COVID-19 detection using chest X-rays: is lung segmentation important for generalization?
arXiv:2104.06176 · doi:10.1007/s42600-022-00242-y
Abstract
Purpose: we evaluated the generalization capability of deep neural networks (DNNs), trained to classify chest X-rays as Covid-19, normal or pneumonia, using a relatively small and mixed dataset. Methods: we proposed a DNN to perform lung segmentation and classification, stacking a segmentation module (U-Net), an original intermediate module and a classification module (DenseNet201). To evaluate generalization, we tested the DNN with an external dataset (from distinct localities) and used Bayesian inference to estimate probability distributions of performance metrics. Results: our DNN achieved 0.917 AUC on the external test dataset, and a DenseNet without segmentation, 0.906. Bayesian inference indicated mean accuracy of 76.1% and [0.695, 0.826] 95% HDI (highest density interval, which concentrates 95% of the metric's probability mass) with segmentation and, without segmentation, 71.7% and [0.646, 0.786]. Conclusion: employing a novel DNN evaluation technique, which uses LRP and Brixia scores, we discovered that areas where radiologists found strong Covid-19 symptoms are the most important for the stacked DNN classification. External validation showed smaller accuracies than internal, indicating difficulty in generalization, which is positively affected by segmentation. Finally, the performance in the external dataset and the analysis with LRP suggest that DNNs can be trained in small and mixed datasets and still successfully detect Covid-19.
arXiv commentText and figure improvements. Results did not change. Included DOI and reference to the published article (Research on Biomedical Engineering, Springer). Link for the published paper: https://trebuchet.public.springernature.app/get_content/1ab346c8-06ea-49ed-92f3-deaec80f6988
References in corpus (5)
- ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
- The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
- CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
- COVID-19 Image Data Collection
- A Deep Convolutional Neural Network for COVID-19 Detection Using Chest X-Rays