发表机构
Nagoya University; Graduate School of Informatics, Nagoya University; Graduate School of Science and Technology, Nara Institute of Science and Technology; Research Center for Medical Bigdata, National Institute of Informatics; Keio University School of Medicine; Juntendo University（名古屋大学; 名古屋大学信息学研究科; 奈良先端科学技术大学院大学科学技术研究科; 信息学研究所医疗大数据研究中心; 庆应义塾大学医学院; 顺天堂大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对COVID-19患者激增导致的医疗人力短缺问题，本文提出由3D CNN与3D MLP-Mixer组成的混合模型，在含1205份CT影像的数据集上取得79.5%的分类准确率，优于传统3D CNN模型。
AI 中文摘要
本文提出一种使用改进3D MLP-Mixer的胸部CT影像COVID-19自动分类方法。新型冠状病毒肺炎（COVID-19）在全球传播，造成大量感染者与死亡病例；COVID-19患者数量骤增导致医疗机构人力短缺，计算机辅助诊断（CAD）系统可提供快速、定量的诊断结果，助力高效诊断流程、缓解人力短缺。在COVID-19等病毒性肺炎的影像诊断中，局部与全局图像特征均至关重要，因病毒性肺炎会在肺部大范围引发磨玻璃影与实变。本文提出用于COVID-19诊断辅助的胸部CT影像自动分类方法：MLP-Mixer是一种采用类视觉Transformer架构的图像分类新方法，可同时利用局部与全局图像特征进行分类；为对3D CT体积进行分类，本文开发了由3D卷积神经网络（CNN）与3D MLP-Mixer组成的混合分类模型。该方法在包含1205份CT体积的数据集上评估分类准确率，获得79.5%的分类准确率，高于仅由3D CNN层与简单MLP层构成的传统3D CNN模型的准确率。
英文摘要
This paper proposes an automated classification method of COVID-19 chest CT volumes using improved 3D MLP-Mixer. Novel coronavirus disease 2019 (COVID-19) spreads over the world, causing a large number of infected patients and deaths. Sudden increase in the number of COVID-19 patients causes a manpower shortage in medical institutions. Computer-aided diagnosis (CAD) system provides quick and quantitative diagnosis results. CAD system for COVID-19 enables efficient diagnosis workflow and contributes to reduce such manpower shortage. In image-based diagnosis of viral pneumonia cases including COVID-19, both local and global image features are important because viral pneumonia cause many ground glass opacities and consolidations in large areas in the lung. This paper proposes an automated classification method of chest CT volumes for COVID-19 diagnosis assistance. MLP-Mixer is a recent method of image classification using Vision Transformer-like architecture. It performs classification using both local and global image features. To classify 3D CT volumes, we developed a hybrid classification model that consists of both a 3D convolutional neural network (CNN) and a 3D version of the MLP-Mixer. Classification accuracy of the proposed method was evaluated using a dataset that contains 1205 CT volumes and obtained 79.5% of classification accuracy. The accuracy was higher than that of conventional 3D CNN models consists of 3D CNN layers and simple MLP layers.
CommentsAccepted as a poster presentation in SPIE Medical Imaging 2023
Journal refProceedings of SPIE Medical Imaging 2023, Computer-Aided Diagnosis, Vol. 12465
