Glaucoma eye screening using robotic process automation and machine learning

Name: Panaree Chaipayom

LCSH: Kasetsart University -- Theses. M.Eng. (Information and Communication Technology for Embedded Systems) 2020

Classification :.LCCS: TJ211

LCSH: Kasetsart University. -- Department of Electrical Engineering -- Theses

LCSH: Robotics

LCSH: Machine learning

LCSH: Image processing

LCSH: Medical screening

LCSH: Glaucoma

Abstract: Glaucoma is the second’s eye disease that can cause blindness. Current medical treatment cannot cure the disease. However, it can prolong the blindness if early preventive treatments are given. Glaucoma detection on a population basis, mass glaucoma screening, can reduce a number of undiagnosed glaucoma condition and help catch glaucoma early. Therefore, identifying Glaucoma as soon as possible can reduce the risk of being blind. Many methods and technologies are developed for glaucoma screening. In this study, we design a glaucoma screening system which incorporate robotic process automation (RPA) and machine learning (ML) technologies to assist others components of the conventional screening system. Robotic process automation is mainly used as a tool for transferring data such as patient history, fundus images between central ERP and a mobile application, which works as user interface. ML modules are used for analyzing Optic Disc and diagnosing glaucoma condition. The ML’ results assists ophthalmologists in evaluation and decision. In this thesis, two algorithms of Optic Disc Assessments, and single and fused features based glaucoma detections are investigated. The design framework of RPA and ML glaucoma screening system and its developed mobile application are presented. The application is easy to use. The users recommend of enlarged font size and separation interface between general users and technician users. With RPA and ML, results show that RPA decreases work duration by 75% and diagnosis accuracy depends on image database, feature extractions and classifications. In this work, fused feature with linear SVM classifier generally yields higher accuracy than single feature.

Kasetsart University. Office of the University Library

Address: Bangkok

Email: tdckulib@ku.ac.th

Name: Somying Thainimit

Role: Thesis Advisor

Created: 2020

Modified: 2025-07-09

Issued: 2025-07-09

วิทยานิพนธ์/Thesis

application/pdf

URL: https://www.lib.ku.ac.th/KUthesis/2563/panaree-cha-all.pdf

CallNumber: TJ211 .P37

eng

DegreeName: Master of Engineering

Level: Master's Degree

Descipline: Information and Communication Technology for Embedded System

Grantor: Kasetsart University

©copyrights Kasetsart University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	panaree-cha-all.pdf	3.16 MB

ใช้เวลา

0.031863 วินาที