An effective CNN and Transformer complementary network for medical image segmentation

计算机科学 卷积神经网络 分割 变压器 人工智能 编码器 图像分割 模式识别(心理学) 计算机视觉 工程类 电压 操作系统 电气工程
作者
Feiniu Yuan,Zhengxiao Zhang,Zhijun Fang
出处
期刊:Pattern Recognition [Elsevier BV]
卷期号:136: 109228-109228 被引量:295
标识
DOI:10.1016/j.patcog.2022.109228
摘要

The Transformer network was originally proposed for natural language processing. Due to its powerful representation ability for long-range dependency, it has been extended for vision tasks in recent years. To fully utilize the advantages of Transformers and Convolutional Neural Networks (CNNs), we propose a CNN and Transformer Complementary Network (CTCNet) for medical image segmentation. We first design two encoders by Swin Transformers and Residual CNNs to produce complementary features in Transformer and CNN domains, respectively. Then we cross-wisely concatenate these complementary features to propose a Cross-domain Fusion Block (CFB) for effectively blending them. In addition, we compute the correlation between features from the CNN and Transformer domains, and apply channel attention to the self-attention features by Transformers for capturing dual attention information. We incorporate cross-domain fusion, feature correlation and dual attention together to propose a Feature Complementary Module (FCM) for improving the representation ability of features. Finally, we design a Swin Transformer decoder to further improve the representation ability of long-range dependencies, and propose to use skip connections between the Transformer decoded features and the complementary features for extracting spatial details, contextual semantics and long-range information. Skip connections are performed in different levels for enhancing multi-scale invariance. Experimental results show that our CTCNet significantly surpasses the state-of-the-art image segmentation models based on CNNs, Transformers, and even Transformer and CNN combined models designed for medical image segmentation. It achieves superior performance on different medical applications, including multi-organ segmentation and cardiac segmentation.
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
刚刚
SYY完成签到,获得积分10
1秒前
繁荣的戾发布了新的文献求助10
1秒前
primrose完成签到 ,获得积分10
1秒前
2秒前
曾国强发布了新的文献求助10
4秒前
Akim应助岁月轮回采纳,获得10
4秒前
4秒前
5秒前
jessica发布了新的文献求助10
5秒前
baolongzhan完成签到,获得积分10
5秒前
5秒前
沙非娅发布了新的文献求助10
6秒前
lv发布了新的文献求助10
7秒前
曹志毅发布了新的文献求助20
7秒前
半分青完成签到,获得积分10
8秒前
axiao发布了新的文献求助10
9秒前
9秒前
怡崽发布了新的文献求助10
10秒前
坚强似狮完成签到,获得积分10
10秒前
乐乐应助起风了采纳,获得10
10秒前
11秒前
11秒前
刻苦的煎蛋完成签到,获得积分10
11秒前
曾国强完成签到,获得积分10
13秒前
瑶桑完成签到,获得积分10
14秒前
15秒前
冷漠的布丁完成签到,获得积分10
15秒前
15秒前
岁月轮回发布了新的文献求助10
16秒前
月光入梦完成签到 ,获得积分10
17秒前
拖拖沓沓ttt完成签到,获得积分20
17秒前
19秒前
20秒前
咩咩完成签到,获得积分10
21秒前
Owen应助sure采纳,获得10
21秒前
jessica完成签到,获得积分10
22秒前
Owen应助拖拖沓沓ttt采纳,获得10
22秒前
24秒前
赘婿应助DUANYALI采纳,获得10
26秒前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
Production Logging: Theoretical and Interpretive Elements 3000
CRC Handbook of Chemistry and Physics 104th edition 1000
Izeltabart tapatansine - AdisInsight 600
Introduction to Comparative Public Administration Administrative Systems and Reforms in Europe, Third Edition 3rd edition 500
Distinct Aggregation Behaviors and Rheological Responses of Two Terminally Functionalized Polyisoprenes with Different Quadruple Hydrogen Bonding Motifs 450
THE STRUCTURES OF 'SHR' AND 'YOU' IN MANDARIN CHINESE 320
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3761949
求助须知:如何正确求助?哪些是违规求助? 3305642
关于积分的说明 10135083
捐赠科研通 3019747
什么是DOI,文献DOI怎么找? 1658374
邀请新用户注册赠送积分活动 792030
科研通“疑难数据库(出版商)”最低求助积分说明 754783