Integrating Clinical Knowledge into Concept Bottleneck Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913422864547840 |
|---|---|
| author | Pang, Winnie Ke, Xueyi Tsutsui, Satoshi Wen, Bihan |
| author_facet | Pang, Winnie Ke, Xueyi Tsutsui, Satoshi Wen, Bihan |
| contents | Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model. However, training CBMs solely in a data-driven manner can introduce undesirable biases, which may compromise prediction performance, especially when the trained models are evaluated on out-of-domain images (e.g., those acquired using different devices). To mitigate this challenge, we propose integrating clinical knowledge to refine CBMs, better aligning them with clinicians' decision-making processes. Specifically, we guide the model to prioritize the concepts that clinicians also prioritize. We validate our approach on two datasets of medical images: white blood cell and skin images. Empirical validation demonstrates that incorporating medical guidance enhances the model's classification performance on unseen datasets with varying preparation methods, thereby increasing its real-world applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06600 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Integrating Clinical Knowledge into Concept Bottleneck Models Pang, Winnie Ke, Xueyi Tsutsui, Satoshi Wen, Bihan Computer Vision and Pattern Recognition Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model. However, training CBMs solely in a data-driven manner can introduce undesirable biases, which may compromise prediction performance, especially when the trained models are evaluated on out-of-domain images (e.g., those acquired using different devices). To mitigate this challenge, we propose integrating clinical knowledge to refine CBMs, better aligning them with clinicians' decision-making processes. Specifically, we guide the model to prioritize the concepts that clinicians also prioritize. We validate our approach on two datasets of medical images: white blood cell and skin images. Empirical validation demonstrates that incorporating medical guidance enhances the model's classification performance on unseen datasets with varying preparation methods, thereby increasing its real-world applicability. |
| title | Integrating Clinical Knowledge into Concept Bottleneck Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06600 |