paper-with-me

홈 › Papers

CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships between Chest X-Rays

2022-08-08 · Gaurang Karwande, Amarachi Mbakawe, Joy T. Wu, Leo A. Celi, Mehdi Moradi, Ismini Lourentzou

Despite the progress in utilizing deep learning to automate chest radiograph interpretation and disease diagnosis tasks, change between sequential Chest X-rays (CXRs) has received limited attention. Monitoring the progression of pathologies that are visualized through chest imaging poses several challenges in anatomical motion estimation and image registration, i.e., spatially aligning the two images and modeling temporal dynamics in change detection. In this work, we propose CheXRelNet, a neural model that can track longitudinal pathology change relations between two CXRs. CheXRelNet incorporates local and global visual features, utilizes inter-image and intra-image anatomical information, and learns dependencies between anatomical region attributes, to accurately predict disease change for a pair of CXRs. Experimental results on the Chest ImaGenome dataset show increased downstream performance compared to baselines. Code is available at https://github.com/PLAN-Lab/ChexRelNet

📄 PDF Abstract BibTeX arXiv:2208.03873

Code (1)

plan-lab/chexrelnet 공식 구현 pytorch

Tasks

AnatomyChange DetectionImage RegistrationMotion Estimation

Similar Papers 제목 키워드 기반

Anatomy-Aware Cardiac Motion Estimation

2020-08-17 · Pingjun Chen, Xiao Chen, Eric Z. Chen, Hanchao Yu 외

Cardiac motion estimation is critical to the assessment of cardiac function. Myocardium feature tracking (FT) can directly estimate cardiac motion from cine MRI, which requires no special scanning procedure. However, cur…

AnatomyMotion Estimation

Learning accurate rigid registration for longitudinal brain MRI from synthetic data

2025-01-22 · JingRu Fu, Adrian V. Dalca, Bruce Fischl, Rodrigo Moreno 외

Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registrati…

Anatomy

Reconstructing Sinus Anatomy from Endoscopic Video -- Towards a Radiation-free Approach for Quantitative Longitudinal Assessment

2020-03-18 · Xingtong Liu, Maia Stiber, Jindan Huang, Masaru Ishii 외

Reconstructing accurate 3D surface models of sinus anatomy directly from an endoscopic video is a promising avenue for cross-sectional and longitudinal analysis to better understand the relationship between sinus anatomy…

3D ReconstructionAnatomy

Brightness-Invariant Tracking Estimation in Tagged MRI

2025-05-23 · Zhangxing Bian, Shuwen Wei, Xiao Liang, Yuan-Chiao Lu 외

Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal …

AnatomyDenoisingOptical Flow EstimationTAG

AI-Driven Three-Dimensional Reconstruction and Quantitative Analysis for Burn Injury Assessment

2026-01-27 · S. Kalaycioglu, C. Hong, K. Zhai, H. Xie 외 arxiv

Accurate, reproducible burn assessment is critical for treatment planning, healing monitoring, and medico-legal documentation, yet conventional visual inspection and 2D photography are subjective and limited for longitud…