Optical coherence tomography image based eye disease detection using deep convolutional neural network

Abstract

Over the past few decades, health care industries and medical practitioners faced a lot of obstacles to diagnosing medical-related problems due to inadequate technology and availability of equipment. In the present era, computer science technologies such as IoT, Cloud Computing, Artificial Intelligence and its allied techniques, etc. play a crucial role in the identification of medical diseases, especially in the domain of Ophthalmology. Despite this, ophthalmologists have to perform the various disease diagnosis task manually which is time-consuming and the chances of error are also very high because some of the abnormalities of eye diseases possess the same symptoms. Furthermore, multiple autonomous systems also exist to categorize the diseases but their prediction rate does not accomplish state-of-art accuracy. In the proposed approach by implementing the concept of Attention, Transfer Learning with the Deep Convolution Neural Network, the model accomplished an accuracy of 97.79% and 95.6% on the training and testing data respectively. This autonomous model efficiently classifies the various oscular disorders namely Choroidal Neovascularization, Diabetic Macular Edema, Drusen from the Optical Coherence Tomography images. It may provide a realistic solution to the healthcare sector to bring down the ophthalmologist burden in the screening of Diabetic Retinopathy.

Keywords: Artificial intelligence; Convolutional neural network; Deep learning (DL); Diabetic retinopathy; Eye disease; Ophthalmology; Optical coherence tomography; Transfer learning.

Fig. 1

Number of labelled images in dataset

Fig. 2

Sample OCT scans of eye diseases

Fig. 3

Histogram of normal retinal images

Fig. 4

Proposed model architecture

Fig. 5

VGG-16 CNN architecture (abstract form)

Fig. 6

VFF16_Attention model architecture (proposed model)

Fig. 7

a MobileNet model accuracy. b MobileNet model loss

Fig. 8

a InceptionV3 model accuracy. b. InceptionV3 model loss

Fig. 9

a EfficientNet model accuracy. b EfficientNet model loss

Fig. 10

a ResNet model accuracy. b ResNet model loss

Fig. 11

a DenseNet model accuracy. b DenseNet model loss

Fig. 12

a Attention results (CNV eye scans). b Attention results (normal eye scans)

Fig. 13

a VGG16_Attention model accuracy. b VGG16_Attention model loss