Dense Segmentation in Selected Dimensions: Application to Retinal Optical Coherence Tomography


Bart Liefers, Cristina González-Gonzalo, Caroline Klaver, Bram van Ginneken, Clara I. Sánchez ;
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:337-346, 2019.


We present a novel convolutional neural network architecture designed for dense segmentation in a subset of the dimensions of the input data. The architecture takes an N-dimensional image as input, and produces a label for every pixel in M output dimensions, where 0 < M < N. Large context is incorporated by an encoder-decoder structure, while funneling shortcut subnetworks provide precise localization. We demonstrate applicability of the architecture on two problems in retinal optical coherence tomography: segmentation of geographic atrophy and segmentation of retinal layers. Performance is compared against two baseline methods, that leave out either the encoder-decoder structure or the shortcut subnetworks. For segmentation of geographic atrophy, an average Dice score of 0.49 ± 0.21 was obtained, compared to 0.46 ± 0.22 and 0.28 ± 0.19 for the baseline methods, respectively. For the layer-segmentation task, the proposed architecture achieved a mean absolute error of 1.305 ± 0.547 pixels compared to 1.967 ± 0.841 and 2.166 ± 0.886± for the baseline methods.

Related Material