屈莹;陈晨;吕小毅;

• 1:新疆大学信息科学与工程学院
• 2:新疆大学软件学院
• 3:新疆维吾尔自治区信号检测与处理重点实验室

摘要(Abstract)：

为了利用机器学习算法快速筛查出葡萄膜炎,本文分别选取了健康人和葡萄膜炎患者的眼底OCT(Optical Coherence Tomography, OCT)图像,提取图像的形态特征、灰度差分统计特征、灰度梯度共生矩阵和小波变换等多种特征,将特征串行融合;随后用Lasso算法特征提取,用多种机器学习算法进行分类研究.结果显示:基于Medium Gaussian核函数的支持向量机(Support Vector Machine, SVM)获得了90.3%的分类准确率,其受试者工作特性曲线(Receiver Operating Characteristic curve, ROC)下的面积(Area Under Curve, AUC)为0.97,为研究中的最高准确率.本文首次将机器学习分类算法应用于葡萄膜炎患者眼底OCT图像的分类中,是对葡萄膜炎诊断的探索性研究,对葡萄膜炎的辅助诊断具有重要意义.

关键词(KeyWords)： 葡萄膜炎;眼底OCT图像;机器学习;ROC曲线;辅助诊断

Abstract:

Keywords:

基金项目(Foundation): 天山青年-杰出青年科技项目(2019Q003)

作者(Authors): 屈莹;陈晨;吕小毅;

DOI: 10.13568/j.cnki.651094.651316.2020.11.16.0003

参考文献(References)：

• [1]SMITH J R.Management of uveitis[J].Clinical and Experimental Medicine,2004,4(1):21-29.
• [2]MISEROCCHI E,FOGLIATO G,MODORATI G,et al.Review on the worldwide epidemiology of uveitis[J].European Journal of Ophthalmology,2013,23(5):705-717.
• [3]LEE J Y,KIM D Y,WOO S J,et al.Clinical patterns of uveitis in tertiary ophthalmology centers in Seoul,South Korea[J].Ocular Immunology and Inflammation,2017,25(1):S24-S30.
• [4]HUNTER R S,SKONDRA D,PAPALIODIS G,et al.Role of OCT in the diagnosis and management of macular Edema from uveitis[J].Seminars in Ophthalmology,2012,27(5/6):236-241.
• [5]CHOWDHURY A R,CHATTERJEE T,BANERJEE S.A random forest classifier-based approach in the detection of abnormalities in the retina[J].Medical&Biological Engineering&Computing,2019,57(1):193-203.
• [6]COELHO F,COSTA M,VERLEYSEN M,et al.LASSO multi-objective learning algorithm for feature selection[J].Soft Computing,2020,24(1/4):13209-13217.
• [7]FANG L Y,WANG C,LI S T,et al.Attention to Lesion:Lesion-Aware convolutional neural network for retinal optical coherence tomography image classification[J].IEEE Transactions on Medical Imaging,2019,38(3):1959-1970.
• [8]SUN Y K,LEI M.Method for optical coherence tomography image classification using local features and earth mover’s distance[J].Journal of Biomedical Optics,2019,14(5):054037.
• [9]FANG L Y,WANG C,LI S T,et al.Automatic classification of retinal three-dimensional optical coherence tomography images using principal component analysis network with composite kernels[J].Journal of Biomedical Optics,2017,22(11):1-10.
• [10]LU W,TONG Y,YU Y,et al.Deep learning-based automated classification of multi-categorical abnormalities from optical coherence tomography images[J].Translational Vision Science&Technology,2018,7(6):41.
• [11]GUPTA V,GUPTA A.Ancillary investigations in uveitis[J].Indian Journal of Ophthalmology,2013,61(6):263-268.
• [12]HUANG P,ZHANG S L,LI M,et al.Classification of cervical biopsy images based on LASSO and EL-SVM[J].IEEE Access,2020,8:24219-24228.
• [13]DANALA G,PATEI B,AGHAEI F,et al.Classification of breast masses using a computer-aided diagnosis scheme of contrast enhanced digital mammograms[J].Annals of Biomedical Engineering,2018,46(9):1419-1431.
• [14]TONG Y,LU W,YU Y,et al.Application of machine learning in ophthalmic imaging modalities[J].Eye and Vision,2020,7(1):161-181.
• [15]LU W,TONG Y,YU Y,et al.Applications of artificial intelligence in ophthalmology:General Overview[J].Journal of Ophthalmology,2018,2018(6):1-15.
• [16]RAJAGURU H,GANESAN K,BOJAN V K.Earlier detection of cancer regions from MR image features and SVM classifiers[J].International Journal of Imaging Systems and Technology,2016,26(3):196-208.
• [17]ZHANG H Q,WANG J,SUN Z Q,et al.Feature selection for neural networks using group lasso regularization[J].IEEE Transactions on Knowledge and Data Engineering,2020,32:659-673.
• [18]CHEN C Y,GUO X Y,WANG J,et al.The diagnostic value of radiomics-based machine learning in predicting the grade of meningiomas using conventional magnetic resonance imaging:A Preliminary Study[J].Frontiers in Oncology,2019,9:1338.
• [19]杨文忠,杨蒙蒙,温杰彬,等.基于One Class-SVM+Autoencoder模型的车辆碰撞检测[J].新疆大学学报(自然科学版)(中英文),2020,37(3):271-276+281.YANG W Z,YANG M M,WEN J B,et al.Vehicle collision detection based on One Class-SVM+Autoencoder Model[J].Journal of Xinjiang University (Natural Science Edition in Chinese and English),2020,37(3):271-276+281.(in Chinese)
• [20]RAJAGURU H,BOJAN V K.Performance Analysis of EM,SVD,and SVM Classifiers in Classification of Carcinogenic Regions of Medical Images[J].International Journal of Imaging Systems and Technology,2014,24(1):16-22.
• [21]KAUR P,PANNU H S,MALHI A K.Plant disease recognition using fractional-order Zernike moments and SVM classifier[J].Neural Computing&Applications,2019,31(12):8749-8768.
• [22]AMATO G,FALCHI F,GENNARO C.Fast image classification for monument recognition[J].Acm Journal on Computing and Cultural Heritage,2015,8(4):1-25.
• [23]HU J,PENG H,WANG J,et al.kNN-P:A kNN classifier optimized by P systems[J].Theoretical Computer Science,2020,817:55-65.
• [24]MURUGAN A,NAIR S A H,KUMAR K P S.Detection of skin cancer using SVM,random forest and kNN classifiers[J].Journal of Medical Systems,2020,43(8):1-9.
• [25]孟欣欣,阿里甫·库尔班,吕情深,等.基于迁移学习的自然环境下香梨目标识别研究[J].新疆大学学报(自然科学版),2019,36(4):461-467.MENG X X,Arifu Kuerban,LYU Q S,et al.Research on object recognition of fragrant pear in natural environment based on Transfer Learning[J].Journal of Xinjiang University (Natural Science edition),2019,36(4):461-467.(in Chinese)
• [26]杨东旭,赖惠成,班俊硕,等.基于改进DCNN结合迁移学习的图像分类方法[J].新疆大学学报(自然科学版),2018,35(2):195-202.YANG D X,LAI H C,BAN J S,et al.Image classification based on improved DCNN combined with transfer learning[J].Journal of Xinjiang University (Natural Science edition),2018,35(2):195-202.(in Chinese)
• [27]MA L,LIU X B,SONG L,et al.A new classifier fusion method based on historical and on-line classification reliability for recognizing common CT imaging signs of lung diseases[J].Computerized Medical Imaging and Graphics,2015(40):39-48.