TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

计算机科学 分割 人工智能 图像分割 编码器 变压器 卷积神经网络 地点 基于分割的对象分类 尺度空间分割 计算机视觉 模式识别(心理学) 工程类 语言学 哲学 电压 电气工程 操作系统
作者
Jieneng Chen,Yongyi Lu,Qihang Yu,Xiangde Luo,Ehsan Adeli,Yan Wang,Le Lü,Alan Yuille,Yuyin Zhou
出处
期刊:Cornell University - arXiv 被引量:2135
标识
DOI:10.48550/arxiv.2102.04306
摘要

Medical image segmentation is an essential prerequisite for developing healthcare systems, especially for disease diagnosis and treatment planning. On various medical image segmentation tasks, the u-shaped architecture, also known as U-Net, has become the de-facto standard and achieved tremendous success. However, due to the intrinsic locality of convolution operations, U-Net generally demonstrates limitations in explicitly modeling long-range dependency. Transformers, designed for sequence-to-sequence prediction, have emerged as alternative architectures with innate global self-attention mechanisms, but can result in limited localization abilities due to insufficient low-level details. In this paper, we propose TransUNet, which merits both Transformers and U-Net, as a strong alternative for medical image segmentation. On one hand, the Transformer encodes tokenized image patches from a convolution neural network (CNN) feature map as the input sequence for extracting global contexts. On the other hand, the decoder upsamples the encoded features which are then combined with the high-resolution CNN feature maps to enable precise localization. We argue that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information. TransUNet achieves superior performances to various competing methods on different medical applications including multi-organ segmentation and cardiac segmentation. Code and models are available at https://github.com/Beckschen/TransUNet.
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
刚刚
1秒前
穗穗完成签到,获得积分20
2秒前
小博士328完成签到,获得积分10
2秒前
peace发布了新的文献求助20
2秒前
BOBO完成签到,获得积分10
2秒前
wanci应助平常的之槐采纳,获得10
3秒前
云瑾应助...采纳,获得10
3秒前
4秒前
云瑾应助迅哥采纳,获得10
5秒前
5秒前
surivial发布了新的文献求助10
6秒前
6秒前
公孙玲珑发布了新的文献求助10
6秒前
激昂的白凡应助聚乙二醇采纳,获得10
7秒前
星辰大海应助开朗的觅柔采纳,获得10
7秒前
7秒前
22发布了新的文献求助10
7秒前
科目三应助细心的语蓉采纳,获得10
8秒前
潇洒的妙芙完成签到,获得积分10
9秒前
感性的笑容完成签到,获得积分20
9秒前
9秒前
10秒前
Julia关注了科研通微信公众号
11秒前
Akim应助听eryi采纳,获得10
12秒前
Dou发布了新的文献求助10
12秒前
13秒前
bkagyin应助科学家采纳,获得10
13秒前
淳于笑翠完成签到,获得积分10
13秒前
pinging发布了新的文献求助10
13秒前
公孙玲珑完成签到,获得积分10
14秒前
希望天下0贩的0应助妖妖采纳,获得10
14秒前
14秒前
14秒前
无花果应助艾米采纳,获得10
14秒前
hhhzzz完成签到,获得积分10
16秒前
隐形曼青应助哲000采纳,获得10
16秒前
李爱国应助22采纳,获得10
16秒前
聪慧百合完成签到,获得积分10
17秒前
三号发布了新的文献求助10
17秒前
高分求助中
Evolution 10000
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
юрские динозавры восточного забайкалья 800
A new approach of magnetic circular dichroism to the electronic state analysis of intact photosynthetic pigments 500
Diagnostic immunohistochemistry : theranostic and genomic applications 6th Edition 500
Chen Hansheng: China’s Last Romantic Revolutionary 500
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 3148931
求助须知:如何正确求助?哪些是违规求助? 2799908
关于积分的说明 7837731
捐赠科研通 2457479
什么是DOI,文献DOI怎么找? 1307870
科研通“疑难数据库(出版商)”最低求助积分说明 628312
版权声明 601685