CONRep: Uncertainty-Aware Vision-Language Report Drafting Using Conformal Prediction
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_ | 1866911420650618880 |
|---|---|
| author | Elyassirad, Danial Gheiji, Benyamin Vatanparast, Mahsa Ahmadzadeh, Amir Mahmoud Agah, Seyed Amir Asef Moassefi, Mana Tavakoli, Meysam Faghani, Shahriar |
| author_facet | Elyassirad, Danial Gheiji, Benyamin Vatanparast, Mahsa Ahmadzadeh, Amir Mahmoud Agah, Seyed Amir Asef Moassefi, Mana Tavakoli, Meysam Faghani, Shahriar |
| contents | Automated radiology report drafting (ARRD) using vision-language models (VLMs) has advanced rapidly, yet most systems lack explicit uncertainty estimates, limiting trust and safe clinical deployment. We propose CONRep, a model-agnostic framework that integrates conformal prediction (CP) to provide statistically grounded uncertainty quantification for VLM-generated radiology reports. CONRep operates at both the label level, by calibrating binary predictions for predefined findings, and the sentence level, by assessing uncertainty in free-text impressions via image-text semantic alignment. We evaluate CONRep using both generative and contrastive VLMs on public chest X-ray datasets. Across both settings, outputs classified as high confidence consistently show significantly higher agreement with radiologist annotations and ground-truth impressions than low-confidence outputs. By enabling calibrated confidence stratification without modifying underlying models, CONRep improves the transparency, reliability, and clinical usability of automated radiology reporting systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03910 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CONRep: Uncertainty-Aware Vision-Language Report Drafting Using Conformal Prediction Elyassirad, Danial Gheiji, Benyamin Vatanparast, Mahsa Ahmadzadeh, Amir Mahmoud Agah, Seyed Amir Asef Moassefi, Mana Tavakoli, Meysam Faghani, Shahriar Image and Video Processing Automated radiology report drafting (ARRD) using vision-language models (VLMs) has advanced rapidly, yet most systems lack explicit uncertainty estimates, limiting trust and safe clinical deployment. We propose CONRep, a model-agnostic framework that integrates conformal prediction (CP) to provide statistically grounded uncertainty quantification for VLM-generated radiology reports. CONRep operates at both the label level, by calibrating binary predictions for predefined findings, and the sentence level, by assessing uncertainty in free-text impressions via image-text semantic alignment. We evaluate CONRep using both generative and contrastive VLMs on public chest X-ray datasets. Across both settings, outputs classified as high confidence consistently show significantly higher agreement with radiologist annotations and ground-truth impressions than low-confidence outputs. By enabling calibrated confidence stratification without modifying underlying models, CONRep improves the transparency, reliability, and clinical usability of automated radiology reporting systems. |
| title | CONRep: Uncertainty-Aware Vision-Language Report Drafting Using Conformal Prediction |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2602.03910 |