Exudate Segmentation on Retinal Atlas Space

Sharib Ali (1) , Kedir Adal (1) , Désiré Sidibé (1) , T.P. Karnowski (2) , M.D. Edward Chaum (3) , Fabrice Meriaudeau (1)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
2 ORNL - Oak Ridge National Laboratory [Oak Ridge]
3 Hamilton Eye Institute

Diabetic macular edema is characterized by hard exudates. Presence of such exudates cause vision loss in the affected areas. We present a novel approach of segmenting exudates for screening and follow-ups by building an ethnicity based statistical atlas. The chromatic distribution in such an atlas gives a good measure of probability of the pixels belonging to the healthy retinal pigments or to the abnormalities (like lesions, imaging artifacts etc.) in the retinal fundus image. Post-processing schemes are introduced in this paper for the enhancement of the edges of such exudates for final segmentation and to separate lesion from false positives. A sensitivity(recall) of 82.5 % at 35% of positive predictive value on FROC-curve is achieved. Results are obtained on a publicly available HEI-MED data-set and have been compared to two reference methods on the same dataset showing the competitiveness of the proposed algorithm.

Mots clés: Exudate segmentation; Retinal atlas; Riesz transform

Domaines: Traitement des images [eess.IV]

Sharib Ali, Kedir Adal, Désiré Sidibé, T.P. Karnowski, M.D. Edward Chaum, et al.. Exudate Segmentation on Retinal Atlas Space. International Symposium on Image and Signal Processing and Analysis, Sep 2013, Trieste, Italy. pp.5. ⟨hal-00854653v2⟩