Attention-based Saliency Maps Improve Interpretability of Pneumothorax Classification

Purpose: To investigate chest radiograph (CXR) classification performance of vision transformers (ViT) and interpretability of attention-based saliency using the example of pneumothorax classification. Materials and Methods: In this retrospective study, ViTs were fine-tuned for lung disease classification using four public data sets: CheXpert, Chest X-Ray 14, MIMIC CXR, and VinBigData. Saliency maps were generated using transformer multimodal explainability and gradient-weighted class activation mapping (GradCAM). Classification performance was evaluated on the Chest X-Ray 14, VinBigData, and SIIM-ACR data sets using the area under the receiver operating characteristic curve analysis (AUC) and compared with convolutional neural networks (CNNs). The explainability methods were evaluated with positive/negative perturbation, sensitivity-n, effective heat ratio, intra-architecture repeatability and interarchitecture reproducibility. In the user study, three radiologists classified 160 CXRs with/without saliency maps for pneumothorax and rated their usefulness. Results: ViTs had comparable CXR classification AUCs compared with state-of-the-art CNNs 0.95 (95% CI: 0.943, 0.950) versus 0.83 (95%, CI 0.826, 0.842) on Chest X-Ray 14, 0.84 (95% CI: 0.769, 0.912) versus 0.83 (95% CI: 0.760, 0.895) on VinBigData, and 0.85 (95% CI: 0.847, 0.861) versus 0.87 (95% CI: 0.868, 0.882) on SIIM ACR. Both saliency map methods unveiled a strong bias toward pneumothorax tubes in the models. Radiologists found 47% of the attention-based saliency maps useful and 39% of GradCAM. The attention-based methods outperformed GradCAM on all metrics. Conclusion: ViTs performed similarly to CNNs in CXR classification, and their attention-based saliency maps were more useful to radiologists and outperformed GradCAM.

A knee cannot have lung disease: out-of-distribution detection with in-distribution voting using the medical example of chest X-ray classification

Deep learning models are being applied to more and more use cases with astonishing success stories, but how do they perform in the real world? To test a model, a specific cleaned data set is assembled. However, when deployed in the real world, the model will face unexpected, out-of-distribution (OOD) data. In this work, we show that the so-called "radiologist-level" CheXnet model fails to recognize all OOD images and classifies them as having lung disease. To address this issue, we propose in-distribution voting, a novel method to classify out-of-distribution images for multi-label classification. Using independent class-wise in-distribution (ID) predictors trained on ID and OOD data we achieve, on average, 99 % ID classification specificity and 98 % sensitivity, improving the end-to-end performance significantly compared to previous works on the chest X-ray 14 data set. Our method surpasses other output-based OOD detectors even when trained solely with ImageNet as OOD data and tested with X-ray OOD images.