Automated Pterygium Detection Using Deep Neural Network

Abstract

Ocular imaging has developed rapidly and plays a critical role in clinical care and ocular disease management. Development of image processing technologies pertinent to ocular diseases has paved the way for automated diagnostic systems including detection techniques using deep learning (DL) approaches. The prevalence of an abnormal tissue layer in the conjunctiva, known as pterygium eye disease, is increasing due to lack of awareness. Despite the non-cancerous/benign nature of pterygium, a clinical diagnosis from an ophthalmologist is still required to prevent the pterygium tissues from extending into the pupil, which would result in blurred vision. However, current diagnostic methods are mostly dependent on human expertise. Automated detection can potentially serve as an assistive method to reduce diagnosis time by applying a DL approach. Considering the lack of comprehensive research work on pterygium detection using DL, we propose a new architecture consisting of an improved CNN-based trained network named VggNet16-wbn that is derived from VggNet16, a pre-trained CNN algorithm. This paper presents an overview of the DL as a core approach to the transfer learning (TL) concept, as well as current efforts towards automated ocular detection approaches. A new architecture of a CNN-based trained network was proposed based on a network assessment from six CNN pre-trained networks to detect pterygium. This work consists of two main modules, namely, data acquisition and DCNN classification. The proposed trained network, VggNet16-wbn, shows the best performance with 99.22% accuracy, 98.45% sensitivity, and a perfect score on specificity and area under the curve metrics. This work has high potential for creating a pterygium screening system that can be used as a baseline for fully automated detection using a DL approach.

Systematic Bibliometric and Visualized Analysis of Research Hotspots and Trends on the Application of Artificial Intelligence in Ophthalmic Disease Diagnosis

“…For example, the collection of ophthalmic examination data from different races, countries, or regions ( Bellemo et al, 2019 ; Raumviboonsuk et al, 2019 ; Al Turk et al, 2020 ). More disease types should also be included in these studies, such as pterygium, familial amyloidosis, and thyroid-associated ophthalmopathy ( Kessel et al, 2020 ; Zamani et al, 2020 ; Xu W. et al, 2021 ; Song et al, 2021 ). In addition, more ophthalmologists with different levels of training should participate in the screening stage of the data set and the examination stage of the algorithm to obtain clinically-based diagnoses.…”

Appositeness of Optimized and Reliable Machine Learning for Healthcare: A Survey

“…The applications of it include interaction-less services with speech communication, automation of transcript generation, clinical notes synthesis, correspondence for an emergency in staff unavailability, etc. These methods are time and cost-effective and increase productivity, to manage the healthcare infrastructure internally well, applications of clinical audio and speech processing have been successful where automation is a new modality for patients as well as clinicians [ 115 ]. Clinical speech processing confronts two major challenges as disfluency and utterance segmentation which stalls processing activity.…”

Towards a Connected Mobile Cataract Screening System: A Future Approach

“…CAD systems are intended to assist physicians by automatically interpreting images, which results in decreases in human dependency, boosts the rate of diagnosis, and lowers total treatment costs by reducing false-positive and false-negative (FN) predictions [58]. In addition, anterior segment photographed images that focus on the anterior part of the eyes have also been used for ocular disease detection [59,60]. For that reason, some researchers have started to explore the use of digital camera images from smartphones for early cataract detection and screening.…”