Guardado en:
Detalles Bibliográficos
Autores principales: Park, Sang-Jun, Heo, Keun-Soo, Shin, Dong-Hee, Son, Young-Han, Oh, Ji-Hye, Kam, Tae-Eui
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.11786
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915245667123200
author Park, Sang-Jun
Heo, Keun-Soo
Shin, Dong-Hee
Son, Young-Han
Oh, Ji-Hye
Kam, Tae-Eui
author_facet Park, Sang-Jun
Heo, Keun-Soo
Shin, Dong-Hee
Son, Young-Han
Oh, Ji-Hye
Kam, Tae-Eui
contents The automatic generation of radiology reports has emerged as a promising solution to reduce a time-consuming task and accurately capture critical disease-relevant findings in X-ray images. Previous approaches for radiology report generation have shown impressive performance. However, there remains significant potential to improve accuracy by ensuring that retrieved reports contain disease-relevant findings similar to those in the X-ray images and by refining generated reports. In this study, we propose a Disease-aware image-text Alignment and self-correcting Re-alignment for Trustworthy radiology report generation (DART) framework. In the first stage, we generate initial reports based on image-to-text retrieval with disease-matching, embedding both images and texts in a shared embedding space through contrastive learning. This approach ensures the retrieval of reports with similar disease-relevant findings that closely align with the input X-ray images. In the second stage, we further enhance the initial reports by introducing a self-correction module that re-aligns them with the X-ray images. Our proposed framework achieves state-of-the-art results on two widely used benchmarks, surpassing previous approaches in both report generation and clinical efficacy metrics, thereby enhancing the trustworthiness of radiology reports.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11786
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation
Park, Sang-Jun
Heo, Keun-Soo
Shin, Dong-Hee
Son, Young-Han
Oh, Ji-Hye
Kam, Tae-Eui
Computer Vision and Pattern Recognition
The automatic generation of radiology reports has emerged as a promising solution to reduce a time-consuming task and accurately capture critical disease-relevant findings in X-ray images. Previous approaches for radiology report generation have shown impressive performance. However, there remains significant potential to improve accuracy by ensuring that retrieved reports contain disease-relevant findings similar to those in the X-ray images and by refining generated reports. In this study, we propose a Disease-aware image-text Alignment and self-correcting Re-alignment for Trustworthy radiology report generation (DART) framework. In the first stage, we generate initial reports based on image-to-text retrieval with disease-matching, embedding both images and texts in a shared embedding space through contrastive learning. This approach ensures the retrieval of reports with similar disease-relevant findings that closely align with the input X-ray images. In the second stage, we further enhance the initial reports by introducing a self-correction module that re-aligns them with the X-ray images. Our proposed framework achieves state-of-the-art results on two widely used benchmarks, surpassing previous approaches in both report generation and clinical efficacy metrics, thereby enhancing the trustworthiness of radiology reports.
title DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.11786