%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2023/09.22.03.26
%2 sid.inpe.br/sibgrapi/2023/09.22.03.26.48
%T Retinal images registration via unsupervised deep learning
%D 2023
%A Benvenuto, Giovana Augusta,
%A Casaca, Wallace,
%@affiliation UNESP
%@affiliation UNESP
%E Clua, Esteban Walter Gonzalez,
%E Körting, Thales Sehn,
%E Paulovich, Fernando Vieira,
%E Feris, Rogerio,
%B Conference on Graphics, Patterns and Images, 36 (SIBGRAPI)
%C Rio Grande, RS
%8 Nov. 06-09, 2023
%S Proceedings
%K Image registration, image processing, deep learning, retina.
%X In ophthalmology and vision science applications, aligning a pair of retinal images is of paramount importance to support disease diagnosis and routine eye examinations. This paper introduces an end-to-end framework capable of learning the registration task in a fully unsupervised manner. The proposed approach combines Convolutional Neural Networks and Spatial Transformer Network into a unified pipeline that incorporates a similarity metric to gauge the difference between the images, enabling image alignment without requiring any ground-truth data. The validation study demonstrates that the model can successfully deal with several categories of fundus images, surpassing other recent techniques for retinal registration.
%@language en
%3 Benvenuto_CRWTD_Sibigrapi2023.pdf