Mobile Screening Framework of Anterior Segment Photographed Images

Abstract

This work presents a qualitative measurement of anterior segment photographed images (ASPIs) to identify between normal eyes and eyes with pterygium and pinguecula through Otsu multi-thresholding approach without contrast enhancement. In addition, we also propose a mobile screening framework of ASPIs through smartphones. ASPIs were directly sent to the cloud storage once an ASPI was captured using a smartphone camera, and then each image was processed through a digital image processing approach in a processing platform. Three important steps, namely, pre-processing, image segmentation and qualitative assessment, are involved in the processing platform of the mobile screening framework. The ASPIs are pre-processed to minimise or eliminate any unwanted areas within the image. Then, these ASPIs are segmented through multi-thresholding Otsu approach with clustering number n = 3. Segmentation result shows that the accuracy of the proposed method is 87.5%, which is comparable with the previously established work that has applied three-step differencing (3SD) method. However, the proposed approach has better computational time which is six times faster than the 3SD method. These results demonstrate a remarkable effort to produce a simple but straightforward digital image processing approach to be implemented in cloud computing for future studies.

Mobile Application Based on Convolutional Neural Networks for Pterygium Detection in Anterior Segment Eye Images at Ophthalmological Medical Centers

“…The set of ASPI images was provided by the Peruvian Pterygium Center [9] and the authors of the articles [4], [10], [11], [12]. There are 534 ASPIs, of which 474 were captured using a slit lamp and 60 were captured by smartphones.…”

“…In this article, we present the development of a system aimed at detecting Pterygium disease, which consists of a mobile application, using a detection model in the anterior segment of the eye images based on the ResNext50 Convolutional Neural Network (CNN) architecture trained with an external dataset provided by the Peruvian Pterygium Center [9] and the authors of the articles [4], [10], [11], [12]. Through this application, users can take a photograph using their phone's camera, allowing the detection of the presence and severity of pterygium in the patient (mild or advanced).…”

Semantic segmentation and image quality assessment of anterior segment images for smartphones

“…The models mentioned above are not specially designed for smartphone images. Only a few researchers are on semantic segmentation for anterior segment images captured by smartphones [15][16]. Pujari et al [15] studied the utility of smartphones in ophthalmology and pointed out that smartphones will further easy the clinicians work because they are small and handy tools.…”

“…Pujari et al [15] studied the utility of smartphones in ophthalmology and pointed out that smartphones will further easy the clinicians work because they are small and handy tools. Zamani et al [16] presented a qualitative measurement of anterior segment photographed images (ASPIs) through Otsu multi-thresholding approach without contrast enhancement. However, at the same time, there are many works on iris segmentation, similar to the semantic segmentation of anterior segment images.…”