SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914801330946048 |
|---|---|
| author | Kapse, Saarthak Pati, Pushpak Das, Srijan Zhang, Jingwei Chen, Chao Vakalopoulou, Maria Saltz, Joel Samaras, Dimitris Gupta, Rajarsi R. Prasanna, Prateek |
| author_facet | Kapse, Saarthak Pati, Pushpak Das, Srijan Zhang, Jingwei Chen, Chao Vakalopoulou, Maria Saltz, Joel Samaras, Dimitris Gupta, Rajarsi R. Prasanna, Prateek |
| contents | Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging, given the complexity of gigapixel slides. Traditionally, MIL interpretability is limited to identifying salient regions deemed pertinent for downstream tasks, offering little insight to the end-user (pathologist) regarding the rationale behind these selections. To address this, we propose Self-Interpretable MIL (SI-MIL), a method intrinsically designed for interpretability from the very outset. SI-MIL employs a deep MIL framework to guide an interpretable branch grounded on handcrafted pathological features, facilitating linear predictions. Beyond identifying salient regions, SI-MIL uniquely provides feature-level interpretations rooted in pathological insights for WSIs. Notably, SI-MIL, with its linear prediction constraints, challenges the prevalent myth of an inevitable trade-off between model interpretability and performance, demonstrating competitive results compared to state-of-the-art methods on WSI-level prediction tasks across three cancer types. In addition, we thoroughly benchmark the local and global-interpretability of SI-MIL in terms of statistical analysis, a domain expert study, and desiderata of interpretability, namely, user-friendliness and faithfulness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15010 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology Kapse, Saarthak Pati, Pushpak Das, Srijan Zhang, Jingwei Chen, Chao Vakalopoulou, Maria Saltz, Joel Samaras, Dimitris Gupta, Rajarsi R. Prasanna, Prateek Computer Vision and Pattern Recognition Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging, given the complexity of gigapixel slides. Traditionally, MIL interpretability is limited to identifying salient regions deemed pertinent for downstream tasks, offering little insight to the end-user (pathologist) regarding the rationale behind these selections. To address this, we propose Self-Interpretable MIL (SI-MIL), a method intrinsically designed for interpretability from the very outset. SI-MIL employs a deep MIL framework to guide an interpretable branch grounded on handcrafted pathological features, facilitating linear predictions. Beyond identifying salient regions, SI-MIL uniquely provides feature-level interpretations rooted in pathological insights for WSIs. Notably, SI-MIL, with its linear prediction constraints, challenges the prevalent myth of an inevitable trade-off between model interpretability and performance, demonstrating competitive results compared to state-of-the-art methods on WSI-level prediction tasks across three cancer types. In addition, we thoroughly benchmark the local and global-interpretability of SI-MIL in terms of statistical analysis, a domain expert study, and desiderata of interpretability, namely, user-friendliness and faithfulness. |
| title | SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.15010 |