CIResDiff: A Clinically-Informed Residual Diffusion Model for Predicting Idiopathic Pulmonary Fibrosis Progression

doi:10.1007/978-3-031-73284-3_9

	CIResDiff: A Clinically-Informed Residual Diffusion Model for Predicting Idiopathic Pulmonary Fibrosis Progression
	Jiang, Caiwen1,2,3,4 ; Xing, Xiaodan 3,4; Oul, Zaixin 1,2; Liu, Mianxin 6; Simone, Walsh 3,4; Yang, Guang 3,4,7,9,10; Shen, Dinggang1,2,5,8
	2025
会议录名称	MACHINE LEARNING IN MEDICAL IMAGING, PT I, MLMI 2024 (IF:0.402[JCR-2005],0.000[5-Year])
ISSN	0302-9743
卷号	15241
发表状态	已发表
DOI	10.1007/978-3-031-73284-3_9
摘要	The progression of Idiopathic Pulmonary Fibrosis (IPF) significantly correlates with higher patient mortality rates. Early detection of IPF progression is critical for initiating timely treatment, which can effectively slow down the advancement of the disease. However, the current clinical criteria define disease progression requiring two CT scans with a one-year interval, presenting a dilemma: a disease progression is identified only after the disease has already progressed. To this end, in this paper, we develop a novel diffusion model to accurately predict the progression of IPF by generating patient's follow-up CT scan from the initial CT scan. Specifically, from the clinical prior knowledge, we tailor improvements to the traditional diffusion model and propose a Clinically-Informed Residual Diffusion model, called CIResDiff. The key innovations of CIResDiff include 1) performing the target region pre-registration to align the lung regions of two CT scans at different time points for reducing the generation difficulty, 2) adopting the residual diffusion instead of traditional diffusion to enable the model focus more on differences (i.e., lesions) between the two CT scans rather than the largely identical anatomical content, and 3) designing the clinically-informed process based on CLIP technology to integrate lung function information which is highly relevant to diagnosis into the reverse process for assisting generation. Extensive experiments on clinical data demonstrate that our approach can outperform state-of-the-art methods and effectively predict the progression of IPF.
关键词	Prediction of pulmonary fibrosis progression Residual diffusion model Clinically Informed CLIP-based text processing
会议名称	15th International Workshop on Machine Learning in Medical Imaging
出版地	GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
会议地点	null,Marrakesh,MOROCCO
会议日期	OCT 06, 2024
URL	查看原文
收录类别	CPCI-S
语种	英语
资助项目	National Natural Science Foundation of China["U23A20295","62131015","62250710165","2022ZD0209000"] ; Shanghai Municipal Central Guided Local Science and Technology Development Fund[YDZX20233100001001] ; China Ministry of Science and Technology[STI2030-Major Projects-2022ZD0213100] ; Key R&D Program of Guangdong Province, China["2023B0303040001","2021B0101420006"] ; ERC IMI["10100 5122","952172"] ; MRC[MC/PC/21013] ; Royal Society[IECn NS FCn211235] ; Boehringer Ingelheim Ltd[RDA01] ; Wellcome Leap Dynamic Resilience["EP/Z002206/1","MR/V023799/1"]
WOS研究方向	Computer Science ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001424557900009
出版者	SPRINGER INTERNATIONAL PUBLISHING AG
EISSN	1611-3349
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/414201
专题	生物医学工程学院信息科学与技术学院_博士生生物医学工程学院_PI研究组_沈定刚组
通讯作者	Shen, Dinggang
作者单位	1.ShanghaiTech Univ, Sch Biomed Engn, Shanghai, Peoples R China 2.ShanghaiTech Univ, State Key Lab Adv Med Mat & Devices, Shanghai, Peoples R China 3.Imperial Coll London, Bioengn Dept, London, England 4.Imperial Coll London, Imperial X, London, England 5.Shanghai Clin Res & Trial Ctr, Shanghai 201210, Peoples R China 6.Shanghai Artificial Intelligence Lab, Shanghai 200232, Peoples R China 7.Imperial Coll London, Natl Heart & Lung Inst, London, England 8.Shanghai United Imaging Intelligence Co Ltd, Shanghai, Peoples R China 9.Royal Brompton Hosp, Cardiovasc Res Ctr, London, England 10.Kings Coll London, Sch Biomed Engn & Imaging Sci, London, England
第一作者单位	生物医学工程学院; 上海科技大学
通讯作者单位	生物医学工程学院; 上海科技大学
第一作者的第一单位	生物医学工程学院
推荐引用方式 GB/T 7714	Jiang, Caiwen,Xing, Xiaodan,Oul, Zaixin,et al. CIResDiff: A Clinically-Informed Residual Diffusion Model for Predicting Idiopathic Pulmonary Fibrosis Progression[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2025.