Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.02034 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915613177282560 |
|---|---|
| author | Zhong, Zhusi Wang, Yuli Bi, Lulu Ma, Zhuoqi Ahn, Sun Ho Mullin, Christopher J. Greineder, Colin F. Atalay, Michael K. Collins, Scott Baird, Grayson L. Lin, Cheng Ting Stayman, Webster Kolb, Todd M. Kamel, Ihab Bai, Harrison X. Jiao, Zhicheng |
| author_facet | Zhong, Zhusi Wang, Yuli Bi, Lulu Ma, Zhuoqi Ahn, Sun Ho Mullin, Christopher J. Greineder, Colin F. Atalay, Michael K. Collins, Scott Baird, Grayson L. Lin, Cheng Ting Stayman, Webster Kolb, Todd M. Kamel, Ihab Bai, Harrison X. Jiao, Zhicheng |
| contents | Medical imaging plays a pivotal role in modern healthcare, with computed tomography pulmonary angiography (CTPA) being a critical tool for diagnosing pulmonary embolism and other thoracic conditions. However, the complexity of interpreting CTPA scans and generating accurate radiology reports remains a significant challenge. This paper introduces Abn-BLIP (Abnormality-aligned Bootstrapping Language-Image Pretraining), an advanced diagnosis model designed to align abnormal findings to generate the accuracy and comprehensiveness of radiology reports. By leveraging learnable queries and cross-modal attention mechanisms, our model demonstrates superior performance in detecting abnormalities, reducing missed findings, and generating structured reports compared to existing methods. Our experiments show that Abn-BLIP outperforms state-of-the-art medical vision-language models and 3D report generation methods in both accuracy and clinical relevance. These results highlight the potential of integrating multimodal learning strategies for improving radiology reporting. The source code is available at https://github.com/zzs95/abn-blip. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02034 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA Zhong, Zhusi Wang, Yuli Bi, Lulu Ma, Zhuoqi Ahn, Sun Ho Mullin, Christopher J. Greineder, Colin F. Atalay, Michael K. Collins, Scott Baird, Grayson L. Lin, Cheng Ting Stayman, Webster Kolb, Todd M. Kamel, Ihab Bai, Harrison X. Jiao, Zhicheng Computer Vision and Pattern Recognition Artificial Intelligence Medical imaging plays a pivotal role in modern healthcare, with computed tomography pulmonary angiography (CTPA) being a critical tool for diagnosing pulmonary embolism and other thoracic conditions. However, the complexity of interpreting CTPA scans and generating accurate radiology reports remains a significant challenge. This paper introduces Abn-BLIP (Abnormality-aligned Bootstrapping Language-Image Pretraining), an advanced diagnosis model designed to align abnormal findings to generate the accuracy and comprehensiveness of radiology reports. By leveraging learnable queries and cross-modal attention mechanisms, our model demonstrates superior performance in detecting abnormalities, reducing missed findings, and generating structured reports compared to existing methods. Our experiments show that Abn-BLIP outperforms state-of-the-art medical vision-language models and 3D report generation methods in both accuracy and clinical relevance. These results highlight the potential of integrating multimodal learning strategies for improving radiology reporting. The source code is available at https://github.com/zzs95/abn-blip. |
| title | Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.02034 |