Sanchez, SergioVallez, NoeliaBueno, GloriaMarrugo, Andres G2024-11-292024-11-292024-11-122024-11-29Sanchez S, Vallez N, Bueno G, Marrugo AG (2024) Data augmentation via warping transforms for modeling natural variability in the corneal endothelium enhances semi-supervised segmentation. PLoS ONE 19(11): e0311849. https://doi.org/10.1371/journal.pone.0311849https://hdl.handle.net/20.500.12585/12773Image segmentation of the corneal endothelium with deep convolutional neural networks (CNN) is challenging due to the scarcity of expert-annotated data. This work proposes a data augmentation technique via warping to enhance the performance of semi-supervised training of CNNs for accurate segmentation. We use a unique augmentation process for images and masks involving keypoint extraction, Delaunay triangulation, local affine transformations, and mask refinement. This approach accurately captures the natural variability of the corneal endothelium, enriching the dataset with realistic and diverse images. The proposed method achieved an increase in the mean intersection over union (mIoU) and Dice coefficient (DC) metrics of 17.2% and 4.8% respectively, for the segmentation task in corneal endothelial images on multiple CNN architectures. Our data augmentation strategy successfully models the natural variability in corneal endothelial images, thereby enhancing the performance and generalization capabilities of semi-supervised CNNs in medical image cell segmentation tasks.18 páginasapplication/pdfenghttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/article10.1371/journal.pone.0311849Data augmentationWarping transformsCorneal endotheliumSemi-supervised segmentationDeep convolutional neural networks (CNNs)Image segmentationMedical imagingKeypoint extractionDelaunay triangulationAffine transformationsMask refinement Mean intersection over union (mIoU)Dice coefficient (DC)Natural variabilityMedical image cell segmentationinfo:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivatives 4.0 InternacionalUniversidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarLEMB