Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914157665714176 |
|---|---|
| author | Vu, Anh Mai Vo, Tuan L. Bui, Ngoc Lam Quang Binh, Nam Nguyen Le Awasthi, Akash Vo, Huy Quoc Nguyen, Thanh-Huy Han, Zhu Mohan, Chandra Van Nguyen, Hien |
| author_facet | Vu, Anh Mai Vo, Tuan L. Bui, Ngoc Lam Quang Binh, Nam Nguyen Le Awasthi, Akash Vo, Huy Quoc Nguyen, Thanh-Huy Han, Zhu Mohan, Chandra Van Nguyen, Hien |
| contents | Interpretability is essential in Whole Slide Image (WSI) analysis for computational pathology, where understanding model predictions helps build trust in AI-assisted diagnostics. While Integrated Gradients (IG) and related attribution methods have shown promise, applying them directly to WSIs introduces challenges due to their high-resolution nature. These methods capture model decision patterns but may overlook class-discriminative signals that are crucial for distinguishing between tumor subtypes. In this work, we introduce Contrastive Integrated Gradients (CIG), a novel attribution method that enhances interpretability by computing contrastive gradients in logit space. First, CIG highlights class-discriminative regions by comparing feature importance relative to a reference class, offering sharper differentiation between tumor and non-tumor areas. Second, CIG satisfies the axioms of integrated attribution, ensuring consistency and theoretical soundness. Third, we propose two attribution quality metrics, MIL-AIC and MIL-SIC, which measure how predictive information and model confidence evolve with access to salient regions, particularly under weak supervision. We validate CIG across three datasets spanning distinct cancer types: CAMELYON16 (breast cancer metastasis in lymph nodes), TCGA-RCC (renal cell carcinoma), and TCGA-Lung (lung cancer). Experimental results demonstrate that CIG yields more informative attributions both quantitatively, using MIL-AIC and MIL-SIC, and qualitatively, through visualizations that align closely with ground truth tumor regions, underscoring its potential for interpretable and trustworthy WSI-based diagnostics |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08464 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification Vu, Anh Mai Vo, Tuan L. Bui, Ngoc Lam Quang Binh, Nam Nguyen Le Awasthi, Akash Vo, Huy Quoc Nguyen, Thanh-Huy Han, Zhu Mohan, Chandra Van Nguyen, Hien Computer Vision and Pattern Recognition Artificial Intelligence Interpretability is essential in Whole Slide Image (WSI) analysis for computational pathology, where understanding model predictions helps build trust in AI-assisted diagnostics. While Integrated Gradients (IG) and related attribution methods have shown promise, applying them directly to WSIs introduces challenges due to their high-resolution nature. These methods capture model decision patterns but may overlook class-discriminative signals that are crucial for distinguishing between tumor subtypes. In this work, we introduce Contrastive Integrated Gradients (CIG), a novel attribution method that enhances interpretability by computing contrastive gradients in logit space. First, CIG highlights class-discriminative regions by comparing feature importance relative to a reference class, offering sharper differentiation between tumor and non-tumor areas. Second, CIG satisfies the axioms of integrated attribution, ensuring consistency and theoretical soundness. Third, we propose two attribution quality metrics, MIL-AIC and MIL-SIC, which measure how predictive information and model confidence evolve with access to salient regions, particularly under weak supervision. We validate CIG across three datasets spanning distinct cancer types: CAMELYON16 (breast cancer metastasis in lymph nodes), TCGA-RCC (renal cell carcinoma), and TCGA-Lung (lung cancer). Experimental results demonstrate that CIG yields more informative attributions both quantitatively, using MIL-AIC and MIL-SIC, and qualitatively, through visualizations that align closely with ground truth tumor regions, underscoring its potential for interpretable and trustworthy WSI-based diagnostics |
| title | Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.08464 |