3D Medical image segmentation using parallel transformers

计算机科学 变压器 人工智能 分割 编码器 卷积神经网络 图像分割 模式识别(心理学) 深度学习 计算机视觉 工程类 操作系统 电气工程 电压
作者
Qingsen Yan,Shengqiang Liu,Songhua Xu,Caixia Dong,Zongfang Li,Qinfeng Shi,Yanning Zhang,Duwei Dai
出处
期刊:Pattern Recognition [Elsevier BV]
卷期号:138: 109432-109432 被引量:58
标识
DOI:10.1016/j.patcog.2023.109432
摘要

Most recent 3D medical image segmentation methods adopt convolutional neural networks (CNNs) that rely on deep feature representation and achieve adequate performance. However, due to the convolutional architectures having limited receptive fields, they cannot explicitly model the long-range dependencies in the medical image. Recently, Transformer can benefit from global dependencies using self-attention mechanisms and learn highly expressive representations. Some works were designed based on the Transformers, but the existing Transformers suffer from extreme computational and memories, and they cannot take full advantage of the powerful feature representations in 3D medical image segmentation. In this paper, we aim to connect the different resolution streams in parallel and propose a novel network, named Transformer based High Resolution Network (TransHRNet), with an Effective Transformer (EffTrans) block, which has sufficient feature representation even at high feature resolutions. Given a 3D image, the encoder first utilizes CNN to extract the feature representations to capture the local information, and then the different feature maps are reshaped elaborately for tokens that are fed into each Transformer stream in parallel to learn the global information and repeatedly exchange the information across streams. Unfortunately, the proposed framework based on the standard Transformer needs a huge amount of computation, thus we introduce a deep and effective Transformer to deliver better performance with fewer parameters. The proposed TransHRNet is evaluated on the Multi-Atlas Labeling Beyond the Cranial Vault (BCV) dataset that consists of 11 major human organs and the Medical Segmentation Decathlon (MSD) dataset for brain tumor and spleen segmentation tasks. Experimental results show that it performs better than the convolutional and other related Transformer-based methods on the 3D multi-organ segmentation tasks. Code is available at https://github.com/duweidai/TransHRNet.
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
乖猫要努力应助落后翠柏采纳,获得10
1秒前
3秒前
澡雪发布了新的文献求助10
3秒前
4秒前
5秒前
6秒前
Qian完成签到,获得积分10
6秒前
onlyan发布了新的文献求助10
7秒前
wjx关闭了wjx文献求助
9秒前
victorchen发布了新的文献求助10
9秒前
9秒前
小景毕业发布了新的文献求助10
10秒前
Yorshka完成签到,获得积分10
11秒前
13秒前
巫马夜安完成签到,获得积分10
14秒前
可爱的函函应助123采纳,获得10
14秒前
14秒前
wjx关闭了wjx文献求助
15秒前
15秒前
Bystander完成签到 ,获得积分10
16秒前
shine发布了新的文献求助10
16秒前
NexusExplorer应助复杂语山采纳,获得10
16秒前
yxy发布了新的文献求助10
16秒前
19秒前
WD发布了新的文献求助10
19秒前
wjx关闭了wjx文献求助
19秒前
留白完成签到 ,获得积分10
19秒前
小景毕业完成签到,获得积分10
20秒前
bkagyin应助lemon采纳,获得10
20秒前
卢哲发布了新的文献求助10
20秒前
华仔应助泡泡糖与一世安采纳,获得30
20秒前
曾经曼梅完成签到,获得积分10
23秒前
科研通AI2S应助Kollia采纳,获得30
23秒前
乐乐应助onlyan采纳,获得10
24秒前
24秒前
wjx关闭了wjx文献求助
24秒前
最短的咒发布了新的文献求助10
25秒前
25秒前
26秒前
池鱼发布了新的文献求助150
28秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 3975458
求助须知:如何正确求助?哪些是违规求助? 3519866
关于积分的说明 11199996
捐赠科研通 3256213
什么是DOI,文献DOI怎么找? 1798133
邀请新用户注册赠送积分活动 877386
科研通“疑难数据库(出版商)”最低求助积分说明 806305