Self-supervised learning for multi-center magnetic resonance imaging harmonization without traveling phantoms

计算机科学 人工智能 图像配准 计算机视觉 忠诚 直方图 模式识别(心理学) 图像(数学) 电信
作者
Xiao Chang,Xin Cai,Yibo Dan,Yang Song,Qing Lu,Guang Yang,Shengdong Nie
出处
期刊:Physics in Medicine and Biology [IOP Publishing]
卷期号:67 (14): 145004-145004 被引量:4
标识
DOI:10.1088/1361-6560/ac7b66
摘要

Abstract Objective. With the progress of artificial intelligence (AI) in magnetic resonance imaging (MRI), large-scale multi-center MRI datasets have a great influence on diagnosis accuracy and model performance. However, multi-center images are highly variable due to the variety of scanners or scanning parameters in use, which has a negative effect on the generality of AI-based diagnosis models. To address this problem, we propose a self-supervised harmonization (SSH) method. Approach. Mapping the style of images between centers allows harmonization without traveling phantoms to be formalized as an unpaired image-to-image translation problem between two domains. The mapping is a two-stage transform, consisting of a modified cycle generative adversarial network (cycleGAN) for style transfer and a histogram matching module for structure fidelity. The proposed algorithm is demonstrated using female pelvic MRI images from two 3 T systems and compared with three state-of-the-art methods and one conventional method. In the absence of traveling phantoms, we evaluate harmonization from three perspectives: image fidelity, ability to remove inter-center differences, and influence on the downstream model. Main results. The improved image sharpness and structure fidelity are observed using the proposed harmonization pipeline. It largely decreases the number of features with a significant difference between two systems (from 64 to 45, lower than dualGAN: 57, cycleGAN: 59, ComBat: 64, and CLAHE: 54). In the downstream cervical cancer classification, it yields an area under the receiver operating characteristic curve of 0.894 (higher than dualGAN: 0.828, cycleGAN: 0.812, ComBat: 0.685, and CLAHE: 0.770). Significance. Our SSH method yields superior generality of downstream cervical cancer classification models by significantly decreasing the difference in radiomics features, and it achieves greater image fidelity.
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
小叶子发布了新的文献求助10
刚刚
1秒前
1秒前
光电很亮发布了新的文献求助10
2秒前
2秒前
2秒前
墩墩发布了新的文献求助10
3秒前
Ryan完成签到,获得积分10
3秒前
slb1319完成签到,获得积分10
3秒前
EEE完成签到,获得积分10
4秒前
小小完成签到,获得积分10
4秒前
愉快迎荷完成签到,获得积分10
4秒前
4秒前
满anna完成签到 ,获得积分10
4秒前
jin发布了新的文献求助80
4秒前
挤爆沙丁鱼完成签到,获得积分10
4秒前
5秒前
long完成签到 ,获得积分10
5秒前
5秒前
微末完成签到,获得积分10
6秒前
6秒前
pi发布了新的文献求助10
6秒前
林渊发布了新的文献求助10
6秒前
舒心胜发布了新的文献求助10
6秒前
8秒前
8秒前
erhan7发布了新的文献求助10
8秒前
顾矜应助yoyo采纳,获得10
8秒前
111完成签到,获得积分10
9秒前
一一完成签到,获得积分10
9秒前
Joyj99完成签到,获得积分10
9秒前
一丁点可爱完成签到,获得积分10
10秒前
赘婿应助iii采纳,获得30
10秒前
yiersan发布了新的文献求助10
11秒前
谷谷完成签到,获得积分10
11秒前
量子星尘发布了新的文献求助30
11秒前
11秒前
感动的刚发布了新的文献求助10
12秒前
12秒前
金鑫鑫完成签到,获得积分10
12秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Social Research Methods (4th Edition) by Maggie Walter (2019) 2390
A new approach to the extrapolation of accelerated life test data 1000
北师大毕业论文 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 390
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Robot-supported joining of reinforcement textiles with one-sided sewing heads 360
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 4009429
求助须知:如何正确求助?哪些是违规求助? 3549323
关于积分的说明 11301690
捐赠科研通 3283833
什么是DOI,文献DOI怎么找? 1810413
邀请新用户注册赠送积分活动 886275
科研通“疑难数据库(出版商)”最低求助积分说明 811301