The Influence of Image Morphology on Neural Network-Based Segmentation Results

In this article, we have provided initial results of evaluating the influence of trainingdata morphology on convolutional neural networks segmentation quality. To do this, we selected4 different soil samples and segmented them using an unsupervised converging active contoursalgorithm. With the help of synthetic tomography algorithm, we obtained a true CT – ground-truth pairs for these soil samples. Then we acquired a set of samples with varying degrees ofmorphological properties similarity with the original soil samples by stochastic reconstructions. Inorder to check the effect of morphological properties on the quality of segmentation, we trained anU-Net model with ResNet50 encoder on pairs of synthetic CT – ground-truth data from the initialsoil samples, and assessed the segmentation quality of synthetic CT obtained from stochasticallyreconstructed samples. Based on the metrics, we concluded that the quality of segmentation ismore influenced by the morphological differences of the original soil samples than by differencefrom the generated stochastic reconstructions. We discussed possible ways to improve the futureexperiments design in order to finally close the issue outlined in this work.
Advances in Systems Science and Applications, Выпуск 4 2022, Pages 31-50