Segment Anything Model for Medical Images?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Yuhao, Yang, Xin, Liu, Lian, Zhou, Han, Chang, Ao, Zhou, Xinrui, Chen, Rusi, Yu, Junxuan, Chen, Jiongquan, Chen, Chaoyu, Liu, Sijing, Chi, Haozhe, Hu, Xindi, Yue, Kejuan, Li, Lei, Grau, Vicente, Fan, Deng-Ping, Dong, Fajin, Ni, Dong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913198371766272
author Huang, Yuhao
Yang, Xin
Liu, Lian
Zhou, Han
Chang, Ao
Zhou, Xinrui
Chen, Rusi
Yu, Junxuan
Chen, Jiongquan
Chen, Chaoyu
Liu, Sijing
Chi, Haozhe
Hu, Xindi
Yue, Kejuan
Li, Lei
Grau, Vicente
Fan, Deng-Ping
Dong, Fajin
Ni, Dong
author_facet Huang, Yuhao
Yang, Xin
Liu, Lian
Zhou, Han
Chang, Ao
Zhou, Xinrui
Chen, Rusi
Yu, Junxuan
Chen, Jiongquan
Chen, Chaoyu
Liu, Sijing
Chi, Haozhe
Hu, Xindi
Yue, Kejuan
Li, Lei
Grau, Vicente
Fan, Deng-Ping
Dong, Fajin
Ni, Dong
contents The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging because of the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks. We comprehensively analyzed different models and strategies on the so-called COSMOS 1050K dataset. Our findings mainly include the following: 1) SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations. 2) SAM with the large ViT-H showed better overall performance than that with the small ViT-B. 3) SAM performed better with manual hints, especially box, than the Everything mode. 4) SAM could help human annotation with high labeling quality and less time. 5) SAM was sensitive to the randomness in the center point and tight box prompts, and may suffer from a serious performance drop. 6) SAM performed better than interactive methods with one or a few points, but will be outpaced as the number of points increases. 7) SAM's performance correlated to different factors, including boundary complexity, intensity differences, etc. 8) Finetuning the SAM on specific medical tasks could improve its average DICE performance by 4.39% and 6.68% for ViT-B and ViT-H, respectively. We hope that this comprehensive report can help researchers explore the potential of SAM applications in MIS, and guide how to appropriately use and develop SAM.
format Preprint
id arxiv_https___arxiv_org_abs_2304_14660
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Segment Anything Model for Medical Images?
Huang, Yuhao
Yang, Xin
Liu, Lian
Zhou, Han
Chang, Ao
Zhou, Xinrui
Chen, Rusi
Yu, Junxuan
Chen, Jiongquan
Chen, Chaoyu
Liu, Sijing
Chi, Haozhe
Hu, Xindi
Yue, Kejuan
Li, Lei
Grau, Vicente
Fan, Deng-Ping
Dong, Fajin
Ni, Dong
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging because of the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks. We comprehensively analyzed different models and strategies on the so-called COSMOS 1050K dataset. Our findings mainly include the following: 1) SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations. 2) SAM with the large ViT-H showed better overall performance than that with the small ViT-B. 3) SAM performed better with manual hints, especially box, than the Everything mode. 4) SAM could help human annotation with high labeling quality and less time. 5) SAM was sensitive to the randomness in the center point and tight box prompts, and may suffer from a serious performance drop. 6) SAM performed better than interactive methods with one or a few points, but will be outpaced as the number of points increases. 7) SAM's performance correlated to different factors, including boundary complexity, intensity differences, etc. 8) Finetuning the SAM on specific medical tasks could improve its average DICE performance by 4.39% and 6.68% for ViT-B and ViT-H, respectively. We hope that this comprehensive report can help researchers explore the potential of SAM applications in MIS, and guide how to appropriately use and develop SAM.
title Segment Anything Model for Medical Images?
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2304.14660