Microaneurysm detection in color eye fundus images for diabetic retinopathy screening
Tânia Melo1, Ana Maria Mendonça1, Aurélio Campilho1
1Institute for Systems and Computer Engineering, Technology and Science, Campus da Faculdade de Engenharia da Universidade Do Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal; Faculty of Engineering of the University of Porto, Rua Dr. Roberto Frias, S/n 4200-465, Porto, Portugal.
Abstract:
Diabetic retinopathy (DR) is a diabetes complication, which in extreme situations may lead to blindness. Since the first stages are often asymptomatic, regular eye examinations are required for an early diagnosis. As microaneurysms (MAs) are one of the first signs of DR, several automated methods have been proposed for their detection in order to reduce the ophthalmologists' workload. Although local convergence filters (LCFs) have already been applied for feature extraction, their potential as MA enhancement operators was not explored yet. In this work, we propose a sliding band filter for MA enhancement aiming at obtaining a set of initial MA candidates. Then, a combination of the filter responses with color, contrast and shape information is used by an ensemble of classifiers for final candidate classification. Finally, for each eye fundus image, a score is computed from the confidence values assigned to the MAs detected in the image. The performance of the proposed methodology was evaluated in four datasets. At the lesion level, sensitivities of 64% and 81% were achieved for an average of 8 false positives per image (FPIs) in e-ophtha MA and SCREEN-DR, respectively. In the last dataset, an AUC of 0.83 was also obtained for DR detection.
Insights
This study introduces a new automated method for detecting microaneurysms (MAs), an early sign of diabetic retinopathy (DR). The approach enhances MA detection, aiding in earlier diagnosis and potentially preventing blindness caused by diabetes.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Diabetic retinopathy (DR) is a leading cause of blindness, often asymptomatic in early stages.
- Early diagnosis through regular eye exams is crucial for preventing vision loss.
- Automated detection of microaneurysms (MAs), an initial DR sign, can assist ophthalmologists.
Purpose of the Study:
- To develop and evaluate a novel automated method for microaneurysm (MA) enhancement and detection in retinal fundus images.
- To improve the early diagnosis of diabetic retinopathy (DR).
Main Methods:
- A sliding band filter was proposed for MA enhancement to identify candidate lesions.
- Ensemble classifiers combined filter responses with color, contrast, and shape features for classification.
- A confidence score was computed for detected MAs in each image.
Main Results:
- The method achieved sensitivities of 64% and 81% at the lesion level on the e-ophtha MA and SCREEN-DR datasets, respectively.
- An average of 8 false positives per image (FPIs) was reported.
- An Area Under the Curve (AUC) of 0.83 was obtained for DR detection on a separate dataset.
Conclusions:
- The proposed method shows promise for automated MA detection and DR screening.
- This technique could potentially reduce the workload for ophthalmologists and improve early DR diagnosis.
- Further validation on diverse datasets is warranted.
