6. Bar Y, Diamant I, Wolf L, et al Deep learning with non-medical training used for chest pathology identification. In:SPIE Medical Imaging. International Society for Optics and Photonics. 2015;94140V.
7. Depeursinge A, Chin AS, Leung AN, et al. Automated classification of usual interstitial pneumonia using regional volumetric texture analysis in high-resolution computed tomography. Invest Radiol. 2015;50:261-267.
8. Naing L, Winn T, Rusli BN. Practical issues in calculating the sample size for prevalence studies. Med Stat Arch Orofacial Sci. 2006;1:9-14.
9. Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks. arXiv. 2014; 1312.6199v4.
10. Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv. 2013; 1311.2524.
11. Huang C, Li Y, Change Loy C, et al. Learning deep representation for imbalanced classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016:5375-5384.
12. Altman DG, Bland JM. Diagnostic tests 2: predictive values. BMJ. 1994;309:102.
13. Zhou X, Li S, Qin K, et al. Deep adaptive network: an efficient deep neural network with sparse binary connections. arXiv preprint arXiv. 2016; 1604.06154.
14. Zintgraf L, Cohen T,WellingM.A newmethod to visualize deep neural networks. arXiv. 2016; 1603.02518v2.
15. Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell. 2016; 1506.01497v3.
16. Dou Q, Chen H, Yu L, et al. Automatic detection of cerebral microbleeds fromMR images via 3D convolutional neural networks. IEEE Trans Med Imaging. 2016; 35:1182-1195.