Atlas-based score for automatic glaucoma risk stratification

被引:6
作者
Girard, Fantin [1 ]
Hurtut, Thomas [1 ]
Kavalec, Conrad [2 ]
Cheriet, Farida [1 ]
机构
[1] Polytech Montreal, Montreal, PQ H3T 1J4, Canada
[2] St Marys Hosp, Montreal, PQ H3T 1M5, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Statistical atlas; Deep learning segmentation; Glaucoma detection; Retina; CUP; IMAGES; DISC; SEGMENTATION; SYSTEM;
D O I
10.1016/j.compmedimag.2020.101797
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Glaucoma is a disease that affects the optic nerve and can lead to blindness. The cup-to-disc ratio (CDR) measurement is one of the key clinical indicators for glaucoma assessment. However, the CDR only evaluates the relative sizes of the cup and optic disc (OD) via their diameters, and does not characterize local morphological changes that can inform clinicians on early signs of glaucoma. In this work, we propose a novel glaucoma score based on a statistical atlas framework that automatically quantifies the deformations of the OD region induced by glaucoma. A deep-learning approach is first used to segment the optic cup with a dedicated atlas-based data augmentation strategy. The segmented OD region (disc, cup and vessels) is then registered to the statistical OD atlas and the deformation is projected onto the atlas eigenvectors. The atlas glaucoma score (AGS) is then obtained by a linear combination of the principal modes of deformation of the atlas with linear discriminant analysis. The AGS performs better than the CDR on the three datasets used for evaluation, including RIM-ONE and ORIGA650. Compared to the CDR measurement, which yields an area under the ROC curve (AUC) of 91.4% using the expert segmentations, the AGS achieves an AUC of 98.2%. Our novel glaucoma score captures more complex deformations within the optic disc region than the CDR can. Such morphological changes are the first cue of glaucoma onset, before the visual field is affected. The proposed approach can thus significantly improve early detection of glaucoma.
引用
收藏
页数:15
相关论文
共 35 条
[1]   Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features [J].
Abramoff, Michael D. ;
Alward, Wallace L. M. ;
Greenlee, Emily C. ;
Shuba, Lesya ;
Kim, Chan Y. ;
Fingert, John H. ;
Kwon, Young H. .
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2007, 48 (04) :1665-1673
[2]  
Abramoff Michael D, 2010, IEEE Rev Biomed Eng, V3, P169, DOI 10.1109/RBME.2010.2084567
[3]   Decision support system for the glaucoma using Gabor transformation [J].
Acharya, U. Rajendra ;
Ng, E. Y. K. ;
Eugene, Lim Wei Jie ;
Noronha, Kevin P. ;
Min, Lim Choo ;
Nayak, K. Prabhakar ;
Bhandary, Sulatha V. .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2015, 15 :18-26
[4]  
[Anonymous], 1999, CLIN EYE VISION CARE
[5]   Glaucoma risk index: Automated glaucoma detection from color fundus images [J].
Bock, Ruediger ;
Meier, Joerg ;
Nyul, Laszlo G. ;
Hornegger, Joachim ;
Michelson, Georg .
MEDICAL IMAGE ANALYSIS, 2010, 14 (03) :471-481
[6]   Bagging predictors [J].
Breiman, L .
MACHINE LEARNING, 1996, 24 (02) :123-140
[7]   A Radiomics Approach to Computer-Aided Diagnosis with Cardiac Cine-MRI [J].
Cetin, Irem ;
Sanroma, Gerard ;
Petersen, Steffen E. ;
Napel, Sandy ;
Camara, Oscar ;
Gonzalez Ballester, Miguel-Angel ;
Lekadir, Karim .
STATISTICAL ATLASES AND COMPUTATIONAL MODELS OF THE HEART: ACDC AND MMWHS CHALLENGES, 2018, 10663 :82-90
[8]  
Chalam K.V., 2011, FUNDAMENTALS PRINCIP
[9]   Automatic Feature Learning for Glaucoma Detection Based on Deep Learning [J].
Chen, Xiangyu ;
Xu, Yanwu ;
Yan, Shuicheng ;
Wong, Damon Wing Kee ;
Wong, Tien Yin ;
Liu, Jiang .
MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, PT III, 2015, 9351 :669-677
[10]   Sparse Dissimilarity-Constrained Coding for Glaucoma Screening [J].
Cheng, Jun ;
Yin, Fengshou ;
Wong, Damon Wing Kee ;
Tao, Dacheng ;
Liu, Jiang .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2015, 62 (05) :1395-1403