Explainable emphysema detection on chest radiographs with deep learning

Abstract

We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong’s test is used to compare with the black-box model ROC and McNemar’s test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392.

Explainability of three-dimensional convolutional neural networks for functional magnetic resonance imaging of Alzheimer’s disease classification based on gradient-weighted class activation mapping

“…The performance is comparable to state-of-art methods, showcasing the potential of patch-based region of interest (ROI) ensembles in providing informative landmarks for MRI analysis. In addition to MRI images, [ 36 ] presented a deep learning system designed to automatically identify four visually explainable signs of emphysema in frontal and lateral chest radiographs, providing explainable labels for the detected signs. [ 37 ] leverages a neural network model trained on synthetic NaI(Tl) urban search data to assess and adapt explanation methods for gamma-ray spectral data.…”

Implementation of Artificial Intelligence–Assisted Chest X-ray Interpretation: It Is About Time

“…There is an augmented curiosity but a cautious adoption of AI-based diagnostics by radiologists ( 8 ). AI algorithms have been developed and deployed for specific CXR diagnostic tasks, such as detection of lung nodules ( 7 ), emphysema ( 9 ), pneumonia ( 10 ), and pneumothorax ( 11 ), which have exhibited radiologist-level performance and accuracy. Even though AI applications in CXR diagnosis have been shown to aid radiologists in detection of key radiographic findings, the benefit of AI-assisted CXR diagnosis and interpretation by nonradiologist physicians has not been well examined.…”