MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915896936628224 |
|---|---|
| author | Park, Woohyeon Kim, Jaeik Cho, Sunghwan Steve Hong, Pa Jeong, Wookyoung Nam, Yoojin Kim, Namjoon Wong, Ginny Y. Cheung, Ka Chun Do, Jaeyoung |
| author_facet | Park, Woohyeon Kim, Jaeik Cho, Sunghwan Steve Hong, Pa Jeong, Wookyoung Nam, Yoojin Kim, Namjoon Wong, Ginny Y. Cheung, Ka Chun Do, Jaeyoung |
| contents | Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present MEDIC-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (<Ano>) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter image difference tokens (<Diff>) explicitly encode temporal changes between studies, allowing the model to distinguish worsening, improvement, and stability in disease burden. Finally, a dedicated explainability stage trains the model to generate heatmaps that highlight lesion-related regions, offering clear visual evidence that is consistent with the model's reasoning. Through our staged design, MEDIC-AD steadily boosts performance across anomaly detection, symptom tracking, and anomaly segmentation, achieving state-of-the-art results compared with both closed source and medical-specialized baselines. Evaluations on real longitudinal clinical data collected from real hospital workflows further show that MEDIC-AD delivers stable predictions and clinically faithful explanations in practical patient-monitoring and decision-support workflows |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27176 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence Park, Woohyeon Kim, Jaeik Cho, Sunghwan Steve Hong, Pa Jeong, Wookyoung Nam, Yoojin Kim, Namjoon Wong, Ginny Y. Cheung, Ka Chun Do, Jaeyoung Computer Vision and Pattern Recognition Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present MEDIC-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (<Ano>) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter image difference tokens (<Diff>) explicitly encode temporal changes between studies, allowing the model to distinguish worsening, improvement, and stability in disease burden. Finally, a dedicated explainability stage trains the model to generate heatmaps that highlight lesion-related regions, offering clear visual evidence that is consistent with the model's reasoning. Through our staged design, MEDIC-AD steadily boosts performance across anomaly detection, symptom tracking, and anomaly segmentation, achieving state-of-the-art results compared with both closed source and medical-specialized baselines. Evaluations on real longitudinal clinical data collected from real hospital workflows further show that MEDIC-AD delivers stable predictions and clinically faithful explanations in practical patient-monitoring and decision-support workflows |
| title | MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27176 |