Automatic Diabetic Retinopathy detection using BossaNova representation

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

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

9 Citations (Scopus)

Abstract

The biomedical community has shown a continued interest in automated detection of Diabetic Retinopathy (DR), with new imaging techniques, evolving diagnostic criteria, and advancing computing methods. Existing state of the art for detecting DR-related lesions tends to emphasize different, specific approaches for each type of lesion. However, recent research has aimed at general frameworks adaptable for large classes of lesions. In this paper, we follow this latter trend by exploring a very flexible framework, based upon two-tiered feature extraction (low-level and mid-level) from images and Support Vector Machines. The main contribution of this work is the evaluation of BossaNova, a recent and powerful mid-level image characterization technique, which we contrast with previous art based upon classical Bag of Visual Words (BoVW). The new technique using BossaNova achieves a detection performance (measured by area under the curve - AUC) of 96.4% for hard exudates, and 93.5% for red lesions using a cross-dataset training/testing protocol.
Original languageEnglish
Title of host publicationEMBC 2014
Subtitle of host publication36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society : Proceedings
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages146-149
Number of pages4
ISBN (Print)9781424479290
DOIs
Publication statusPublished - 2014
EventAnnual International Conference of the IEEE Engineering in Medicine and Biology Society (36th : 2014) - Chicago, IL
Duration: 26 Aug 201430 Aug 2014

Conference

ConferenceAnnual International Conference of the IEEE Engineering in Medicine and Biology Society (36th : 2014)
CityChicago, IL
Period26/08/1430/08/14

Fingerprint Dive into the research topics of 'Automatic Diabetic Retinopathy detection using BossaNova representation'. Together they form a unique fingerprint.

  • Cite this

    Pires, R., Avila, S., Jelinek, H. F., Wainer, J., Valle, E., & Rocha, A. (2014). Automatic Diabetic Retinopathy detection using BossaNova representation. In EMBC 2014: 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society : Proceedings (pp. 146-149). Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/EMBC.2014.6943550