UNETR++: Delving Into Efficient and Accurate 3D Medical Image Segmentation

计算机科学 分割 瓶颈 判别式 人工智能 计算复杂性理论 推论 图像分割 掷骰子 失败 模式识别(心理学) 算法 并行计算 数学 几何学 嵌入式系统
作者
Abdelrahman Shaker,Muhammad Maaz,Hanoona Rasheed,Salman Khan,Ming–Hsuan Yang,Fahad Shahbaz Khan
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:43 (9): 3377-3390 被引量:75
标识
DOI:10.1109/tmi.2024.3398728
摘要

Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks. Within the transformer models, the self-attention mechanism is one of the main building blocks that strives to capture long-range dependencies, compared to the local convolutional-based design. However, the self-attention operation has quadratic complexity which proves to be a computational bottleneck, especially in volumetric medical imaging, where the inputs are 3D with numerous slices. In this paper, we propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features using a pair of inter-dependent branches based on spatial and channel attention. Our spatial attention formulation is efficient and has linear complexity with respect to the input. To enable communication between spatial and channel-focused branches, we share the weights of query and key mapping functions that provide a complimentary benefit (paired attention), while also reducing the complexity. Our extensive evaluations on five benchmarks, Synapse, BTCV, ACDC, BraTS, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy. On Synapse, our UNETR++ sets a new state-of-the-art with a Dice Score of 87.2%, while significantly reducing parameters and FLOPs by over 71%, compared to the best method in the literature. Our code and models are available at: https://tinyurl.com/2p87x5xn.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
十三发布了新的文献求助10
刚刚
1秒前
1秒前
liangmh完成签到,获得积分10
1秒前
一二不休完成签到,获得积分10
1秒前
123发布了新的文献求助10
2秒前
4秒前
ding应助黑熊安巴尼采纳,获得10
5秒前
Ava应助wjxcl采纳,获得10
5秒前
闪闪如南发布了新的文献求助10
5秒前
深情安青应助一二不休采纳,获得10
6秒前
8秒前
123完成签到,获得积分10
8秒前
不扯先生完成签到,获得积分10
9秒前
柳絮完成签到,获得积分20
10秒前
lll完成签到,获得积分10
10秒前
sdl完成签到,获得积分10
10秒前
Orange应助孟婆的碗采纳,获得10
11秒前
zhangmy1989发布了新的文献求助30
11秒前
11秒前
清秀的不言完成签到 ,获得积分10
11秒前
杂化轨道退役研究员完成签到,获得积分10
11秒前
FashionBoy应助tanglu采纳,获得10
12秒前
13秒前
闪闪如南完成签到,获得积分10
14秒前
wjxcl完成签到,获得积分10
15秒前
15秒前
15秒前
12233完成签到,获得积分10
16秒前
16秒前
洪武完成签到,获得积分20
16秒前
17秒前
Yuantian发布了新的文献求助10
18秒前
传奇3应助浪花淘尽英雄采纳,获得10
19秒前
流川枫完成签到,获得积分10
19秒前
赘婿应助leo采纳,获得10
19秒前
追寻夏烟完成签到 ,获得积分10
20秒前
闪闪寒云完成签到 ,获得积分10
20秒前
13633501455完成签到 ,获得积分10
21秒前
阿里完成签到,获得积分10
21秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038569
求助须知:如何正确求助?哪些是违规求助? 3576279
关于积分的说明 11374944
捐赠科研通 3305979
什么是DOI,文献DOI怎么找? 1819354
邀请新用户注册赠送积分活动 892698
科研通“疑难数据库(出版商)”最低求助积分说明 815048