Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

• Main Authors: Phan, Vu Minh Hieu, Xie, Yutong, Qi, Yuankai, Liu, Lingqiao, Liu, Liyang, Zhang, Bowen, Liao, Zhibin, Wu, Qi, To, Minh-Son, Verjans, Johan W
• Format: Journal Article
• Language: English
• Published: 12.03.2024
• Subjects: Computer Science - Computer Vision and Pattern Recognition

CVPR2024 Medical vision language pre-training (VLP) has emerged as a frontier of research, enabling zero-shot pathological recognition by comparing the query image with the textual descriptions for each disease. Due to the complex semantics of biomedical texts, current methods struggle to align medi...