TY - GEN
T1 - Automatic Diabetic Retinopathy detection using BossaNova representation
AU - Pires, Ramon
AU - Avila, Sandra
AU - Jelinek, Herbert F.
AU - Wainer, Jacques
AU - Valle, Eduardo
AU - Rocha, Anderson
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/11/2
Y1 - 2014/11/2
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84929456977&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2014.6943550
DO - 10.1109/EMBC.2014.6943550
M3 - Conference contribution
C2 - 25569918
AN - SCOPUS:84929456977
T3 - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
SP - 146
EP - 149
BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
Y2 - 26 August 2014 through 30 August 2014
ER -