高级检索
当前位置: 首页 > 详情页

Co-Correcting: Noise-Tolerant Medical Image Classification via Mutual Label Correction

文献详情

资源类型:
WOS体系:

收录情况: ◇ SCIE ◇ EI

单位: [1]College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China [2]Department of Ophthalmology, China-Japan Friendship Hospital, Beijing 100029, China
出处:
ISSN:

关键词: Biomedical imaging Noise measurement Deep learning Training Task analysis Reliability Probabilistic logic Mutual learning label probability estimation annotation correction curriculum medical image classification

摘要:
With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming, collecting labels from crowd-sourcing suffers from the noises which may degenerate the accuracy of classifiers. Therefore, approaches that can effectively handle label noises are highly desired. Unfortunately, recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image. To fill the gap, this paper proposes a noise-tolerant medical image classification framework named Co-Correcting, which significantly improves classification accuracy and obtains more accurate labels through dual-network mutual learning, label probability estimation, and curriculum label correcting. On two representative medical image datasets and the MNIST dataset, we test six latest Learning-with-Noisy-Labels methods and conduct comparative studies. The experiments show that Co-Correcting achieves the best accuracy and generalization under different noise ratios in various tasks. Our project can be found at: https://github.com/JiarunLiu/Co-Correcting.

基金:
语种:
被引次数:
WOS:
中科院(CAS)分区:
出版当年[2020]版:
大类 | 1 区 医学
小类 | 1 区 计算机:跨学科应用 1 区 核医学 2 区 工程:生物医学 2 区 工程:电子与电气 2 区 成像科学与照相技术
最新[2025]版:
大类 | 1 区 医学
小类 | 1 区 计算机:跨学科应用 1 区 工程:生物医学 1 区 工程:电子与电气 1 区 成像科学与照相技术 1 区 核医学
JCR分区:
出版当年[2019]版:
Q1 ENGINEERING, ELECTRICAL & ELECTRONIC Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS Q1 ENGINEERING, BIOMEDICAL Q1 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
最新[2023]版:
Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS Q1 ENGINEERING, BIOMEDICAL Q1 ENGINEERING, ELECTRICAL & ELECTRONIC Q1 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

影响因子: 最新[2023版] 最新五年平均[2021-2025] 出版当年[2019版] 出版当年五年平均[2015-2019] 出版前一年[2018版] 出版后一年[2020版]

第一作者:
第一作者单位: [1]College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
通讯作者:
推荐引用方式(GB/T 7714):
APA:
MLA:

资源点击量:1320 今日访问量:0 总访问量:817 更新日期:2025-05-01 建议使用谷歌、火狐浏览器 常见问题

版权所有:重庆聚合科技有限公司 渝ICP备12007440号-3 地址:重庆市两江新区泰山大道西段8号坤恩国际商务中心16层(401121)