AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913583676260352 |
|---|---|
| author | Li, Chengyin Khanduri, Prashant Qiang, Yao Sultan, Rafi Ibn Chetty, Indrin Zhu, Dongxiao |
| author_facet | Li, Chengyin Khanduri, Prashant Qiang, Yao Sultan, Rafi Ibn Chetty, Indrin Zhu, Dongxiao |
| contents | Segment Anything Model (SAM) is one of the pioneering prompt-based foundation models for image segmentation and has been rapidly adopted for various medical imaging applications. However, in clinical settings, creating effective prompts is notably challenging and time-consuming, requiring the expertise of domain specialists such as physicians. This requirement significantly diminishes SAM's primary advantage, its interactive capability with end users, in medical applications. Moreover, recent studies have indicated that SAM, originally designed for 2D natural images, performs suboptimally on 3D medical image segmentation tasks. This subpar performance is attributed to the domain gaps between natural and medical images and the disparities in spatial arrangements between 2D and 3D images, particularly in multi-organ segmentation applications. To overcome these challenges, we present a novel technique termed AutoProSAM. This method automates 3D multi-organ CT-based segmentation by leveraging SAM's foundational model capabilities without relying on domain experts for prompts. The approach utilizes parameter-efficient adaptation techniques to adapt SAM for 3D medical imagery and incorporates an effective automatic prompt learning paradigm specific to this domain. By eliminating the need for manual prompts, it enhances SAM's capabilities for 3D medical image segmentation and achieves state-of-the-art (SOTA) performance in CT-based multi-organ segmentation tasks. The code is in this {\href{https://github.com/ChengyinLee/AutoProSAM_2024}{link}}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_14936 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation Li, Chengyin Khanduri, Prashant Qiang, Yao Sultan, Rafi Ibn Chetty, Indrin Zhu, Dongxiao Computer Vision and Pattern Recognition Artificial Intelligence Segment Anything Model (SAM) is one of the pioneering prompt-based foundation models for image segmentation and has been rapidly adopted for various medical imaging applications. However, in clinical settings, creating effective prompts is notably challenging and time-consuming, requiring the expertise of domain specialists such as physicians. This requirement significantly diminishes SAM's primary advantage, its interactive capability with end users, in medical applications. Moreover, recent studies have indicated that SAM, originally designed for 2D natural images, performs suboptimally on 3D medical image segmentation tasks. This subpar performance is attributed to the domain gaps between natural and medical images and the disparities in spatial arrangements between 2D and 3D images, particularly in multi-organ segmentation applications. To overcome these challenges, we present a novel technique termed AutoProSAM. This method automates 3D multi-organ CT-based segmentation by leveraging SAM's foundational model capabilities without relying on domain experts for prompts. The approach utilizes parameter-efficient adaptation techniques to adapt SAM for 3D medical imagery and incorporates an effective automatic prompt learning paradigm specific to this domain. By eliminating the need for manual prompts, it enhances SAM's capabilities for 3D medical image segmentation and achieves state-of-the-art (SOTA) performance in CT-based multi-organ segmentation tasks. The code is in this {\href{https://github.com/ChengyinLee/AutoProSAM_2024}{link}}. |
| title | AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2308.14936 |