Research on Medical Image Segmentation Based on SAM and Its Future Prospects DOI Creative Commons
Kebin Fan, Liang Liang, Hao Li

et al.

Bioengineering, Journal Year: 2025, Volume and Issue: 12(6), P. 608 - 608

Published: June 3, 2025

The rapid advancement of prompt-based models in natural language processing and image generation has revolutionized the field segmentation. introduction Segment Anything Model (SAM) further invigorated this domain with its unprecedented versatility. However, applicability to medical segmentation remains uncertain due significant disparities between images, which demand careful consideration. This study comprehensively analyzes recent efforts adapt SAM for segmentation, including empirical benchmarking methodological refinements aimed at bridging gap SAM’s capabilities unique challenges imaging. Furthermore, we explore future directions field. While direct application complex, multimodal, multi-target datasets may not yet yield optimal results, insights from these provide crucial guidance developing foundational tailored intricacies analysis. Despite existing challenges, holds considerable potential demonstrate advantages robust near future.

Language: Английский

Segment anything model for medical image segmentation: Current applications and future directions DOI
Yichi Zhang, Zhenrong Shen, Rushi Jiao

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 171, P. 108238 - 108238

Published: Feb. 27, 2024

Language: Английский

Citations

74
Polyp Segmentation Using a Hybrid Vision Transformer and a Hybrid Loss Function DOI
Evgin Göçeri

Deleted Journal, Journal Year: 2024, Volume and Issue: 37(2), P. 851 - 863

Published: Jan. 12, 2024

Accurate and early detection of precursor adenomatous polyps their removal at the stage can significantly decrease mortality rate occurrence disease since most colorectal cancer evolve from polyps. However, accurate segmentation by doctors are difficult mainly these factors: (i) quality screening with colonoscopy depends on imaging experience doctors; (ii) visual inspection is time-consuming, burdensome, tiring; (iii) prolonged inspections lead to being missed even when physician experienced. To overcome problems, computer-aided methods have been proposed. they some disadvantages or limitations. Therefore, in this work, a new architecture based residual transformer layers has designed used for polyp segmentation. In proposed segmentation, both high-level semantic features low-level spatial utilized. Also, novel hybrid loss function The focal Tversky loss, binary cross-entropy, Jaccard index reduces image-wise pixel-wise differences as well improves regional consistencies. Experimental works indicated effectiveness approach terms dice similarity (0.9048), recall (0.9041), precision (0.9057), F2 score (0.8993). Comparisons state-of-the-art shown its better performance.

Language: Английский

Citations

46
A systematic review of deep learning based image segmentation to detect polyp DOI Open Access
Mayuri Gupta, Ashish Mishra

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(1)

Published: Jan. 1, 2024

Language: Английский

Citations

30
A survey on deep learning for polyp segmentation: techniques, challenges and future trends DOI Creative Commons

Jiaxin Mei,

Tao Zhou,

Kaiwen Huang

et al.

Visual Intelligence, Journal Year: 2025, Volume and Issue: 3(1)

Published: Jan. 3, 2025

Language: Английский

Citations

7
SAM-IE: SAM-based image enhancement for facilitating medical image diagnosis with segmentation foundation model DOI

Changyan Wang,

Haobo Chen, X. K. Zhou

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 249, P. 123795 - 123795

Published: March 23, 2024

Language: Английский

Citations

11
Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding DOI

Zhiheng Cheng,

Qingyue Wei,

Hongru Zhu

et al.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Journal Year: 2024, Volume and Issue: 35, P. 3511 - 3522

Published: June 16, 2024

Language: Английский

Citations

10
When SAM Meets Sonar Images DOI
Lin Wang, Xiufen Ye, Liqiang Zhu

et al.

IEEE Geoscience and Remote Sensing Letters, Journal Year: 2024, Volume and Issue: 21, P. 1 - 5

Published: Jan. 1, 2024

Segment Anything Model (SAM) has revolutionized the way of segmentation due to its remarkable capacity for generalized segmentation. However, SAM's performance may decline when applied tasks involving domains that differ from natural images. Nonetheless, by employing fine-tuning techniques, SAM exhibits promising capabilities in specific domains, such as medicine and planetary science. Notably, there is a lack research on application sonar imaging. In this paper, we aim address gap conducting comprehensive investigation Specifically, evaluate with various settings Moreover, fine-tune images using effective methods both prompts semantic The experimental results reveal substantial enhancement fine-tuned SAM, increasing 0.24 0.75 mIoU. This underscores potential image applications. Additionally, even only 2 out 11 categories are utilized training, model box prompt sustains an mIoU 0.69, showcasing outstanding capability general code available at https://github.com/wangsssky/SonarSAM.

Language: Английский

Citations

7
Deep Bayesian segmentation for colon polyps: Well-calibrated predictions in medical imaging DOI
Daniel Ramos, Héctor J. Hortúa

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 104, P. 107383 - 107383

Published: Jan. 14, 2025

Language: Английский

Citations

1
Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learning DOI

Tianang Leng,

Y. T. Zhang,

Kun Han

et al.

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Journal Year: 2024, Volume and Issue: unknown, P. 7910 - 7920

Published: Jan. 3, 2024

While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical primarily attributable insufficient representation of images training dataset. Nonetheless, gathering comprehensive datasets and models that are universally applicable is particularly challenging due long-tail problem common images.To address this gap, here we present a Self-Sampling Meta SAM (SSM-SAM) framework few-shot image segmentation. Our innovation lies design three key modules: 1) An online fast gradient descent optimizer, further optimized by meta-learner, which ensures swift robust adaptation new tasks. 2) A module designed provide well-aligned visual prompts improved attention allocation; 3) attention-based decoder specifically capture relationship between different slices. Extensive experiments on popular abdominal CT dataset an MRI demonstrate proposed method achieves significant improvements over state-of-the-art methods segmentation, with average 10.21% 1.80% terms DSC, respectively. In conclusion, novel approach rapid interactive adapting organ just 0.83 minutes. Code available at https://github.com/DragonDescentZerotsu/SSM-SAM

Language: Английский

Citations

6
LeSAM: Adapt Segment Anything Model for Medical Lesion Segmentation DOI
Yunbo Gu, Qianyu Wu, Hui Tang

et al.

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2024, Volume and Issue: 28(10), P. 6031 - 6041

Published: May 29, 2024

The Segment Anything Model (SAM) is a foundational model that has demonstrated impressive results in the field of natural image segmentation. However, its performance remains suboptimal for medical segmentation, particularly when delineating lesions with irregular shapes and low contrast. This can be attributed to significant domain gap between images on which SAM was originally trained. In this paper, we propose an adaptation specifically tailored lesion segmentation termed LeSAM. LeSAM first learns medical-specific knowledge through efficient module integrates it general obtained from pre-trained SAM. Subsequently, leverage merged generate masks using modified mask decoder implemented as lightweight U-shaped network design. modification enables better delineation boundaries while facilitating ease training. We conduct comprehensive experiments various tasks involving different modalities such CT scans, MRI ultrasound images, dermoscopic endoscopic images. Our proposed method achieves superior compared previous state-of-the-art methods 8 out 12 achieving competitive remaining 4 datasets. Additionally, ablation studies are conducted validate effectiveness our modules decoder.

Language: Английский

Citations

5