医学图像数据增强技术的研究现状与进展

Abstract
Figure/Table
References (26)
Related Citation (1)

Download: PDF (0 KB) HTML (43 KB)
Export: BibTeX | EndNote (RIS)

Abstract Artificial intelligence-assisted medical image recognition diagnosis and treatment system has been used extensively. However, it is difficult to collect enough data to train the model under the current medical environment and social background. By data augmentation technology on processing existed samples, shrotage of data can be greatly eased. This article briefly summarized the common image augmentation techniques used in recent years. According to the number of samples processed, the existing data augmentation techniques are divided into two categories: singlesample data augmentation and multi-sample data augmentation. The former is further divided into pixel-level processing and overall horizontal geometric processing according to the different processing levels; while the latter mainly introduces the object of operation in the entire sample set represented by synthetic minority oversampling technique(SMOTE) algorithm and generative adversarial networks (GAN), and solves the imbalance by adjusting the sampling ratio. Additionally, this article also analyzed the advantages and disadvantages of each method, and summarized the performance and improvement of the above algorithms in recent years to provide new ideas for related practitioners.

Key words： Artificial intelligence Data augmentation Synthetic minority oversampling technique Generative adversarial networks

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Tian-ren
	LI Yi-ning
	WANG Hong-yi
	KANG Jian
	ZHAO Shuang
	LIU An

Cite this article:

WANG Tian-ren,LI Yi-ning,WANG Hong-yi, et al. Current status and research progress on medical image data augmentation technology[J]. 中国当代医药, 2021, 28(3): 34-37转44.

URL:

http://dangdaiyiyao.com/EN/ OR http://dangdaiyiyao.com/EN/Y2021/V28/I3/34

[14]	van der Walt S，Schnberger JL，Nunez-Iglesias J，et al.scikit-image：image processing in Python[J].Peer J，2014，2：e453.
[15]	Fotouhi S，Asadi S，Kattan MW.A comprehensive data level analysis for cancer diagnosis on imbalanced data[J].J Biomed Inform，2019，90：103 089.
[16]	Elreedy D，Atiya AF.A Comprehensive Analysis of Synthetic Minority Oversampling Technique（SMOTE）for handling class imbalance[J].Inform Sci，2019，505：32-64.
[1]	Schwendicke F，Golla T，Dreher M，et al.Convolutional neural networks for dental image diagnostics：A scoping review[J].J Dent，2019，91：103 226.
[2]	Kasinathan G，Jayakumara S，Gandomi AH，et al.Automated 3-D lung tumor detection and classification by an active contour model and CNN classifier[J].Expert Syst Appl，2019，134：112-119.
[3]	Gao F，Wu T，Li J，et al.SD-CNN：A shallow-deep CNN for improved breast cancer diagnosis[J].Comput Med Imaging Graph，2018，70：53-62.
[4]	Liu X，Hou F，Qin H，et al.Multi-view multi-scale CNNs for lung nodule type classification from CT images[J].Pattern Recognit，2018，77：262-275.
[5]	Gu J，Wang Z，Kuen J，et al.Recent advances in convolutional neural networks[J].Pattern Recognit，2018，77：354-377.
[6]	Sajjad M，Khan S，Muhammad K，et al.Multi-grade brain tumor classification using deep CNN with extensive data augmentation[J].J Comput Sci，2019，30：174-182.
[7]	Noguchi S，Nishio M，Yakami M，et al.Bone segmentation on whole-body CT using convolutional neural network with novel data augmentation techniques[J].Comput Biol Med，2020，121：103 767.
[8]	池凯凯，蔡荣辉，丁维龙，等.基于深度学习的智能骨龄评估[J].计算机科学，2019，46（S2）：89-93.
[9]	Krell MM，Su Kyoung Kim.Rotational data augmentation for electroencephalographic data[J].Annu Int Conf IEEE Eng Med Biol Soc，2017，2017：471-474.
[10]	彭礼烨，梁倍源，黄思钊，等.基于数据增强和Mask RCNN 模型的肤质自动识别方法与流程[P].专利申请号：201910806679.6
[11]	向俊，卢宏涛，官青，等.一种甲状腺肿瘤细胞学涂片图像分类方法及其装置[P].专利申请号：CN201810318242.3
[12]	熊继平，叶灵枫，叶童.一种图像数据扩增方法与流程[P].专利申请号：CN201811309890.9
[13]	Hussain Z，Gimenez F，Yi D，et al.Differential Data Augmentation Techniques for Medical Imaging Classification Tasks [J].AMIA Annu Symp Proc，2018，2017：979-984.
[17]	Wang KJ，Adrian AM，Chen KH，et al.A hybrid classifier combining Borderline-SMOTE with AIRS algorithm for estimating brain metastasis from lung cancer：a case study in Taiwan[J].Comput Methods Programs Biomed，2015，119（2）：63-76.
[18]	Pan T，Zhao J，Wu W，et al.Learning imbalanced datasets based on SMOTE and Gaussian distribution[J].Inform Sci，2020，512：1214-1233.
[19]	Dong Y，Wang X.A New Over-Sampling Approach：Random-SMOTE for Learning from Imbalanced Data Sets，in Knowledge Science，Engineering and Management[J].Editors，2011，343-352.
[20]	Chawla NV，Lazarevic A，Hall LO，et al.SMOTEBoost：Improving Prediction of the Minority Class in Boosting[C]//European Conference on Principles of Data Mining and Knowledge Discovery.Springer，Berlin，Heidelberg，2003.
[21]	Muramatsu C，Nishio M，Goto T，et al.Improving breast mass classification by shared data with domain transformation using a generative adversarial network[J].Comput Biol Med，2020，119：103 698.
[22]	Bisneto TRV，Filho AODC，Magalhes DMV.Generative adversarial network and texture features applied to automatic glaucoma detection[J].Applied Soft Computing，2020，90：106 165.
[23]	Kim HJ，Lee D.Image denoising with conditional generative adversarial networks （CGAN） in low dose chest images[J].Nucl Instrum Meth Phys Res A，2020，954：161 914.
[24]	Kumar Singh V，Rashwan HA，Romani S，et al.Breast tumor segmentation and shape classification in mammograms using generative adversarial and convolutional neural network[J].Expert Syst Appl，2020，139：112 855.
[25]	Wei Z，Zou J，Zhang J，et al.Automatic epileptic EEG detection using convolutional neural network with improvements in time-domain[J].Biomed Signal Process Control，2019，53：101 551.
[26]	Li H，Boimel P，Janopaul-Naylor J，et al.DEEP CONVOLUTIONAL NEURAL NETWORKS FOR IMAGING DATA BASED SURVIVAL ANALYSIS OF RECTAL CANCER[J].Proc IEEE Int Symp Biomed Imaging，2019，2019：846-849.