已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整的填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI

计算机科学 乳房磁振造影 人工智能 分割 图像分割 乳腺肿瘤 计算机视觉 乳腺摄影术 乳腺癌 医学 癌症 内科学
作者
Lei Zhou,Yuzhong Zhang,Jiadong Zhang,Xuejun Qian,Chen Gong,Kun Sun,Zhongxiang Ding,Xing Wang,Zhenhui Li,Zaiyi Liu,Dinggang Shen
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tmi.2024.3435450
摘要

Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for identifying the presence of breast disease. However, accurate segmentation of breast tumor is a challenging task, often necessitating the development of complex networks. To strike an optimal trade-off between computational costs and segmentation performance, we propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. Specifically, the hybrid network consists of a encoder-decoder architecture by stacking convolution and decovolution layers. Effective 3D transformer layers are then implemented after the encoder subnetworks, to capture global dependencies between the bottleneck features. To improve the efficiency of hybrid network, two parallel encoder subnetworks are designed for the decoder and the transformer layers, respectively. To further enhance the discriminative capability of hybrid network, a prototype learning guided prediction module is proposed, where the category-specified prototypical features are calculated through on-line clustering. All learned prototypical features are finally combined with the features from decoder for tumor mask prediction. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network achieves superior performance than the state-of-the-art (SOTA) methods, while maintaining balance between segmentation accuracy and computation cost. Moreover, we demonstrate that automatically generated tumor masks can be effectively applied to identify HER2-positive subtype from HER2-negative subtype with the similar accuracy to the analysis based on manual tumor segmentation. The source code is available at https://github.com/ZhouL-lab/PLHN.
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
典雅的蜡烛完成签到,获得积分10
刚刚
專注完美近乎苛求完成签到 ,获得积分10
1秒前
3秒前
NexusExplorer应助科研通管家采纳,获得50
5秒前
共享精神应助科研通管家采纳,获得10
5秒前
tianshanfeihe完成签到 ,获得积分10
5秒前
星辰大海应助科研通管家采纳,获得10
5秒前
Lucas应助科研通管家采纳,获得10
5秒前
科研通AI5应助科研通管家采纳,获得10
5秒前
5秒前
Augenstern完成签到 ,获得积分10
5秒前
洋洋完成签到 ,获得积分10
6秒前
Yummy完成签到,获得积分10
6秒前
WangJL完成签到 ,获得积分10
7秒前
落落完成签到 ,获得积分0
9秒前
科研通AI5应助典雅的蜡烛采纳,获得10
10秒前
在水一方应助Yummy采纳,获得10
10秒前
威武皮带完成签到,获得积分10
12秒前
wang1完成签到 ,获得积分10
14秒前
king完成签到,获得积分10
15秒前
爆米花完成签到,获得积分10
15秒前
only完成签到 ,获得积分10
17秒前
ThreeAct6完成签到,获得积分10
18秒前
king发布了新的文献求助10
20秒前
jacob258发布了新的文献求助10
23秒前
wang完成签到 ,获得积分10
26秒前
Wang_JN完成签到 ,获得积分10
26秒前
所所应助禹卓采纳,获得10
26秒前
vippp完成签到 ,获得积分10
27秒前
人文完成签到 ,获得积分10
27秒前
28秒前
yillin完成签到 ,获得积分10
30秒前
struggling2026完成签到 ,获得积分10
30秒前
Leif完成签到 ,获得积分0
31秒前
烟喜发布了新的文献求助10
31秒前
孔嘉康完成签到,获得积分10
33秒前
lx完成签到,获得积分20
33秒前
肚子幽伤完成签到 ,获得积分10
34秒前
天天快乐应助辰的小猫采纳,获得10
38秒前
烟喜完成签到,获得积分10
39秒前
高分求助中
Les Mantodea de Guyane Insecta, Polyneoptera 2500
Mobilization, center-periphery structures and nation-building 600
Introduction to Strong Mixing Conditions Volumes 1-3 500
Technologies supporting mass customization of apparel: A pilot project 450
China—Art—Modernity: A Critical Introduction to Chinese Visual Expression from the Beginning of the Twentieth Century to the Present Day 430
Multichannel rotary joints-How they work 400
A Field Guide to the Amphibians and Reptiles of Madagascar - Frank Glaw and Miguel Vences - 3rd Edition 400
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 3795454
求助须知:如何正确求助?哪些是违规求助? 3340458
关于积分的说明 10300316
捐赠科研通 3057032
什么是DOI,文献DOI怎么找? 1677356
邀请新用户注册赠送积分活动 805385
科研通“疑难数据库(出版商)”最低求助积分说明 762491