A novel multiscale convolutional neural network based age-related macular degeneration detection using OCT images. (May 2021)

• Record Type: Journal Article
• Authors: Thomas, Anju; P. M., Harikrishnan; K. Krishna, Adithya; P., Palanisamy; Gopi, Varun P.
• Is Part Of: Biomedical signal processing and control. Volume 67(2021)
• Publication Date: 2021-05
• Subjects: Age-related macular degeneration -- Multiscale CNN -- Sigmoid activation function; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102538
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The proposed CNN consist of multiscale Convolutional Layers which permits the network to produce large number of local structures with different filter sizes. The 128 relevant features from the second fully connected layer of the CNN are followed by the sigmoid activation function for the binary classification. The proposed network is trained using the Mendeley dataset and tested with the Mendeley dataset and the other three datasets, which provide notable results. Suitable for real-time implementation due to the less number of learnable parameter which reduces the complexity of the system. Abstract: Age-related macular degeneration (AMD) is an ocular disorder that affects the elderly. The prevalence of AMD is growing due to the aging population in society; hence early diagnosis is necessary to prevent vision loss in the elderly. Arranging a detailed eye screening system for detecting AMD is a very challenging process. This paper proposes a novel multiscale convolutional neural network (CNN) architecture for accurate diagnosis of AMD. The architecture proposed is a multiscale CNN with seven convolutional layers for classifying AMD or normal images. The multiscale convolution layer enables a large number of local structures to be generated with various filter sizes. In this proposed network, the sigmoid function is used as the classifier. The proposed CNN network is trained on the Mendeley dataset and tested on four datasets, namely Mendeley, OCTID, Duke, SD-OCT Noor dataset and achieved an accuracy of 99.73%, 98.08%, 96.66%, and 97.95% respectively. Comparison with alternative methods yielded results that exhibit the efficiency of the proposed algorithm in AMD detection. Even if the proposed model is trained only on the Mendeley dataset, it achieved good detection accuracy when tested with other datasets. This indicates the proposed model's ability to classify AMD/Normal images from other datasets. Comparison with other approaches produced results that exhibit the efficiency of the proposed algorithm in detecting AMD. The proposed architecture can be applied in rapid screening of the eye for the early detection of AMD. Due to less complexity and fewer learnable parameters, the proposed CNN can be implemented in real-time.