Implementation and Application of an Intelligent Pterygium Diagnosis System Based on Deep Learning

Abstract

Objective: This study aims to implement and investigate the application of a special intelligent diagnostic system based on deep learning in the diagnosis of pterygium using anterior segment photographs.Methods: A total of 1,220 anterior segment photographs of normal eyes and pterygium patients were collected for training (using 750 images) and testing (using 470 images) to develop an intelligent pterygium diagnostic model. The images were classified into three categories by the experts and the intelligent pterygium diagnosis system: (i) the normal group, (ii) the observation group of pterygium, and (iii) the operation group of pterygium. The intelligent diagnostic results were compared with those of the expert diagnosis. Indicators including accuracy, sensitivity, specificity, kappa value, the area under the receiver operating characteristic curve (AUC), as well as 95% confidence interval (CI) and F1-score were evaluated.Results: The accuracy rate of the intelligent diagnosis system on the 470 testing photographs was 94.68%; the diagnostic consistency was high; the kappa values of the three groups were all above 85%. Additionally, the AUC values approached 100% in group 1 and 95% in the other two groups. The best results generated from the proposed system for sensitivity, specificity, and F1-scores were 100, 99.64, and 99.74% in group 1; 90.06, 97.32, and 92.49% in group 2; and 92.73, 95.56, and 89.47% in group 3, respectively.Conclusion: The intelligent pterygium diagnosis system based on deep learning can not only judge the presence of pterygium but also classify the severity of pterygium. This study is expected to provide a new screening tool for pterygium and benefit patients from areas lacking medical resources.

Computer-Assisted Pterygium Screening System: A Review

“…However, the proposed MobileNet architecture was only trained by using a low number of samples without any pre-trained weights. A similar issue was also encountered in the works in [22,43], whereby the authors used a low number of samples and, even worse, the dataset distribution was imbalanced between the classes. Furthermore, the tested data were relatively homogeneous, being derived from a single ethnicity only.…”

“…A deeper network can be observed in the work by Xu et al [43], whereby EfficientNet is used to classify anterior eye images to identify the cases of observed and surgery-required pterygium. EfficientNet-B6 [44], which is the second-deepest network from the EfficientNet family of architectures, was trained by using a total of 750 images, and an additional 470 images were used during the validation phase.…”

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.…”

Keratoviz-A multistage keratoconus severity analysis and visualization using deep learning and class activated maps

“…Contribution in [21] led to the implementation and application of deep learning techniques to develop an intelligent Pterygium diagnosis system. Also in 2021, contributors of [22] used disk-based corneal topography as their primary dataset on which they applied deep learning models to detect the presence of keratoconus.…”