Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.01131 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910039838556160 |
|---|---|
| author | Nahiduzzaman, Md Korevaar, Steven Bab-Hadiashar, Alireza Tennakoon, Ruwan |
| author_facet | Nahiduzzaman, Md Korevaar, Steven Bab-Hadiashar, Alireza Tennakoon, Ruwan |
| contents | Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data, which are costly and impractical to obtain in clinical contexts. Recent attempts to bypass annotation, such as zero-shot vision-language models or concept-generation frameworks, struggle to capture domain-specific medical features, leading to poor reliability. In this paper, we propose a novel Prior-guided Concept Predictor (PCP), a weakly supervised framework that enables concept answer prediction without explicit supervision or reliance on language models. PCP leverages class-level concept priors as weak supervision and incorporates a refinement mechanism with KL divergence and entropy regularization to align predictions with clinical reasoning. Experiments on PH2 (dermoscopy) and WBCatt (hematology) show that PCP improves concept-level F1-score by over 33% compared to zero-shot baselines, while delivering competitive classification performance on four medical datasets (PH2, WBCatt, HAM10000, and CXR4) relative to fully supervised concept bottleneck models (CBMs) and V-IP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01131 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis Nahiduzzaman, Md Korevaar, Steven Bab-Hadiashar, Alireza Tennakoon, Ruwan Computer Vision and Pattern Recognition Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data, which are costly and impractical to obtain in clinical contexts. Recent attempts to bypass annotation, such as zero-shot vision-language models or concept-generation frameworks, struggle to capture domain-specific medical features, leading to poor reliability. In this paper, we propose a novel Prior-guided Concept Predictor (PCP), a weakly supervised framework that enables concept answer prediction without explicit supervision or reliance on language models. PCP leverages class-level concept priors as weak supervision and incorporates a refinement mechanism with KL divergence and entropy regularization to align predictions with clinical reasoning. Experiments on PH2 (dermoscopy) and WBCatt (hematology) show that PCP improves concept-level F1-score by over 33% compared to zero-shot baselines, while delivering competitive classification performance on four medical datasets (PH2, WBCatt, HAM10000, and CXR4) relative to fully supervised concept bottleneck models (CBMs) and V-IP. |
| title | Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.01131 |