Abnormality Detection and Localization in Chest X-Rays using Deep Convolutional Neural Networks

Abstract

Chest X-Rays (CXRs) are widely used for diagnosing abnormalities in the heart and lung area. Automatically detecting these abnormalities with high accuracy could greatly enhance real world diagnosis processes. Lack of standard publicly available dataset and benchmark studies, however, makes it difficult to compare various detection methods. In order to overcome these difficulties, we have used a publicly available Indiana CXR, JSRT and Shenzhen dataset and studied the performance of known deep convolutional network (DCN) architectures on different abnormalities. We find that the same DCN architecture doesn't perform well across all abnormalities. Shallow features or earlier layers consistently provide higher detection accuracy compared to deep features. We have also found ensemble models to improve classification significantly compared to single model. Combining these insight, we report the highest accuracy on chest X-Ray abnormality detection on these datasets. We find that for cardiomegaly detection, the deep learning method improves the accuracy by a staggering 17 percentage point compared to rule based methods. We applied the techniques to the problem of tuberculosis detection on a different dataset and achieved the highest accuracy. Our localization experiments using these trained classifiers show that for spatially spread out abnormalities like cardiomegaly and pulmonary edema, the network can localize the abnormalities successfully most of the time. One remarkable result of the cardiomegaly localization is that the heart and its surrounding region is most responsible for cardiomegaly detection, in contrast to the rule based models where the ratio of heart and lung area is used as the measure. We believe that through deep learning based classification and localization, we will discover many more interesting features in medical image diagnosis that are not considered traditionally.

arXiv comment14 figures, 16 pages, 8 tables

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Survey on Deep Learning in Medical Image Analysis
• Deep Learning for Identifying Metastatic Breast Cancer

Cited by in corpus (23)

• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• COVID-19 Image Data Collection: Prospective Predictions Are the Future
• Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
• Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
• Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
• Large Scale Automated Reading of Frontal and Lateral Chest X-Rays using Dual Convolutional Neural Networks
• New Bag of Deep Visual Words based features to classify chest x-ray images for COVID-19 diagnosis
• Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation
• A bone suppression model ensemble to improve COVID-19 detection in chest X-rays
• Multi-task Learning for Chest X-ray Abnormality Classification on Noisy Labels
• Justifying Diagnosis Decisions by Deep Neural Networks
• DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images
• Sepsis Prediction and Vital Signs Ranking in Intensive Care Unit Patients
• Towards Radiologist-Level Accurate Deep Learning System for Pulmonary Screening
• Artificial intelligence based prediction on lung cancer risk factors using deep learning
• Pathology Extraction from Chest X-Ray Radiology Reports: A Performance Study
• Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
• Deep Learning for Automated Screening of Tuberculosis from Indian Chest X-rays: Analysis and Update
• Deep Mask For X-ray Based Heart Disease Classification
• Multi-loss ensemble deep learning for chest X-ray classification
• Top-K Deep Video Analytics: A Probabilistic Approach
• Deep Hiearchical Multi-Label Classification Applied to Chest X-Ray Abnormality Taxonomies
• Noise Sensitivity of Local Descriptors vs ConvNets: An application to Facial Recognition