Gradient Attention Map Based Verification of Deep Convolutional Neural Networks with Application to X-ray Image Datasets
This addresses the need for safer deployment of deep learning in medical imaging, such as orthodontics and skeletal maturity assessment, by providing a verification framework, though it is incremental as it builds on existing methods like Grad-CAM.
The paper tackled the problem of unreliable predictions when deep learning models are applied to data different from their training sets in medical imaging, proposing a verification framework that uses Gradient Attention Maps, feature map analysis, and a garbage class to identify unsuitable models and inputs, with experimental results showing effective identification.
Deep learning models have great potential in medical imaging, including orthodontics and skeletal maturity assessment. However, applying a model to data different from its training set can lead to unreliable predictions that may impact patient care. To address this, we propose a comprehensive verification framework that evaluates model suitability through multiple complementary strategies. First, we introduce a Gradient Attention Map (GAM)-based approach that analyzes attention patterns using Grad-CAM and compares them via similarity metrics such as IoU, Dice Similarity, SSIM, Cosine Similarity, Pearson Correlation, KL Divergence, and Wasserstein Distance. Second, we extend verification to early convolutional feature maps, capturing structural mis-alignments missed by attention alone. Finally, we incorporate an additional garbage class into the classification model to explicitly reject out-of-distribution inputs. Experimental results demonstrate that these combined methods effectively identify unsuitable models and inputs, promoting safer and more reliable deployment of deep learning in medical imaging.