Automated screening for diabetic retinopathies: IT in the fight against preventable blindness

• Grant number: 08/54443-2
• Support Opportunities: Regular Research Grants
• Start date: November 01, 2008
• End date: June 30, 2011
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Agreement: Microsoft Research
• Principal Investigator: Jacques Wainer
• Grantee: Jacques Wainer
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• City of the host institution: Campinas

Abstract

This study has the following objectives: 1) To develop a system for screening patients that will accurately detect cases of diabetic retinopathy through dilated eye examination – The system will be used as an automated retinopathy classification system, distinguishing between normal images (patients who do not require further attention) and images suggestive of retinopathy (patients who require the attention of a specialist). Therefore, specialists will not need to examine patients in whom no change in the fundus oculi is expected, allowing the specialists to do their job more efficiently. The expectation is that this system will produce few false-negative results (i.e., not detecting retinopathy when it is present), because an indication that there is no change in the fundus oculi Jacques Wainer Institute of Computer Science / State University of Campinas (Unicamp) would exclude the patient in question from receiving the attention of a specialist. The system should detect the following changes, all of which are suggestive of diabetic retinopathy: hemorrhage, exudates, vascular changes, scarring, hyperpigmentation, and hypopigmentation. The initial version of the system will not detect macular edema, which is also associated with diabetes. 2) To implement the system in a true teleophthalmology service, in which only images suggestive of disorder will be referred to specialists – This deployment is aimed at assessing the system “in production” and assessing the needs of infrastructure and organizational requirements for maintaining a diabetic retinopathy teleophthalmology service with automated support. (AU)

Scientific publications

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

PIRES, RAMON; CARVALHO, TIAGO; SPURLING, GEOFFREY; GOLDENSTEIN, SIOME; WAINER, JACQUES; LUCKIE, ALAN; JELINEK, HERBERT F.; ROCHA, ANDERSON. Automated Multi-Lesion Detection for Referable Diabetic Retinopathy in Indigenous Health Care. PLoS One, v. 10, n. 6, JUN 2 2015. (08/54443-2, 10/05647-4)

ROCHA, ANDERSON; HAUAGGE, DANIEL C.; WAINER, JACQUES; GOLDENSTEIN, SIOME. Automatic fruit and vegetable classification from images. COMPUTERS AND ELECTRONICS IN AGRICULTURE, v. 70, n. 1, p. 96-104, JAN 2010. (07/52015-0, 08/08681-9, 05/58103-3, 08/54443-2)

PIRES, RAMON; AVILA, SANDRA; JELINEK, HERBERT F.; WAINER, JACQUES; VALLE, EDUARDO; ROCHA, ANDERSON. Beyond Lesion-Based Diabetic Retinopathy: A Direct Approach for Referral. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, v. 21, n. 1, p. 193-200, JAN 2017. (08/54443-2, 10/05647-4)