Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.26483 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918523480047616 |
|---|---|
| author | Gao, Jianzhe Wang, Churan Zhang, Weiyi Li, Jianghua Li, Li-An Wang, Wenguan Zhu, Yixin Wang, Yizhou |
| author_facet | Gao, Jianzhe Wang, Churan Zhang, Weiyi Li, Jianghua Li, Li-An Wang, Wenguan Zhu, Yixin Wang, Yizhou |
| contents | Medical video diagnosis involves inferring clinical decisions from dynamic tissue responses throughout examination processes. Existing methods rely on an end-to-end learning paradigm that i) focuses on appearance rather than pathology, ii) lacks clinical priors, and iii) reasons solely from observations without counterfactual comparison. This work introduces MedVCR, a counterfactual reasoning framework that mimics clinical diagnostic thinking. MedVCR comprises three components: a Counterfactual Generator that synthesizes tissue evolution under specified pathological states via a diffusion-based manner; a Counterfactual Representation Learning module that encodes diagnostic knowledge through clinical rules (i.e., temporal consistency, pathological separability, and counterfactual alignment); and a Dual Diagnostic Prediction strategy that integrates video-level assessment with frame-level counterfactual analysis. MedVCR is evaluated under both fully supervised (e.g., colposcopy) and weakly supervised (e.g., colonoscopy) video diagnosis settings, yielding 2.6%-10.2% performance gains compared with leading baselines. Comprehensive ablation studies further validate the effectiveness of each component. The code will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26483 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis Gao, Jianzhe Wang, Churan Zhang, Weiyi Li, Jianghua Li, Li-An Wang, Wenguan Zhu, Yixin Wang, Yizhou Computer Vision and Pattern Recognition Medical video diagnosis involves inferring clinical decisions from dynamic tissue responses throughout examination processes. Existing methods rely on an end-to-end learning paradigm that i) focuses on appearance rather than pathology, ii) lacks clinical priors, and iii) reasons solely from observations without counterfactual comparison. This work introduces MedVCR, a counterfactual reasoning framework that mimics clinical diagnostic thinking. MedVCR comprises three components: a Counterfactual Generator that synthesizes tissue evolution under specified pathological states via a diffusion-based manner; a Counterfactual Representation Learning module that encodes diagnostic knowledge through clinical rules (i.e., temporal consistency, pathological separability, and counterfactual alignment); and a Dual Diagnostic Prediction strategy that integrates video-level assessment with frame-level counterfactual analysis. MedVCR is evaluated under both fully supervised (e.g., colposcopy) and weakly supervised (e.g., colonoscopy) video diagnosis settings, yielding 2.6%-10.2% performance gains compared with leading baselines. Comprehensive ablation studies further validate the effectiveness of each component. The code will be released. |
| title | Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.26483 |