paper-with-me

홈 › Papers

Attention-based Saliency Maps Improve Interpretability of Pneumothorax Classification

2023-03-03 · Alessandro Wollek, Robert Graf, Saša Čečatka, Nicola Fink, Theresa Willem, Bastian O. Sabel, Tobias Lasser

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.

📄 PDF Abstract BibTeX arXiv:2303.01871

Code (1)

https://gitlab.lrz.de/IP/publishing/attention-based-saliency-map 공식 구현

Tasks

ClassificationLung Disease Classification

Similar Papers 제목 키워드 기반

Comparing radiologists' gaze and saliency maps generated by interpretability methods for chest x-rays

2021-12-22 · Ricardo Bigolin Lanfredi, Ambuj Arora, Trafton Drew, Joyce D. Schroeder 외

The interpretability of medical image analysis models is considered a key research field. We use a dataset of eye-tracking data from five radiologists to compare the outputs of interpretability methods and the heatmaps r…

Medical Image Analysis

SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training

2023-11-09 · Rui Xu, Wenkang Qin, Peixiang Huang, Hao Wang 외

Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions. Saliency map is a common form of explanation illustrating the heatmap of feature attributions, but it s…

Policy Distillation with Selective Input Gradient Regularization for Efficient Interpretability

2022-05-18 · Jinwei Xing, Takashi Nagata, Xinyun Zou, Emre Neftci 외

Although deep Reinforcement Learning (RL) has proven successful in a wide range of tasks, one challenge it faces is interpretability when applied to real-world problems. Saliency maps are frequently used to provide inter…

Autonomous DrivingDeep Reinforcement LearningReinforcement Learning (RL)

Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence

2025-09-23 · Sanish Suwal, Dipkamal Bhusal, Michael Clifford, Nidhi Rastogi arxiv

Prior works have shown that neural networks can be heavily pruned while preserving performance, but the impact of pruning on model interpretability remains unclear. In this work, we investigate how magnitude-based prunin…

Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models

2026-02-13 · Mónika Farsang, Radu Grosu arxiv

In this paper, we present a unified framework for various bio-inspired models to better understand their structural and functional differences. We show that liquid-capacitance-extended models lead to interpretable behavi…