Abstract
ABSTRACTElectron microscopy (EM) enables imaging at nanometer resolution and can shed light on how cancer evolves to develop resistance to therapy. Acquiring these images has become a routine task; however, analyzing them is now the bottleneck, as manual structure identification is very time-consuming and can take up to several months for a single sample. Deep learning approaches offer a suitable solution to speed up the analysis. In this work, we present a study of several state-of-the-art deep learning models for the task of segmenting nuclei and nucleoli in volumes from tumor biopsies. We compared previous results obtained with the ResUNet architecture to the more recent UNet++, FracTALResNet, SenFormer, and CEECNet models. In addition, we explored the utilization of unlabeled images through semi-supervised learning with Cross Pseudo Supervision. We have trained and evaluated all of the models on sparse manual labels from three fully annotated in-house datasets that we have made available on demand, demonstrating improvements in terms of 3D Dice score. From the analysis of these results, we drew conclusions on the relative gains of using more complex models, semi-supervised learning as well as next steps for the mitigation of the manual segmentation bottleneck.
Publisher
Cold Spring Harbor Laboratory
Reference24 articles.
1. Tumor microenvironment complexity and therapeutic implications at a glance
2. Bousselham, W. , Thibault, G. , Pagano, L. , Machireddy, A. , Gray, J. , Chang, Y. H. , et al. (2021). Efficient self-ensemble framework for semantic segmentation
3. Imaging three-dimensional tissue architectures by focused ion beam scanning electron microscopy
4. Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
5. Looking for Change? Roll the Dice and Demand Attention