Automated abnormality classification of chest radiographs using deep convolutional neural networks

Abstract

As one of the most ubiquitous diagnostic imaging tests in medical practice, chest radiography requires timely reporting of potential findings and diagnosis of diseases in the images. Automated, fast, and reliable detection of diseases based on chest radiography is a critical step in radiology workflow. In this work, we developed and evaluated various deep convolutional neural networks (CNN) for differentiating between normal and abnormal frontal chest radiographs, in order to help alert radiologists and clinicians of potential abnormal findings as a means of work list triaging and reporting prioritization. A CNN-based model achieved an AUC of 0.9824 ± 0.0043 (with an accuracy of 94.64 ± 0.45%, a sensitivity of 96.50 ± 0.36% and a specificity of 92.86 ± 0.48%) for normal versus abnormal chest radiograph classification. The CNN model obtained an AUC of 0.9804 ± 0.0032 (with an accuracy of 94.71 ± 0.32%, a sensitivity of 92.20 ± 0.34% and a specificity of 96.34 ± 0.31%) for normal versus lung opacity classification. Classification performance on the external dataset showed that the CNN model is likely to be highly generalizable, with an AUC of 0.9444 ± 0.0029. The CNN model pre-trained on cohorts of adult patients and fine-tuned on pediatric patients achieved an AUC of 0.9851 ± 0.0046 for normal versus pneumonia classification. Pretraining with natural images demonstrates benefit for a moderate-sized training image set of about 8500 images. The remarkable performance in diagnostic accuracy observed in this study shows that deep CNNs can accurately and effectively differentiate normal and abnormal chest radiographs, thereby providing potential benefits to radiology workflow and patient care.

Efficient Pediatric Pneumonia Diagnosis Using Depthwise Separable Convolutions

“…Tang et al [41] exploited a unique technique to train and evaluate their pneumonia detection model. They first trained their GoogleNet based model on the large NIH dataset of [26].…”

“…All the past models [7,[20][21][22][23][24][38][39][40][41], except [43], have been evaluated in terms of only performance and not in terms of efficiency. Unlike other related work, Hu et al [43] have worked on model efficiency rather than just accuracy.…”

Recalibration of deep learning models for abnormality detection in smartphone-captured chest radiograph

“…Mostly built on convolutional neural networks (CNNs), the algorithms can detect certain pulmonary abnormalities in CXR images within a second. Numerous studies have shown the competency of CNNs achieving performance close to radiology experts 7,11,12,[15][16][17] .…”

Deep Convolutional Approaches for the Analysis of COVID-19 Using Chest X-Ray Images From Portable Devices

“…The advances in terms of computational capabilities as well as the availability of large labeled datasets have promoted the use of deep learning techniques in the field of medical imaging [15]. In particular, the potential of these techniques has been exploited for the detection and assessment of cardiothoracic and pulmonary abnormalities in chest X-ray imaging, one of the most widely used imaging tests in medical practice [16] [17]. Therefore, Anthimopoulos et al [18] present a deep CNN (Convolutional Neural Network) to classify lung image patches into 7 categories considering 6 different patterns of interstitial lung diseases as well as healthy tissue.…”