PulseAugur
EN
LIVE 09:40:36

New framework ProTrans enhances longitudinal chest X-ray analysis

Researchers have developed ProTrans, a new vision-language pretraining framework designed to analyze longitudinal chest X-ray (CXR) data. This framework models disease progression as a directional semantic transition between paired CXR studies, using radiology reports to anchor CXR representations and explicitly encode semantic shifts. ProTrans incorporates reversed temporal modeling and bidirectional reconstruction consistency to disentangle directional semantics and improve trajectory modeling. Experiments show ProTrans outperforms existing methods on downstream tasks like disease progression classification and captioning, establishing it as a unified pretraining framework for longitudinal CXR understanding. AI

RANK_REASON The cluster contains an academic paper detailing a new framework for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Zhangfeng Hu, Zefan Yang, Ge Wang, Tanveer Syeda-Mahmood, Anushree Burade, Mannudeep Kalra, Pingkun Yan ·

    Learning Directional Semantic Transitions for Longitudinal Chest X-ray Analysis

    arXiv:2606.15938v1 Announce Type: new Abstract: Chest X-ray (CXR) interpretation often requires longitudinal comparison to assess disease progression. Existing approaches typically rely on temporal feature fusion or inter-study discrepancy modeling, yet remain limited in capturin…