UN-SAM: Universal Prompt-Free Segmentation for Generalized Nuclei Images

分割 计算机科学 人工智能 计算机视觉
作者
Zhe Chen,Qiang Xu,Xinyu Liu,Yixuan Yuan
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2402.16663
摘要

In digital pathology, precise nuclei segmentation is pivotal yet challenged by the diversity of tissue types, staining protocols, and imaging conditions. Recently, the segment anything model (SAM) revealed overwhelming performance in natural scenarios and impressive adaptation to medical imaging. Despite these advantages, the reliance of labor-intensive manual annotation as segmentation prompts severely hinders their clinical applicability, especially for nuclei image analysis containing massive cells where dense manual prompts are impractical. To overcome the limitations of current SAM methods while retaining the advantages, we propose the Universal prompt-free SAM framework for Nuclei segmentation (UN-SAM), by providing a fully automated solution with remarkable generalization capabilities. Specifically, to eliminate the labor-intensive requirement of per-nuclei annotations for prompt, we devise a multi-scale Self-Prompt Generation (SPGen) module to revolutionize clinical workflow by automatically generating high-quality mask hints to guide the segmentation tasks. Moreover, to unleash the generalization capability of SAM across a variety of nuclei images, we devise a Domain-adaptive Tuning Encoder (DT-Encoder) to seamlessly harmonize visual features with domain-common and domain-specific knowledge, and further devise a Domain Query-enhanced Decoder (DQ-Decoder) by leveraging learnable domain queries for segmentation decoding in different nuclei domains. Extensive experiments prove that UN-SAM with exceptional performance surpasses state-of-the-arts in nuclei instance and semantic segmentation, especially the generalization capability in zero-shot scenarios. The source code is available at https://github.com/CUHK-AIM-Group/UN-SAM.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
良辰应助专一的豌豆采纳,获得10
1秒前
2秒前
清秀的天奇完成签到,获得积分10
2秒前
研友_VZG7GZ应助LHJZS采纳,获得10
2秒前
2秒前
香蕉觅云应助1561giou采纳,获得10
4秒前
fazat发布了新的文献求助10
4秒前
5秒前
6秒前
00完成签到,获得积分10
6秒前
独特的秋完成签到,获得积分10
7秒前
7秒前
险胜完成签到,获得积分10
8秒前
9秒前
9秒前
scq发布了新的文献求助10
10秒前
Hu发布了新的文献求助10
14秒前
16秒前
17秒前
CodeCraft应助gyx采纳,获得10
18秒前
QMZ完成签到,获得积分10
18秒前
顾矜应助siri采纳,获得10
18秒前
熊仔一百应助小米采纳,获得30
18秒前
johnson7777发布了新的文献求助10
19秒前
19秒前
Xman完成签到,获得积分10
19秒前
芝芝发布了新的文献求助10
19秒前
Dandraine发布了新的文献求助10
20秒前
wanna发布了新的文献求助10
22秒前
852应助pokect12138采纳,获得10
23秒前
盐水冰发布了新的文献求助10
23秒前
Amie应助小幸运采纳,获得10
24秒前
科研通AI2S应助Demon采纳,获得10
25秒前
一修完成签到,获得积分20
26秒前
良辰应助Lynn采纳,获得10
26秒前
赘婿应助shenmo18采纳,获得10
26秒前
生化材只有环完成签到,获得积分10
26秒前
cocolu应助袁凯旋采纳,获得10
26秒前
28秒前
勤奋幻柏完成签到,获得积分10
28秒前
高分求助中
Licensing Deals in Pharmaceuticals 2019-2024 3000
Effect of reactor temperature on FCC yield 2000
Very-high-order BVD Schemes Using β-variable THINC Method 1020
Impiego dell’associazione acetazolamide/pentossifillina nel trattamento dell’ipoacusia improvvisa idiopatica in pazienti affetti da glaucoma cronico 900
錢鍾書楊絳親友書札 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
Mission to Mao: Us Intelligence and the Chinese Communists in World War II 600
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3298309
求助须知:如何正确求助?哪些是违规求助? 2933265
关于积分的说明 8463010
捐赠科研通 2606294
什么是DOI,文献DOI怎么找? 1422911
科研通“疑难数据库(出版商)”最低求助积分说明 661573
邀请新用户注册赠送积分活动 644983