WeChat Mini Program
Old Version Features

AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation

IEEE/CVF Winter Conference on Applications of Computer Vision(2025)

Wayne State University Department of Computer Science

Cited 17|Views32
Abstract
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 sub optimally 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.
More
Translated text
Key words
Multi-organ Segmentation,Medical Imaging,3D Images,Image Segmentation,Medical Applications,2D Images,Natural Images,Domain Experts,Segmentation Task,3D Segmentation,Medical Tasks,Medical Image Segmentation,Foundation Model,Adrenal,Convolutional Layers,Computer Vision,Feature Maps,Lookup Table,Transformer Model,Abdominal Computed Tomography,Vision Transformer,3D Input,Dice Score,CT Datasets,Positional Encoding,Image Encoder,Volumetric Segmentation,Self-supervised Learning,3D Convolution,3D Features
PDF
Bibtex
收藏
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:本文提出了一种名为AutoSAM Adapter的方法,用于自动适配SAM模型进行3D医疗图像分割,消除了手动生成提示的需求,并将知识转移到其他为3D医疗图像分析量身定制的轻量级模型,实现了医疗图像分割任务的最佳性能。

方法】:采用参数高效适应技术,开发自动提示学习范式,以促进SAM模型能力的转换到3D医疗图像分割。

实验】:通过广泛的实验评估,证明了AutoSAM Adapter是有效地利用基础模型在2D自然图像分割中 emerging ability for 3D medical image segmentation的关键基础。