首页|基于对比学习MocoV2的COVID-19图像分类

基于对比学习MocoV2的COVID-19图像分类

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
肺炎是一种常见多发感染性疾病,老年人和免疫力较弱者容易感染,尽早发现有助于后期治疗.肺部病变的位置、密度和清晰度等因素会影响肺炎图像分类的准确性.随着深度学习的发展,卷积神经网络被广泛应用于医学图像分类任务中,然而网络的学习能力依赖训练样本的数量和标签.针对电子计算机断层扫描(Computed Tomography,CT)的肺炎图像分类研究,提出一种基于自监督对比学习的网络模型(MCLSE),可以从无标记的数据中学习特征,提高网络模型的准确率.本文模型(MCLSE)首先设计辅助任务,从无标记的图像中挖掘表征完成预训练,提高模型在向量空间中学习数据映射关系的能力.其次,使用卷积神经网络提取特征,为了有效捕获更高层次的特征信息选择SENet网络改进分类模型,建模特征通道的相关性.最后,用训练好的权重加载改进后的分类模型中,下游任务中使用标记数据再次训练网络.在公开数据集SARS-CoV-2 CT和CT Scans for COVID-19 Classification上进行实验,实验结果表明MCLSE对整体样本分类的准确率分别达到99.19%和99.75%,较主流模型有很大提升.
Image Classification of COVID-19 Based on Contrast Learning MocoV2
Pneumonia is a common multi-infectious disease that predisposes the elderly and those with weakened immune sys-tems to infection,and early detection can help with later treatment.Factors such as the location,density and clarity of lung le-sions can affect the accuracy of pneumonia image classification.With the development of deep learning,convolutional neural net-work is widely used in medical image classification tasks,however,the learning ability of the network depends on the number of training samples and labels.Aiming at the classification of pneumonia images in computed tomography(CT),a network model based on self-supervised comparative learning(MCLSE)is proposed,which can learn features from unmarked data and improve the accuracy of the network model.Firsly,auxiliary tasks were designed to mine representations from unmarked images to com-plete pre-training,improving the ability of the model to learn data mapping relationships in vector space.Secondly,the convolu-tional neural network is used to extract features.In order to effectively capture higher level feature information,the compression excitation network is selected to improve the classification model and the correlation between the feature channels is modeled.Fi-nally,the trained weights are loaded into the improved classification model,and the network is trained again with marked data in the downstream task.Experiments were carried out on open data sets,SARS-CoV-2 CT and CT Scan for COVID-19 Classifica-tion.The results show that the accuracy of the MCLSE model in this paper for the overall sample classification reached 99.19%and 99.75%,respectively,which was greatly improved compared with the mainstream model.

COVID-19 imagemedical image classificationconvolutional neural networkself-supervised learningcontras-tive learning

许跃雯、李明、李莉

展开 >

重庆师范大学计算机与信息科学学院,重庆 401331

西南大学计算机与信息科学学院,重庆 400715

COVID-19图像 医学图像分类 卷积神经网络 自监督学习 对比学习

国家自然科学基金资助项目国家自然科学基金资助项目重庆市科委重点项目重庆市教委项目重庆市研究生教改重点项目

6187705161170192cstc2017zdcyzdyf0366113143yjg182022

2024

10.3969/j.issn.1006-2475.2024.02.013

计算机与现代化
江西省计算机学会 江西省计算技术研究所

计算机与现代化

CSTPCD
影响因子：0.472
ISSN：1006-2475
年,卷(期)：2024.(2)
  • 27