Medical Image Segmentation Review: The Success of U-Net

图像分割 人工智能 计算机科学 计算机视觉 分割 尺度空间分割 图像处理 图像纹理 模式识别(心理学) 图像(数学) 医学影像学
作者
Reza Azad,Ehsan Khodapanah Aghdam,Amelie Rauland,Yiwei Jia,Atlas Haddadi Avval,Afshin Bozorgpour,Sanaz Karimijafarbigloo,Joseph Cohen,Ehsan Adeli,Dorit Merhof
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [Institute of Electrical and Electronics Engineers]
卷期号:: 1-20 被引量:8
标识
DOI:10.1109/tpami.2024.3435571
摘要

Automatic medical image segmentation is a crucial topic in the medical domain and successively a critical counterpart in the computer-aided diagnosis paradigm. U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities. Over the years, the U-Net model has received tremendous attention from academic and industrial researchers who have extended it to address the scale and complexity created by medical tasks. These extensions are commonly related to enhancing the U-Net's backbone, bottleneck, or skip connections, or including representation learning, or combining it with a Transformer architecture, or even addressing probabilistic prediction of the segmentation map. Having a compendium of different previously proposed U-Net variants makes it easier for machine learning researchers to identify relevant research questions and understand the challenges of the biological tasks that challenge the model. In this work, we discuss the practical aspects of the U-Net model and organize each variant model into a taxonomy. Moreover, to measure the performance of these strategies in a clinical application, we propose fair evaluations of some unique and famous designs on well-known datasets. Furthermore, we provide a comprehensive implementation library with trained models. In addition, for ease of future studies, we created an online list of U-Net papers with their possible official implementation. All information is gathered in a GitHub repository https://github.com/NITR098/Awesome-U-Net.
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
2秒前
rosalieshi应助jado采纳,获得30
3秒前
3秒前
Singularity应助jiapei_1019采纳,获得10
5秒前
DianaRang完成签到,获得积分10
5秒前
李爱国应助云_123采纳,获得10
6秒前
梅卡完成签到 ,获得积分10
7秒前
8秒前
9秒前
9秒前
人专完成签到,获得积分10
10秒前
善学以致用应助lisa采纳,获得10
10秒前
11秒前
天天快乐应助lvlv采纳,获得10
11秒前
科目三应助周星星采纳,获得10
13秒前
13秒前
重生之我是院士完成签到,获得积分10
13秒前
14秒前
14秒前
16秒前
温暖的颜演完成签到 ,获得积分20
16秒前
meng完成签到,获得积分10
18秒前
云_123发布了新的文献求助10
18秒前
cc完成签到 ,获得积分10
18秒前
领导范儿应助噼里啪啦采纳,获得10
18秒前
Misty发布了新的文献求助10
19秒前
19秒前
wanci应助annabel采纳,获得200
21秒前
22秒前
22秒前
23秒前
24秒前
24秒前
25秒前
25秒前
25秒前
25秒前
25秒前
25秒前
pipipiya完成签到,获得积分10
25秒前
高分求助中
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
Rechtsphilosophie 1000
Bayesian Models of Cognition:Reverse Engineering the Mind 888
Le dégorgement réflexe des Acridiens 800
Defense against predation 800
Very-high-order BVD Schemes Using β-variable THINC Method 568
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 3134881
求助须知:如何正确求助?哪些是违规求助? 2785770
关于积分的说明 7774093
捐赠科研通 2441601
什么是DOI,文献DOI怎么找? 1298038
科研通“疑难数据库(出版商)”最低求助积分说明 625075
版权声明 600825