A Deep Learning Approach to Automatic Recognition of Arcus Senilis

Abstract

Background: Arcus Senilis (AS) appears as a white, grey or blue ring or arc in front of the periphery of the iris, and is a symptom of abnormally high cholesterol in patients under 50 years old. Objective: This work proposes a deep learning approach to automatic recognition of AS in eye images. Material and Methods: In this analytical study, a dataset of 191 eye images (130 normal, 61 with AS) was employed where ¾ of the data were used for training the proposed model and ¼ of the data were used for test, using a 4-fold cross-validation. Due to the limited amount of training data, transfer learning was conducted with AlexNet as the pretrained network. Results: The proposed model achieved an accuracy of 100% in classifying the eye images into normal and AS categories. Conclusion: The excellent performance of the proposed model despite limited training set, demonstrate the efficacy of deep transfer learning in AS recognition in eye images. The proposed approach is preferred to previous methods for AS recognition, as it eliminates cumbersome segmentation and feature engineering processes.

Prevalence of corneal arcus and associated factors in a German population—Results from the Gutenberg Health Study

“…We therefore performed several sensitivity analyses and found similar results. Amini and Ameri proposed a deep learning based automatic recognition of corneal arcus [ 38 ]. Their model achieved a high accuracy in classifying images with and without arcus.…”

Enhancement of automatic classification of arcus senilis-nonarcus senilis using convolutional neural networ

“…Iridology is a technique that was discovered more than a century ago to discover information about a person's health by evaluating iris features such as color or pattern [1], [2]. The high level of cholesterol in the human body is one of the disorders that are identifiable using the iridology approach [3].…”

“…Artificial intelligence (AI) is becoming more appealing for medical applications, enabling for the exploration of new areas where computer algorithms might improve medical operations [9]- [12], also recent world-wide disease namely COVID-19 that has been declared as a pandemic by the World Health Organization on 11 th March 2020 [13]- [16]. Recent studies have demonstrated the potential of various non-invasive techniques in detecting cholesterol from the images of iris [1], [17]- [21], skin [22], [23], MRI [24], and hand pattern [25]. Most of these methods are based on ML algorithms that extract all the image features before training the dataset.…”

“…The proposed CNN model has yielded 97.14% classification accuracy [20]. Amini & Ameri applied AlexNet and VGG-16 pre-trained CNN architectures with 4-fold cross-validation into normal and CA images using transfer learning approach [1]. Kocejko et al [9] used CNN automatic identification of the CA presence.…”