医学图像数据集扩充方法研究进展  

Research progress on medical image dataset expansion methods

作　　者：陈英[1] 林洪平 张伟[1] 冯龙锋 郑铖 周滔辉 易珍[2] 刘岚[2] CHEN Ying;LIN Hongping;ZHANG Wei;FENG Longfeng;ZHENG Cheng;ZHOU Taohui;YI Zhen;LIU Lan(School of Software,Nanchang Hangkong University,Nanchang 330063,P.R.China;Department of Medical Imaging,Jiangxi Cancer Hospital,Nanchang330029,P.R.China)

机构地区：[1]南昌航空大学、软件学院,南昌330063 [2]江西省肿瘤医院、医学影像科,南昌330029

出　　处：《生物医学工程学杂志》2023年第1期185-192,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(61762067);江西省自然科学基金资助项目(20202BABL202029)。

摘　　要：计算机辅助诊断(CAD)系统对现代医学诊疗体系具有非常重要的作用,但其性能受训练样本的限制。而训练样本受成像成本、标记成本和涉及患者隐私等因素的影响,导致训练图像多样性不足且难以获取。因此,如何高效且以较低成本扩充现有医学图像数据集成为研究的热点。本文结合国内外的相关文献,对医学图像数据集扩充方法的研究进展进行综述,首先对比分析基于几何变换和基于生成对抗网络的扩充方法,其次重点介绍基于生成对抗网络扩充方法的改进及其适用场景,最后讨论医学图像数据集扩充领域的一些亟待解决的问题并对其未来发展趋势进行展望。Computer-aided diagnosis(CAD) systems play a very important role in modern medical diagnosis and treatment systems, but their performance is limited by training samples. However, the training samples are affected by factors such as imaging cost, labeling cost and involving patient privacy, resulting in insufficient diversity of training images and difficulty in data obtaining. Therefore, how to efficiently and cost-effectively augment existing medical image datasets has become a research hotspot. In this paper, the research progress on medical image dataset expansion methods is reviewed based on relevant literatures at home and abroad. First, the expansion methods based on geometric transformation and generative adversarial networks are compared and analyzed, and then improvement of the augmentation methods based on generative adversarial networks are emphasized. Finally, some urgent problems in the field of medical image dataset expansion are discussed and the future development trend is prospected.

关 键 词：医学图像扩充 计算机辅助诊断系统 几何变换 生成对抗网络 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]