MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation

计算机科学 稳健性(进化) 卷积神经网络 人工智能 分割 对抗制 图像分割 机器学习 水准点(测量) 领域(数学分析) 模式识别(心理学) 数据挖掘 基因 地理 化学 数学分析 大地测量学 生物化学 数学
作者
Chen Chen,Zeju Li,Chuying Ouyang,Matthew Sinclair,Wenjia Bai,Daniel Rueckert
出处
期刊:Lecture Notes in Computer Science 卷期号:: 151-161 被引量:11
标识
DOI:10.1007/978-3-031-16443-9_15
摘要

Convolutional neural networks (CNNs) have achieved remarkable segmentation accuracy on benchmark datasets where training and test sets are from the same domain, yet their performance can degrade significantly on unseen domains, which hinders the deployment of CNNs in many clinical scenarios. Most existing works improve model out-of-domain (OOD) robustness by collecting multi-domain datasets for training, which is expensive and may not always be feasible due to privacy and logistical issues. In this work, we focus on improving model robustness using a single-domain dataset only. We propose a novel data augmentation framework called MaxStyle, which maximizes the effectiveness of style augmentation for model OOD performance. It attaches an auxiliary style-augmented image decoder to a segmentation network for robust feature learning and data augmentation. Importantly, MaxStyle augments data with improved image style diversity and hardness, by expanding the style space with noise and searching for the worst-case style composition of latent features via adversarial training. With extensive experiments on multiple public cardiac and prostate MR datasets, we demonstrate that MaxStyle leads to significantly improved out-of-distribution robustness against unseen corruptions as well as common distribution shifts across multiple, different, unseen sites and unknown image sequences under both low- and high-training data settings. The code can be found at https://github.com/cherise215/MaxStyle .
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
zhui完成签到,获得积分10
刚刚
RESLR完成签到,获得积分10
1秒前
1秒前
1秒前
用户5063899发布了新的文献求助10
1秒前
3秒前
雨的痕迹完成签到,获得积分10
4秒前
Loik发布了新的文献求助10
4秒前
充电宝应助绛川采纳,获得10
4秒前
量子星尘发布了新的文献求助10
6秒前
6秒前
CAOHOU应助sue采纳,获得10
7秒前
7秒前
Loik完成签到,获得积分10
10秒前
10秒前
苗条梦玉发布了新的文献求助10
11秒前
11秒前
11秒前
16秒前
绛川发布了新的文献求助10
17秒前
momo发布了新的文献求助10
18秒前
搜集达人应助潘善若采纳,获得10
18秒前
yyer发布了新的文献求助10
19秒前
实心小墩墩完成签到,获得积分10
21秒前
26秒前
27秒前
香蕉觅云应助su采纳,获得10
27秒前
深情安青应助momo采纳,获得10
29秒前
29秒前
30秒前
可爱的函函应助hu采纳,获得10
32秒前
32秒前
33秒前
ABS发布了新的文献求助10
33秒前
34秒前
FashionBoy应助忘记时间采纳,获得30
35秒前
爆米花应助无情的匪采纳,获得10
36秒前
37秒前
刘寄奴发布了新的文献求助10
38秒前
su发布了新的文献求助10
40秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 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 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 3989297
求助须知:如何正确求助?哪些是违规求助? 3531418
关于积分的说明 11253893
捐赠科研通 3270097
什么是DOI,文献DOI怎么找? 1804884
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809158