Kurtosis Transformation for Multi-Source Domain Generalization Segmentation of OCT Images From Multi-Manufacturers' Devices

峰度 一般化 分割 转化(遗传学) 计算机科学 人工智能 图像分割 领域(数学分析) 计算机视觉 模式识别(心理学) 数学 化学 基因 生物化学 数学分析 统计
作者
Feiyu Sun,Ling Gao,Haoyu Chen,Bei Tian,Tao Peng,Weifang Zhu,Fei Shi,Ronghan Wu,Xinjian Chen,Dehui Xiang
出处
期刊:IEEE Transactions on Biomedical Engineering [Institute of Electrical and Electronics Engineers]
卷期号:73 (1): 90-102 被引量:1
标识
DOI:10.1109/tbme.2025.3577271
摘要

OBJECTIVE: Optical coherence tomography (OCT) images can visualize retinal layers and fundus lesions. Retinal structure segmentation is of great significance in early lesion detection and treatment guidance. However, devices from different OCT manufacturers are largely different from each other, which often leads to degraded results in image segmentation. METHODS: To enrich the diversity of multi-source domains in intensity distributions and image contrasts of multi-manufacturers' OCT images, a kurtosis transformation method is proposed to generate a kurtosis-transformed image. To make the generated potential T-styles as different as possible from the source domain styles, a mean style contrastive learning method is proposed to maximize the distance between style features of a kurtosis-transformed image and multi-source domain images. To improve the diversity and independence of potential T-styles in a high-level orthogonal space, variance style orthogonalization is proposed to impose an orthogonal constraint on the reparametrized variance styles. Mean style features and variance style features are combined to modulate an input image for the training of the segmentation network. RESULTS: Comprehensive experiments have been performed on two OCT image datasets. Compared to state-of-the-art methods, the proposed method can achieve better segmentation. CONCLUSION: The proposed segmentation method can be trained on labeled OCT images from multi-manufacturers' devices and can be tested on unseen manufacturer's device, and has good domain generalization performance in both retinal layer and lesions segmentation tasks. SIGNIFICANCE: The proposed method can be used in routine clinical settings, when OCT images from multi-manufacturers' devices are available.
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
MONNA完成签到 ,获得积分10
刚刚
suzhenyue的应助被科研通管家采纳,获得10
1秒前
领导范儿的应助被科研通管家采纳,获得10
1秒前
mark完成签到,获得积分10
1秒前
molihuakai的应助被科研通管家采纳,获得10
1秒前
Lucas的应助被科研通管家采纳,获得10
1秒前
安全平静完成签到,获得积分10
1秒前
奔跑的应助被科研通管家采纳,获得10
1秒前
SciGPT的应助被科研通管家采纳,获得10
2秒前
不安蜜蜂完成签到,获得积分10
2秒前
suzhenyue的应助被科研通管家采纳,获得10
2秒前
田様的应助被科研通管家采纳,获得10
2秒前
爆米花的应助被瘦瘦滢采纳,获得10
2秒前
思源的应助被科研通管家采纳,获得10
2秒前
cdercder的应助被科研通管家采纳,获得10
2秒前
香蕉觅云的应助被科研通管家采纳,获得10
2秒前
2秒前
2秒前
情怀的应助被科研通管家采纳,获得10
3秒前
林大侠完成签到,获得积分10
3秒前
健忘冷风完成签到,获得积分10
3秒前
今后的应助被科研通管家采纳,获得10
3秒前
颖颖完成签到,获得积分10
3秒前
彭永彬完成签到 ,获得积分10
3秒前
Maestro_S的应助被科研通管家采纳,获得10
3秒前
3秒前
Nobody完成签到,获得积分10
3秒前
fanyy完成签到,获得积分10
3秒前
3秒前
顺利妙松完成签到,获得积分10
3秒前
isabellae发布了新的文献求助10
4秒前
格调完成签到,获得积分10
4秒前
天天向上的应助被时尚的从凝采纳,获得50
5秒前
积极的千琴完成签到,获得积分10
5秒前
水寒完成签到,获得积分10
5秒前
温柔问梅完成签到,获得积分10
5秒前
YYYYY完成签到,获得积分10
5秒前
wa完成签到 ,获得积分10
6秒前
酪酥爱大米完成签到,获得积分10
6秒前
专注的星星完成签到,获得积分10
6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
The World Atlas of Wine 9th edition 1000
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
Social Psychology in the Real World 600
八旗制度の研究 600
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 8180135
求助须知:如何正确求助?哪些是违规求助? 9570290
关于积分的说明 21809391
捐赠科研通 7776237
什么是DOI,文献DOI怎么找? 3433266
关于科研通互助平台的介绍 2557465
邀请新用户注册赠送积分活动 2479039