MS-TCNet: An effective Transformer–CNN combined network using multi-scale feature learning for 3D medical image segmentation

计算机科学 人工智能 卷积神经网络 尺度空间分割 分割 特征(语言学) 基于分割的对象分类 稳健性(进化) 编码器 模式识别(心理学) 深度学习 棱锥(几何) 特征学习 图像分割 计算机视觉 数学 操作系统 基因 几何学 化学 生物化学 语言学 哲学
作者
Yu Ao,Weili Shi,Bai Ji,Yu Miao,Wei He,Zhengang Jiang
出处
期刊:Computers in Biology and Medicine [Elsevier BV]
卷期号:170: 108057-108057 被引量:54
标识
DOI:10.1016/j.compbiomed.2024.108057
摘要

Medical image segmentation is a fundamental research problem in the field of medical image processing. Recently, the Transformer have achieved highly competitive performance in computer vision. Therefore, many methods combining Transformer with convolutional neural networks (CNNs) have emerged for segmenting medical images. However, these methods cannot effectively capture the multi-scale features in medical images, even though texture and contextual information embedded in the multi-scale features are extremely beneficial for segmentation. To alleviate this limitation, we propose a novel Transformer–CNN combined network using multi-scale feature learning for three-dimensional (3D) medical image segmentation, which is called MS-TCNet. The proposed model utilizes a shunted Transformer and CNN to construct an encoder and pyramid decoder, allowing six different scale levels of feature learning. It captures multi-scale features with refinement at each scale level. Additionally, we propose a novel lightweight multi-scale feature fusion (MSFF) module that can fully fuse the different-scale semantic features generated by the pyramid decoder for each segmentation class, resulting in a more accurate segmentation output. We conducted experiments on three widely used 3D medical image segmentation datasets. The experimental results indicated that our method outperformed state-of-the-art medical image segmentation methods, suggesting its effectiveness, robustness, and superiority. Meanwhile, our model has a smaller number of parameters and lower computational complexity than conventional 3D segmentation networks. The results confirmed that the model is capable of effective multi-scale feature learning and that the learned multi-scale features are useful for improving segmentation performance. We open-sourced our code, which can be found at https://github.com/AustinYuAo/MS-TCNet.
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
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
英俊的铭的应助被linlianhao采纳,获得10
刚刚
小马甲的应助被小懿采纳,获得10
1秒前
1秒前
9465426发布了新的文献求助30
1秒前
iceanbecky发布了新的文献求助10
2秒前
打打的应助被风清扬采纳,获得10
2秒前
任性玫瑰发布了新的文献求助10
2秒前
hmhu完成签到,获得积分10
3秒前
3秒前
欧耶完成签到,获得积分20
3秒前
3秒前
回望发布了新的文献求助10
3秒前
xiaofeixia完成签到 ,获得积分10
4秒前
answer答案完成签到,获得积分10
4秒前
稳稳完成签到,获得积分10
5秒前
56455完成签到,获得积分10
6秒前
iNk的应助被Fantaro采纳,获得10
6秒前
LJH发布了新的文献求助10
6秒前
Qiao发布了新的文献求助10
6秒前
keibinn完成签到 ,获得积分10
7秒前
额特别发布了新的文献求助10
7秒前
8秒前
8秒前
8秒前
David发布了新的文献求助10
8秒前
巧克力发布了新的文献求助10
9秒前
9秒前
DW的应助被细心的凡蕾采纳,获得10
9秒前
NexusExplorer的应助被别梦寒采纳,获得10
10秒前
清秀语蝶的应助被zsy采纳,获得10
10秒前
NexusExplorer的应助被Www采纳,获得10
11秒前
脑洞疼的应助被111采纳,获得10
11秒前
任性玫瑰完成签到,获得积分10
12秒前
小马甲的应助被欧耶采纳,获得10
12秒前
马莱板凳人完成签到 ,获得积分20
13秒前
Army616完成签到,获得积分10
14秒前
hhh发布了新的文献求助10
14秒前
jiejie发布了新的文献求助10
15秒前
乐乐的应助被自然的含蕾采纳,获得10
15秒前
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8177849
求助须知:如何正确求助?哪些是违规求助? 9568641
关于积分的说明 21800145
捐赠科研通 7772473
什么是DOI,文献DOI怎么找? 3432537
关于科研通互助平台的介绍 2556720
邀请新用户注册赠送积分活动 2478067