Automatic microaneurysm detection using laws texture masks and support vector machines

Abstract

Microaneurysms are one of the first clinical signs of diabetic retinopathy, and their detection is crucial for an early diagnosis of the disease. In this contribution, an approach based on Laws texture features to detect microaneurysms is presented. The proposed algorithm uses support vector machines (SVM) in two classification phases. The first SVM performs a pixel-based classification to find the microaneurysm candidates. The second SVM performs an object classification, aiming to reduce the false detections of the first classifier. The algorithm performance was evaluated on three public data-sets. The results show sensitivities of 62, 66 and 32%, for an average number of 10 false positives per image, in LaTIM, e-ophtha and ROC databases, respectively. Laws texture masks proved to be good features to detect microaneurysm candidates. Moreover, the second classification phase achieved to reducing the false detections.

Keywords:

• Microaneurysm (MA)
• laws texture masks
• fundus image processing
• support vector machines (SVM)

Acknowledgments

Diana Veiga thanks the FCT for the SFRH/BDE/51824/2012 and ENERMETER. We would also like to express our gratitude to the anonymous reviewers for their valuable remarks which benefit the revision of this paper.

Notes

1. http://docs.opencv.org/2.4/modules/ml/doc/support_vector_machines.html.

2. See note 1.

3. See note 1.