Streamlined photoacoustic image processing with foundation models:A training-free solution  

作　　者：Handi Deng Yucheng Zhou Jiaxuan Xiang Liujie Gu Yan Luo Hai Feng Mingyuan Liu Cheng Ma 

机构地区：[1]Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering Tsinghua University 30 Shuangqing Road Haidian,Beijing 100084,P.R.China [2]Institute for Precision Healthcare,Tsinghua University 77 Shuangqing Road,Haidian,Beijing 100084,P.R.China [3]Institute for Intelligent Healthcare,Tsinghua University 77 Shuangqing Road,Haidian,Beijing 100084,P.R.China [4]School of Biological Science and Medical Engineering Beihang University,37 XueYuan Road,Haidian,Beijing 100191,P.R.China [5]TsingPAI Technology Co.,Ltd.,27 Jiancaicheng Middle Road Haidian,Beijing 100096,P.R.China [6]Department of Vascular Surgery,Beijing Friendship Hospital Capital Medical University,95 Yongan Road,Haidian,Beijing 100050,P.R.China

出　　处：《Journal of Innovative Optical Health Sciences》2025年第1期55-65,共11页创新光学健康科学杂志(英文)

基　　金：support from Strategic Project of Precision Surgery,Tsinghua University;Initiative Scientific Research Program,Institute for Intelligent Healthcare,Tsinghua University;Tsinghua-Foshan Institute of Advanced Manufacturing;National Natural Science Foundation of China(61735016);Beijing Nova Program(20230484308);Young Elite Scientists Sponsorship Program by CAST(2023QNRC001);Youth Elite Program of Beijing Friendship Hospital(YYQCJH2022-9);Science and Technology Program of Beijing Tongzhou District(KJ2023CX012).

摘　　要：Foundation models(FMs)have rapidly evolved and have achieved signicant accomplishments in computer vision tasks.Specically,the prompt mechanism conveniently allows users to integrate image prior information into the model,making it possible to apply models without any training.Therefore,we proposed a workflow based on foundation models and zero training to solve the tasks of photoacoustic(PA)image processing.We employed the Segment Anything Model(SAM)by setting simple prompts and integrating the model's outputs with prior knowledge of the imaged objects to accomplish various tasks,including:(1)removing the skin signal in three-dimensional PA image rendering;(2)dual speed-of-sound reconstruction,and(3)segmentation ofnger blood vessels.Through these demonstrations,we have concluded that FMs can be directly applied in PA imaging without the requirement for network design and training.This potentially allows for a hands-on,convenient approach to achieving efficient and accurate segmentation of PA images.This paper serves as a comprehensive tutorial,facilitating the mastery of the technique through the provision of code and sample datasets.

关 键 词：Foundation models photoacoustic imaging image segmentation large model 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R318[自动化与计算机技术—计算机科学与技术]