Multi-task Convolutional Neural Networks for the End-to-end Simultaneous Segmentation and Screening of the Epiretinal Membrane in OCT Images

Gende, M.Moura, Joaquim dePenedo, ManuelNovo Buján, JorgeOrtega Hortas, Marcos2024-05-032024-05-032023-02-16M. Gende, J. D. Moura, J. Novo, M. F. González Penedo, y M. Ortega, «Multi-task Convolutional Neural Networks for the End-to-end Simultaneous Segmentation and Screening of the Epiretinal Membrane in OCT Images», In: Alvaro Leitao and Lucía Ramos (editors). Proceedings of V XoveTIC Conference. XoveTIC 2022, Kalpa Publications in Computing, vol 14, pp. 77-73. doi: 10.29007/xxh7.2515-1762http://hdl.handle.net/2183/36401V Congreso XoveTIC, organizado por el Centro de Investigación en TIC da Universidade da Coruña (CITIC), 5 y 6 de octubre de 2022, A Coruña.[Absctract]: The Epiretinal Membrane (ERM) is an ocular pathology that causes visual distortion. In order to detect and treat the ERM, ophthalmologists visually inspect Optical Coherence Tomography (OCT) images.This is a costly and subjective process. In this work, we present three different fully automatic, end-to-end approaches that make use of multi-task learning to simultaneously screen for and segment ERM symptoms in OCT images. These approaches were implemented into three architectures that capitalise on the way the models share a single architecture for the two complementary tasks.engDeep learningEpiretinal membraneMulti-task learningOptical Coherence TomographyMulti-task Convolutional Neural Networks for the End-to-end Simultaneous Segmentation and Screening of the Epiretinal Membrane in OCT Imagesconference outputopen access