ChexFract: From General to Specialized -- Enhancing Fracture Description Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912703690309632 |
|---|---|
| author | Nechaev, Nikolay Przhezdzetskaia, Evgeniia Umerenkov, Dmitry Dylov, Dmitry V. |
| author_facet | Nechaev, Nikolay Przhezdzetskaia, Evgeniia Umerenkov, Dmitry Dylov, Dmitry V. |
| contents | Generating accurate and clinically meaningful radiology reports from chest X-ray images remains a significant challenge in medical AI. While recent vision-language models achieve strong results in general radiology report generation, they often fail to adequately describe rare but clinically important pathologies like fractures. This work addresses this gap by developing specialized models for fracture pathology detection and description. We train fracture-specific vision-language models with encoders from MAIRA-2 and CheXagent, demonstrating significant improvements over general-purpose models in generating accurate fracture descriptions. Analysis of model outputs by fracture type, location, and age reveals distinct strengths and limitations of current vision-language model architectures. We publicly release our best-performing fracture-reporting model, facilitating future research in accurate reporting of rare pathologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07983 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChexFract: From General to Specialized -- Enhancing Fracture Description Generation Nechaev, Nikolay Przhezdzetskaia, Evgeniia Umerenkov, Dmitry Dylov, Dmitry V. Computer Vision and Pattern Recognition Generating accurate and clinically meaningful radiology reports from chest X-ray images remains a significant challenge in medical AI. While recent vision-language models achieve strong results in general radiology report generation, they often fail to adequately describe rare but clinically important pathologies like fractures. This work addresses this gap by developing specialized models for fracture pathology detection and description. We train fracture-specific vision-language models with encoders from MAIRA-2 and CheXagent, demonstrating significant improvements over general-purpose models in generating accurate fracture descriptions. Analysis of model outputs by fracture type, location, and age reveals distinct strengths and limitations of current vision-language model architectures. We publicly release our best-performing fracture-reporting model, facilitating future research in accurate reporting of rare pathologies. |
| title | ChexFract: From General to Specialized -- Enhancing Fracture Description Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.07983 |