Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects

Journal of Glaucoma

Volumn 26, Issue 12, 2017, Pages 1086-1094

  Muhammad, Hassan ^a,b   Fuchs, Thomas J ^a,b,c   De Cuir, Nicole ^d,e   De Moraes, Carlos G ^b   Blumberg, Dana M ^b   Liebmann, Jeffrey M ^b   Ritch, Robert ^f   Hood, Donald C ^b,d  

^a WEILL CORNELL MEDICAL COLLEGE   (United States)

^b Department of Medical Physics ^*  (United States)

^c MEMORIAL SLOAN KETTERING CANCER CENTER   (United States)

^d Memorial Sloan Kettering Cancer Center ^*  (United States)

^e MC 5501 ^*  (United States)

^f NEW YORK EYE AND EAR INFIRMARY   (United States)

Author keywords

classification; detection; image processing; machine learning; optical coherence tomography

Indexed keywords

ACCESS TO INFORMATION; ALGORITHM; ARTICLE; CLASSIFIER; CONTROLLED STUDY; DIAGNOSTIC TEST; DIAGNOSTIC TEST ACCURACY STUDY; DISEASE CLASSIFICATION; DISEASE SEVERITY; FALSE NEGATIVE RESULT; FALSE POSITIVE RESULT; GONIOSCOPY; HUMAN; HYBRID DEEP LEARNING METHOD; MACHINE LEARNING; MAJOR CLINICAL STUDY; MEDICAL EXPERT; NERVE CELL NETWORK; OPEN ANGLE GLAUCOMA; OPTICAL COHERENCE TOMOGRAPHY; PRIORITY JOURNAL; RANDOM FOREST; RECEIVER OPERATING CHARACTERISTIC; RETINAL NERVE FIBER LAYER THICKNESS; SINGLE WIDE FIELD OPTICAL COHERENCE TOMOGRAPHY; ARTIFICIAL NEURAL NETWORK; CLASSIFICATION; INTRAOCULAR HYPERTENSION; INTRAOCULAR PRESSURE; NERVE FIBER; PATHOLOGY; PATHOPHYSIOLOGY; PHYSIOLOGY; PROCEDURES; REPRODUCIBILITY; RETINA GANGLION CELL; VISUAL FIELD;

GLAUCOMA, OPEN-ANGLE; HUMANS; INTRAOCULAR PRESSURE; MACHINE LEARNING; NERVE FIBERS; NEURAL NETWORKS (COMPUTER); OCULAR HYPERTENSION; REPRODUCIBILITY OF RESULTS; RETINAL GANGLION CELLS; TOMOGRAPHY, OPTICAL COHERENCE; VISUAL FIELDS;

EID: 85037633827     PISSN: 10570829     EISSN: 1536481X     Source Type: Journal    
DOI: 10.1097/IJG.0000000000000765     Document Type: Article

References (20)

1. Hood DC, De Cuir N, Blumberg DM, et al. A single wide-field OCT protocol can provide compelling information for the diagnosis of early glaucoma. Transl Vis Sci Technol. 2017; 5:4.
2. Hood DC, Raza AS, De Moraes CG, et al. Evaluation of a one-page report to aid in detecting glaucomatous damage. Transl Vis Sci Technol. 2014;3:8. doi:10.1167/tvst.3.6.8.
3. Hood DC, Fortune B, Mavrommatis MA, et al. Details of glaucomatous damage are better seen on OCT en face images than on OCT retinal nerve fiber layer thickness maps. Invest Ophthalmol Vis Sci. 2015;56:6208-6216.
4. Jia Y, Shelhamer E, Donahue J, et al. Caffe: convolutional architecture for fast feature embedding. 2014.
5. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2011.
6. Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115:211-252.
7. Paulin M, Revaud J, Harchaoui Z, et al. Transformation pursuit for image classification. IEEE. 2014:3646-3653. doi:10.1109/CVPR.2014.466.
8. Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database. IEEE. 2009:248-255. doi:10.1109/CVPR.2009.5206848.
9. Breiman L. Random forests. Mach Learn. 2001;45:5-32.
10. Amit Y, Geman D. Shape quantization and recognition with randomized trees. Neural Comput. 1997;9:1545-1588.
11. Team R, others. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. 2010.
12. Hood DC, Raza AS. On improving the use of OCT imaging for detecting glaucomatous damage. Br J Ophthalmol. 2014;98 (suppl 2):ii1-ii9.
13. Goldbaum MH, Lee I, Jang G, et al. Progression of patterns (POP): a machine classifier algorithm to identify glaucoma progression in visual fields. Invest Ophthalmol Vis Sci. 2012;53: 6557-6567.
14. Yousefi S, Balasubramanian M, Goldbaum MH, et al. Unsupervised gaussian mixture-model with expectation maximization for detecting glaucomatous progression in standard automated perimetry visual fields. Transl Vis Sci Technol. 2016; 5:2. doi:10.1167/tvst.5.3.2.
15. Belghith A, Bowd C, Medeiros FA, et al. Learning from healthy and stable eyes: a new approach for detection of glaucomatous progression. Artif Intell Med. 2015;64: 105-115.
16. Bowd C, Hao J, Tavares IM, et al. Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes. Invest Ophthalmol Vis Sci. 2008;49:945-953.
17. Bizios D, Heijl A, Hougaard JL, et al. Machine learning classifiers for glaucoma diagnosis based on classification of retinal nerve fibre layer thickness parameters measured by Stratus OCT. Acta Ophthalmol (Copenh). 2010;88:44-52.
18. Silva FR, Vidotti VG, Cremasco F, et al. Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry. Arq Bras Oftalmol. 2013;76:170-174.
19. Barella KA, Costa VP, Gonçalves Vidotti V, et al. Glaucoma diagnostic accuracy of machine learning classifiers using retinal nerve fiber layer and optic nerve data from SD-OCT. J Ophthalmol. 2013;2013:789129. doi:10.1155/2013/789129.
20. Asaoka R, Iwase A, Hirasawa K, et al. Identifying "preperi-metric" glaucoma in standard automated perimetry visual fields. Invest Ophthalmol Vis Sci. 2014;55:7814-7820.