In this section
@article{Liu:2024:10.1109/TMI.2024.3449690,
author = {Liu, C and Cheng, S and Shi, M and Shah, A and Bai, W and Arcucci, R},
doi = {10.1109/TMI.2024.3449690},
journal = {IEEE Trans Med Imaging},
title = {IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training.},
url = {http://dx.doi.org/10.1109/TMI.2024.3449690},
volume = {PP},
year = {2024}
}
TY - JOUR
AB - In the field of medical Vision-Language Pretraining (VLP), significant efforts have been devoted to deriving text and image features from both clinical reports and associated medical images. However, most existing methods may have overlooked the opportunity in leveraging the inherent hierarchical structure of clinical reports, which are generally split into 'findings' for descriptive content and 'impressions' for conclusive observation. Instead of utilizing this rich, structured format, current medical VLP approaches often simplify the report into either a unified entity or fragmented tokens. In this work, we propose a novel clinical prior guided VLP framework named IMITATE to learn the structure information from medical reports with hierarchical vision-language alignment. The framework derives multi-level visual features from the chest X-ray (CXR) images and separately aligns these features with the descriptive and the conclusive text encoded in the hierarchical medical report. Furthermore, a new clinical-informed contrastive loss is introduced for cross-modal learning, which accounts for clinical prior knowledge in formulating sample correlations in contrastive learning. The proposed model, IMITATE, outperforms baseline VLP methods across six different datasets, spanning five medical imaging downstream tasks. Comprehensive experimental results highlight the advantages of integrating the hierarchical structure of medical reports for vision-language alignment.
AU - Liu,C
AU - Cheng,S
AU - Shi,M
AU - Shah,A
AU - Bai,W
AU - Arcucci,R
DO - 10.1109/TMI.2024.3449690
PY - 2024///
TI - IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training.
T2 - IEEE Trans Med Imaging
UR - http://dx.doi.org/10.1109/TMI.2024.3449690
UR - https://www.ncbi.nlm.nih.gov/pubmed/39186435
VL - PP
ER -
For any enquiries about the Fungal Science Network at Imperial, please contact: