Deep Variational Segmentation of Topology-Constrained Object Sets, with Correlated Uncertainty Models, for Robustness to Degradations
Akshay V. Gaikwad, Harshit Varma, Suyash P. Awate · 2023
Some key applications in medical image segmentation involve object complexes having specific topologies, but typical deep neural networks (DNNs) ignore such topologies. We propose a novel DNN framework to model topology-constrained object boundaries, incorporating both individual-object and multi-object topology constraints. Unlike typical DNNs, our topology-constrained DNN makes the learning significantly more robust to out-of-distribution images. Moreover, our DNN combines variational modeling in latent-space with uncertainty modeling of boundary points along with inter-point correlations. Results on publicly available datasets show our framework to outperform existing methods.