Eye Disease Prediction from Optical Coherence Tomography Images with Transfer Learning

Optical Coherence Tomography (OCT) of the human eye are used by optometrists to analyze and detect various age-related eye abnormalities like Choroidal Neovascularization, Drusen (CNV), Diabetic Macular Odeama (DME), Drusen. Detecting these diseases are quite challenging and requires hours of analysis by experts, as their symptoms are somewhat similar. We have used transfer learning with VGG16 and Inception V3 models which are state of the art CNN models. Our solution enables us to predict the disease by analyzing the image through a convolutional neural network (CNN) trained using transfer learning. Proposed approach achieves a commendable accuracy of 94% on the testing data and 99.94% on training dataset with just 4000 units of data, whereas to the best of our knowledge other researchers have achieved similar accuracies using a substantially larger (almost 10 times) dataset.

[1]  M. Treder,et al.  Automated detection of exudative age-related macular degeneration in spectral domain optical coherence tomography using deep learning , 2018, Graefe's Archive for Clinical and Experimental Ophthalmology.

[2]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[3]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[4]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[5]  Arna van Engelen,et al.  Multi-Center MRI Carotid Plaque Component Segmentation Using Feature Normalization and Transfer Learning , 2015, IEEE Transactions on Medical Imaging.

[6]  Lutz Prechelt,et al.  Early Stopping - But When? , 2012, Neural Networks: Tricks of the Trade.

[7]  M. Amaro,et al.  Age-related macular degeneration with choroidal neovascularization in the setting of pre-existing geographic atrophy and ranibizumab treatment. Analysis of a case series and revision paper , 2012 .

[8]  er,et al.  Drusen Imaging: A Review , 2014 .

[9]  James G. Fujimoto,et al.  Optical coherence tomography: high-resolution imaging in nontransparent tissue , 1999 .

[10]  Marleen de Bruijne,et al.  Machine learning approaches in medical image analysis: From detection to diagnosis , 2016, Medical Image Anal..

[11]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[13]  P. Prahs,et al.  OCT-based deep learning algorithm for the evaluation of treatment indication with anti-vascular endothelial growth factor medications , 2017, Graefe's Archive for Clinical and Experimental Ophthalmology.

[14]  Huafeng Liu,et al.  Deep Learning Assessment of Myocardial Infarction From MR Image Sequences , 2019, IEEE Access.

[15]  Edward Y. Chang,et al.  Transfer representation learning for medical image analysis , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[16]  N. Bressler,et al.  Optimizing management of diabetic macular edema in Hong Kong: a collaborative position paper , 2017 .

[17]  Sanjay Kumar,et al.  A Study on the Image Detection Using Convolution Neural Networks and TenserFlow , 2018, 2018 International Conference on Inventive Research in Computing Applications (ICIRCA).