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

Foundation models (FMs) have rapidly evolved and have achieved significant accomplishments in computer vision tasks. Specifically, the prompt mechanism conveniently allows users to integrate image prior information into the model, making it possible to apply models without any training. Therefore, w...

Full description

Saved in:
Bibliographic Details
Main Authors: Handi Deng, Yucheng Zhou, Jiaxuan Xiang, Liujie Gu, Yan Luo, Hai Feng, Mingyuan Liu, Cheng Ma
Format: Article
Language:English
Published: World Scientific Publishing 2025-01-01
Series:Journal of Innovative Optical Health Sciences
Subjects:
Online Access:https://www.worldscientific.com/doi/10.1142/S1793545824500196
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832585051747909632
author Handi Deng
Yucheng Zhou
Jiaxuan Xiang
Liujie Gu
Yan Luo
Hai Feng
Mingyuan Liu
Cheng Ma
author_facet Handi Deng
Yucheng Zhou
Jiaxuan Xiang
Liujie Gu
Yan Luo
Hai Feng
Mingyuan Liu
Cheng Ma
author_sort Handi Deng
collection DOAJ
description Foundation models (FMs) have rapidly evolved and have achieved significant accomplishments in computer vision tasks. Specifically, 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 of finger 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.
format Article
id doaj-art-2218390580d14198b0db03dc5ad16471
institution Kabale University
issn 1793-5458
1793-7205
language English
publishDate 2025-01-01
publisher World Scientific Publishing
record_format Article
series Journal of Innovative Optical Health Sciences
spelling doaj-art-2218390580d14198b0db03dc5ad164712025-01-27T05:49:52ZengWorld Scientific PublishingJournal of Innovative Optical Health Sciences1793-54581793-72052025-01-01180110.1142/S1793545824500196Streamlined photoacoustic image processing with foundation models: A training-free solutionHandi Deng0Yucheng Zhou1Jiaxuan Xiang2Liujie Gu3Yan Luo4Hai Feng5Mingyuan Liu6Cheng Ma7Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University 30 Shuangqing Road, Haidian, Beijing 100084, P. R. ChinaSchool of Biological Science and Medical Engineering, Beihang University, 37 XueYuan Road, Haidian, Beijing 100191, P. R. ChinaTsingPAI Technology Co., Ltd., 27 Jiancaicheng Middle Road, Haidian, Beijing 100096, P. R. ChinaBeijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University 30 Shuangqing Road, Haidian, Beijing 100084, P. R. ChinaBeijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University 30 Shuangqing Road, Haidian, Beijing 100084, P. R. ChinaDepartment of Vascular Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yongan Road, Haidian, Beijing 100050, P. R. ChinaDepartment of Vascular Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yongan Road, Haidian, Beijing 100050, P. R. ChinaBeijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University 30 Shuangqing Road, Haidian, Beijing 100084, P. R. ChinaFoundation models (FMs) have rapidly evolved and have achieved significant accomplishments in computer vision tasks. Specifically, 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 of finger 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.https://www.worldscientific.com/doi/10.1142/S1793545824500196Foundation modelsphotoacoustic imagingimage segmentationlarge model
spellingShingle Handi Deng
Yucheng Zhou
Jiaxuan Xiang
Liujie Gu
Yan Luo
Hai Feng
Mingyuan Liu
Cheng Ma
Streamlined photoacoustic image processing with foundation models: A training-free solution
Journal of Innovative Optical Health Sciences
Foundation models
photoacoustic imaging
image segmentation
large model
title Streamlined photoacoustic image processing with foundation models: A training-free solution
title_full Streamlined photoacoustic image processing with foundation models: A training-free solution
title_fullStr Streamlined photoacoustic image processing with foundation models: A training-free solution
title_full_unstemmed Streamlined photoacoustic image processing with foundation models: A training-free solution
title_short Streamlined photoacoustic image processing with foundation models: A training-free solution
title_sort streamlined photoacoustic image processing with foundation models a training free solution
topic Foundation models
photoacoustic imaging
image segmentation
large model
url https://www.worldscientific.com/doi/10.1142/S1793545824500196
work_keys_str_mv AT handideng streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution
AT yuchengzhou streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution
AT jiaxuanxiang streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution
AT liujiegu streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution
AT yanluo streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution
AT haifeng streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution
AT mingyuanliu streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution
AT chengma streamlinedphotoacousticimageprocessingwithfoundationmodelsatrainingfreesolution