A deep feature fusion and selection‐based retinal eye disease detection from OCT images

Abstract

Optical coherence tomography (OCT) is one of the principal imaging modalities for retinal eye disease detection and classification. Different retinal eye diseases are the leading cause of blindness that can be overcome by early detection. However, ophthalmologists are currently carrying out retinal eye disease detection manually with the help of OCT images that may be erroneous and subjective. Different methods have been presented to automate the manual retinal eye disease detection process that needs further improvement in detection accuracy. This research proposed an automatic method for retinal eye disease detection and classification from OCT images using fusion and selection techniques. First, the modified-Alexnet and ResNet-50 are utilized for deep feature vector extraction. In the next step, these vectors are fused serially and rectified by the proposed feature selection framework and passed as input to different machine learning classifiers for retinal disease diagnosis.

A Novel Artificial-Intelligence-Based Approach for Automatic Assessment of Retinal Disease Images Using Multi-View Deep-Broad Learning Network

“…proposed a residual module for OCT image classification of retinal diseases, which enhances the contrast of feature maps, resulting in clearer retinal layer boundaries. Muhammad Junaid Umer [17] proposed an automatic method to detect and classify retinal ophthalmopathy from OCT images using fusion and selection techniques, and the proposed retinal ophthalmopathy detection method can be reliably used for automatic ophthalmopathy detection in OCT images. Sunija [18] et al proposed a deep convolutional neural network with six convolutional blocks for the classification of retinal OCT images.…”

Review of AlexNet for Medical Image Classification

“…Ophthalmology: AlexNet has shown promise in ophthalmology, particularly in diagnosing and monitoring eye diseases [86]. It can analyze retinal images, such as fundus photographs [87], to detect signs of diabetic retinopathy [88], glaucoma [89], and age-related macular degeneration [90]. By automatically identifying abnormalities and disease-related features in these images, AlexNet assists ophthalmologists in diagnosing and tracking disease progression early.…”

Automated Age-Related Macular Degeneration Detector on Optical Coherence Tomography Images Using Slice-Sum Local Binary Patterns and Support Vector Machine

“…Recently, AI techniques have been extensively utilized to process human retinal information on OCT images. The tasks include DL-based denoising [16,17], DL-based segmentation [18,19], DL-based disease classification [6][7][8][20][21][22], and ML-based disease classification [3,6,[23][24][25][26][27][28]. For the DL-based disease classification, the study in [6] has utilized the AlexNet, GoogLeNet, and Inception-ResNet-v2 to achieve high AMD detection accuracies up to 97.39%, 96.41%, and 98.18%, respectively.…”

“…Table 1 lists the state-of-the-art studies related to SVM-based eye disease classifications. It is worth noting that the studies in [3,24,26,28] employed image-level classification while the studies in [25,27] employed volume-level classification. The volume-level classification is more practical than the image-level classification since an OCT volume is representative for a whole subject.…”