Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jin, Jiayun, Chai, Haolong, Huang, Xueying, Guo, Xiaoqing, Zheng, Zengwei, Zhou, Zhan, Wang, Junmei, Wang, Xinyu, Liu, Jie, Zhou, Binbin
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.01749
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910097086611456
author Jin, Jiayun
Chai, Haolong
Huang, Xueying
Guo, Xiaoqing
Zheng, Zengwei
Zhou, Zhan
Wang, Junmei
Wang, Xinyu
Liu, Jie
Zhou, Binbin
author_facet Jin, Jiayun
Chai, Haolong
Huang, Xueying
Guo, Xiaoqing
Zheng, Zengwei
Zhou, Zhan
Wang, Junmei
Wang, Xinyu
Liu, Jie
Zhou, Binbin
contents Ultrasound imaging is widely used in clinical diagnostics due to its real-time capability and radiation-free nature. However, existing vision-language pre-training models, such as CLIP, are primarily designed for other modalities, and are difficult to directly apply to ultrasound data, which exhibit heterogeneous anatomical structures and diverse diagnostic attributes. To bridge this gap, we construct US-365K, a large-scale ultrasound image-text dataset containing 365k paired samples across 52 anatomical categories. We establish Ultrasonographic Diagnostic Taxonomy (UDT) containing two hierarchical knowledge frameworks. Ultrasonographic Hierarchical Anatomical Taxonomy standardizes anatomical organization, and Ultrasonographic Diagnostic Attribute Framework formalizes nine diagnostic dimensions, including body system, organ, diagnosis, shape, margins, echogenicity, internal characteristics, posterior acoustic phenomena, and vascularity. Building upon these foundations, we propose Ultrasound-CLIP, a semantic-aware contrastive learning framework that introduces semantic soft labels and semantic loss to refine sample discrimination. Moreover, we construct a heterogeneous graph modality derived from UDAF's textual representations, enabling structured reasoning over lesion-attribute relations. Extensive experiments with patient-level data splitting demonstrate that our approach achieves state-of-the-art performance on classification and retrieval benchmarks, while also delivering strong generalization to zero-shot, linear probing, and fine-tuning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_01749
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Ultrasound-CLIP: Semantic-Aware Contrastive Pre-training for Ultrasound Image-Text Understanding
Jin, Jiayun
Chai, Haolong
Huang, Xueying
Guo, Xiaoqing
Zheng, Zengwei
Zhou, Zhan
Wang, Junmei
Wang, Xinyu
Liu, Jie
Zhou, Binbin
Computer Vision and Pattern Recognition
Ultrasound imaging is widely used in clinical diagnostics due to its real-time capability and radiation-free nature. However, existing vision-language pre-training models, such as CLIP, are primarily designed for other modalities, and are difficult to directly apply to ultrasound data, which exhibit heterogeneous anatomical structures and diverse diagnostic attributes. To bridge this gap, we construct US-365K, a large-scale ultrasound image-text dataset containing 365k paired samples across 52 anatomical categories. We establish Ultrasonographic Diagnostic Taxonomy (UDT) containing two hierarchical knowledge frameworks. Ultrasonographic Hierarchical Anatomical Taxonomy standardizes anatomical organization, and Ultrasonographic Diagnostic Attribute Framework formalizes nine diagnostic dimensions, including body system, organ, diagnosis, shape, margins, echogenicity, internal characteristics, posterior acoustic phenomena, and vascularity. Building upon these foundations, we propose Ultrasound-CLIP, a semantic-aware contrastive learning framework that introduces semantic soft labels and semantic loss to refine sample discrimination. Moreover, we construct a heterogeneous graph modality derived from UDAF's textual representations, enabling structured reasoning over lesion-attribute relations. Extensive experiments with patient-level data splitting demonstrate that our approach achieves state-of-the-art performance on classification and retrieval benchmarks, while also delivering strong generalization to zero-shot, linear probing, and fine-tuning tasks.
title Ultrasound-CLIP: Semantic-Aware Contrastive Pre-training for Ultrasound Image-Text Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.01749