Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images

Abstract

Optical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT images. In this work, we have developed a new framework for automated detection of retinal disorders using transfer learning. This model consists of three phases: deep fused and multilevel feature extraction, using 18 pre-trained networks and tent maximal pooling, feature selection with ReliefF, and classification using the optimized classifier. The novelty of this proposed framework is the feature generation using widely used CNNs and to select the most suitable features for classification. The extracted features using our proposed intelligent feature extractor are fed to iterative ReliefF (IRF) to automatically select the best feature vector. The quadratic support vector machine (QSVM) is utilized as a classifier in this work. We have developed our model using two public OCT image datasets, and they are named database 1 (DB1) and database 2 (DB2). The proposed framework can attain 97.40% and 100% classification accuracies using the two OCT datasets, DB1 and DB2, respectively. These results illustrate the success of our model.

MacD‐Net: An automatic guided‐ensemble approach for macular pathology detection using optical coherence tomography images

“…Their suggested approach has an AUC of 99.99%. Barua et al 22 have suggested an approach based on transfer learning; in this approach, the features drawn out from 18 different ImageNet‐trained DCNNs were fused and then the features selected using the ‘ReliefF’ method were used to train quadratic support vector machine (QSVM). Karthik et al 23 have proposed an activation function that helps in improving the contrast of the feature maps and they have also suggested architectural changes in the residual connection of the ResNet architecture.…”

Multimodel System for Driver Distraction Detection and Elimination

“…As some drivers fall asleep with their eyes wide open. Such a model would detect any retinal abnormalities where an analysis is made to detect whether the driver is mentally focused on the road [53].…”

Swin-textural: A novel textural features-based image classification model for COVID-19 detection on chest computed tomography

“…In the last of 2020, a new patch-based deep learning model was presented, named ViT (vision transformer) [ 8 ]. ViT obtained higher classification performance than popular CNNs [ [53] , [54] , [55] , [56] ]. Swin transformer [ 11 ] is an improved version of the ViT and uses variable-sized patch division operations.…”