Unleashing Video Language Models for Fine-grained HRCT Report Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918403020685312 |
|---|---|
| author | Fang, Yingying Zhou, Huichi Lee, KinHei Wang, Yijia Zhang, Zhenxuan Huang, Jiahao Yang, Guang |
| author_facet | Fang, Yingying Zhou, Huichi Lee, KinHei Wang, Yijia Zhang, Zhenxuan Huang, Jiahao Yang, Guang |
| contents | Generating precise diagnostic reports from High-Resolution Computed Tomography (HRCT) is critical for clinical workflow, yet it remains a formidable challenge due to the high pathological diversity and spatial sparsity within 3D volumes. While Video Language Models (VideoLMs) have demonstrated remarkable spatio-temporal reasoning in general domains, their adaptability to domain-specific, high-volume medical interpretation remains underexplored. In this work, we present AbSteering, an abnormality-centric framework that steers VideoLMs toward precise HRCT report generation. Specifically, AbSteering introduces: (i) an abnormality-centric Chain-of-Thought scheme that enforces abnormality reasoning, and (ii) a Direct Preference Optimization objective that utilizes clinically confusable abnormalities as hard negatives to enhance fine-grained discrimination. Our results demonstrate that general-purpose VideoLMs possess strong transferability to high-volume medical imaging when guided by this paradigm. Notably, AbSteering outperforms state-of-the-art domain-specific CT foundation models, which are pretrained with large-scale CTs, achieving superior detection sensitivity while simultaneously mitigating hallucinations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12469 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unleashing Video Language Models for Fine-grained HRCT Report Generation Fang, Yingying Zhou, Huichi Lee, KinHei Wang, Yijia Zhang, Zhenxuan Huang, Jiahao Yang, Guang Computer Vision and Pattern Recognition Generating precise diagnostic reports from High-Resolution Computed Tomography (HRCT) is critical for clinical workflow, yet it remains a formidable challenge due to the high pathological diversity and spatial sparsity within 3D volumes. While Video Language Models (VideoLMs) have demonstrated remarkable spatio-temporal reasoning in general domains, their adaptability to domain-specific, high-volume medical interpretation remains underexplored. In this work, we present AbSteering, an abnormality-centric framework that steers VideoLMs toward precise HRCT report generation. Specifically, AbSteering introduces: (i) an abnormality-centric Chain-of-Thought scheme that enforces abnormality reasoning, and (ii) a Direct Preference Optimization objective that utilizes clinically confusable abnormalities as hard negatives to enhance fine-grained discrimination. Our results demonstrate that general-purpose VideoLMs possess strong transferability to high-volume medical imaging when guided by this paradigm. Notably, AbSteering outperforms state-of-the-art domain-specific CT foundation models, which are pretrained with large-scale CTs, achieving superior detection sensitivity while simultaneously mitigating hallucinations. |
| title | Unleashing Video Language Models for Fine-grained HRCT Report Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.12469 |