Automated identification of thoracic pathology from chest radiographs with enhanced training pipeline

Adora M. DSouza; Anas Z. Abidin; Axel Wismüller

doi:10.1117/12.2512600

13 March 2019 Automated identification of thoracic pathology from chest radiographs with enhanced training pipeline

Adora M. DSouza, Anas Z. Abidin, Axel Wismüller

Proceedings Volume 10950, Medical Imaging 2019: Computer-Aided Diagnosis; 109503F (2019) https://doi.org/10.1117/12.2512600
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

Abstract

Chest x-rays are the most common radiology studies for diagnosing lung and heart disease. Hence, a system for automated pre-reporting of pathologic findings on chest x-rays would greatly enhance radiologists’ productivity. To this end, we investigate a deep-learning framework with novel training schemes for classification of different thoracic pathology labels from chest x-rays. We use the currently largest publicly available annotated dataset ChestX-ray14 of 112,120 chest radiographs of 30,805 patients. Each image was annotated with either a 'NoFinding' class, or one or more of 14 thoracic pathology labels. Subjects can have multiple pathologies, resulting in a multi-class, multi-label problem. We encoded labels as binary vectors using k-hot encoding. We study the ResNet34 architecture, pre-trained on ImageNet, where two key modifications were incorporated into the training framework: (1) Stochastic gradient descent with momentum and with restarts using cosine annealing, (2) Variable image sizes for fine-tuning to prevent overfitting. Additionally, we use a heuristic algorithm to select a good learning rate. Learning with restarts was used to avoid local minima. Area Under receiver operating characteristics Curve (AUC) was used to quantitatively evaluate diagnostic quality. Our results are comparable to, or outperform the best results of current state-of-the-art methods with AUCs as follows: Atelectasis:0.81, Cardiomegaly:0.91, Consolidation:0.81, Edema:0.92, Effusion:0.89, Emphysema: 0.92, Fibrosis:0.81, Hernia:0.84, Infiltration:0.73, Mass:0.85, Nodule:0.76, Pleural Thickening:0.81, Pneumonia:0.77, Pneumothorax:0.89 and NoFinding:0.79. Our results suggest that, in addition to using sophisticated network architectures, a good learning rate, scheduler and a robust optimizer can boost performance.

Citation Download Citation

Adora M. DSouza, Anas Z. Abidin, and Axel Wismüller "Automated identification of thoracic pathology from chest radiographs with enhanced training pipeline", Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 109503F (13 March 2019); https://doi.org/10.1117/12.2512600

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available