Abstract

ORTIZ-FEREGRINO, Rafael; TOVAR-ARRIAGA, Saúl; PEDRAZA-ORTEGA, Jesús Carlos  and  TAKACS, Andras. Retinal Lesion Segmentation Using Transfer Learning with an Encoder-Decoder CNN. Rev. mex. ing. bioméd [online]. 2022, vol.43, n.2, 1246.  Epub Oct 31, 2022. ISSN 2395-9126.  https://doi.org/10.17488/rmib.43.2.4.

Deep learning (DL) techniques achieve high performance in the detection of illnesses in retina images, but the majority of models are trained with different databases for solving one specific task. Consequently, there are currently no solutions that can be used for the detection/segmentation of a variety of illnesses in the retina in a single model. This research uses Transfer Learning (TL) to take advantage of previous knowledge generated during model training of illness detection to segment lesions with encoder-decoder Convolutional Neural Networks (CNN), where the encoders are classical models like VGG-16 and ResNet50 or variants with attention modules. This shows that it is possible to use a general methodology using a single fundus image database for the detection/segmentation of a variety of retinal diseases achieving state-of-the-art results. This model could be in practice more valuable since it can be trained with a more realistic database containing a broad spectrum of diseases to detect/segment illnesses without sacrificing performance. TL can help achieve fast convergence if the samples in the main task (Classification) and sub-tasks (Segmentation) are similar. If this requirement is not fulfilled, the parameters start from scratch.

Keywords : Transfer learning; Encoder-decoder; Retinal images; Lesion segmentation; Deep learning.

        · abstract in Spanish     · text in English     · English ( pdf )