Deep Features and Data Reduction for Classification of SD-OCT Images: Application to Diabetic Macular Edema

作者: Genevieve CY Chan , Syed AA Shah , TB Tang , C-K Lu , H Muller

DOI: 10.1109/ICIAS.2018.8540579

关键词:

摘要: Diabetic Macular Edema (DME) is defined as the accumulation of extracellular fluids in macular region eye, caused by Retinopathy (DR) that will lead to irreversible vision loss if left untreated. This paper presents use a pre-trained Convolutional Neural Network (CNN) based model for classification Spectral Domain Optical Coherence Tomography (SD- OCT) images with feature reduction using Principal Component Analysis (PCA) and Bag Words (BoW). The trained SD-OCT dataset retrieved from Singapore Eye Research Institute (SERI) evaluated an 8-fold cross validation at slide level two patient leave out volume level. For level, accuracy 96.88% obtained data was preprocessed.

参考文章(21)
Conceição Lobo, Isabel Pires, José Cunha-Vaz, Diabetic Macular Edema European Journal of Ophthalmology. ,vol. 8, pp. 127- 130 ,(1998) , 10.1007/978-3-642-27410-7_1
Guillaume Lemaître, Mojdeh Rastgoo, Joan Massich, Shrinivasan Sankar, Fabrice Mériaudeau, Désiré Sidibé, Classification of SD-OCT Volumes with LBP: Application to DME Detection Ophthalmic Medical Image Analysis Workshop (OMIA), Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015. ,vol. 2, pp. 9- 16 ,(2015) , 10.17077/OMIA.1021
G. Csurka, Visual categorization with bags of keypoints european conference on computer vision. ,vol. 1, pp. 22- ,(2004)
Freerk G. Venhuizen, Bram van Ginneken, Bart Bloemen, Mark J. J. P. van Grinsven, Rick Philipsen, Carel Hoyng, Thomas Theelen, Clara I. Sánchez, Automated age-related macular degeneration classification in OCT using unsupervised feature learning Proceedings of SPIE. ,vol. 9414, ,(2015) , 10.1117/12.2081521
Kedir M Adal, Désiré Sidibé, Sharib Ali, Edward Chaum, Thomas P Karnowski, Fabrice Mériaudeau, None, Automated detection of microaneurysms using scale-adapted blob analysis and semi-supervised learning Computer Methods and Programs in Biomedicine. ,vol. 114, pp. 1- 10 ,(2014) , 10.1016/J.CMPB.2013.12.009
Yu-Ying Liu, Mei Chen, Hiroshi Ishikawa, Gadi Wollstein, Joel S. Schuman, James M. Rehg, Automated macular pathology diagnosis in retinal OCT images using multi-scale spatial pyramid and local binary patterns in texture and shape encoding Medical Image Analysis. ,vol. 15, pp. 748- 759 ,(2011) , 10.1016/J.MEDIA.2011.06.005
Pratul P. Srinivasan, Leo A. Kim, Priyatham S. Mettu, Scott W. Cousins, Grant M. Comer, Joseph A. Izatt, Sina Farsiu, Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images Biomedical Optics Express. ,vol. 5, pp. 3568- 3577 ,(2014) , 10.1364/BOE.5.003568
Sharib Ali, Désiré Sidibé, Kedir M Adal, Luca Giancardo, Edward Chaum, Thomas P Karnowski, Fabrice Mériaudeau, None, Statistical atlas based exudate segmentation Computerized Medical Imaging and Graphics. ,vol. 37, pp. 358- 368 ,(2013) , 10.1016/J.COMPMEDIMAG.2013.06.006
Ilya Sutskever, Geoffrey E. Hinton, Alex Krizhevsky, ImageNet Classification with Deep Convolutional Neural Networks neural information processing systems. ,vol. 25, pp. 1097- 1105 ,(2012)
I. T. Jolliffe, Principal Component Analysis and Factor Analysis Springer, New York, NY. pp. 115- 128 ,(1986) , 10.1007/978-1-4757-1904-8_7