Beyond Lesion-Based Diabetic Retinopathy: A Direct Approach for Referral

Author(s)

Pires, Ramon ; Avila, Sandra ; Jelinek, Herbert F. ; Wainer, Jacques ; Valle, Eduardo ; Rocha, Anderson

• Document type: Journal article
• Source: IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS; v. 21, n. 1, p. 193-200, JAN 2017.
• Web of Science Citations: 6

Abstract

Diabetic retinopathy (DR) is the leading cause of blindness in adults, but can be managed if detected early. Automated DR screening helps by indicating which patients should be referred to the doctor. However, current techniques of automated screening still depend too much on the detection of individual lesions. In this study, we bypass lesion detection, and directly train a classifier for DR referral. Additional novelties are the use of state-of-the-art mid-level features for the retinal images: BossaNova and Fisher Vector. Those features extend the classical Bags of Visual Words and greatly improve the accuracy of complex classification tasks. The proposed technique for direct referral is promising, achieving an area under the curve of 96.4%, thus, reducing the classification error by almost 40% over the current state of the art, held by lesion-based techniques. (AU)

• FAPESP's process: 08/54443-2 - Automated screening for diabetic retinopathies: IT in the fight against preventable blindness
• Grantee: Jacques Wainer
• Support Opportunities: Regular Research Grants
• FAPESP's process: 10/05647-4 - Digital forensics: collection, organization, classification and analysis of digital evidences
• Grantee: Anderson de Rezende Rocha
• Support Opportunities: Research Grants - Young Investigators Grants