Interpretability-Aware Pruning for Efficient Medical Image Analysis
This work addresses the need for lightweight and interpretable models in healthcare settings, though it is incremental as it builds on existing interpretability techniques for targeted compression.
The paper tackles the problem of deploying deep learning models in clinical practice by introducing an interpretability-guided pruning framework that reduces model complexity while preserving predictive performance and transparency, achieving high compression rates with minimal accuracy loss across medical image classification benchmarks.
Deep learning has driven significant advances in medical image analysis, yet its adoption in clinical practice remains constrained by the large size and lack of transparency in modern models. Advances in interpretability techniques such as DL-Backtrace, Layer-wise Relevance Propagation, and Integrated Gradients make it possible to assess the contribution of individual components within neural networks trained on medical imaging tasks. In this work, we introduce an interpretability-guided pruning framework that reduces model complexity while preserving both predictive performance and transparency. By selectively retaining only the most relevant parts of each layer, our method enables targeted compression that maintains clinically meaningful representations. Experiments across multiple medical image classification benchmarks demonstrate that this approach achieves high compression rates with minimal loss in accuracy, paving the way for lightweight, interpretable models suited for real-world deployment in healthcare settings.