3D Quantum-inspired Self-supervised Tensor Network for Volumetric
Segmentation of Medical Images
Abstract
This paper introduces a novel shallow 3D self-supervised tensor neural
network for volumetric segmentation of medical images with merits of
obviating training and supervision. The proposed network is referred to
as 3D Quantum-inspired Self-supervised Tensor Neural Network (3D-QNet).
The underlying architecture of 3D-QNet is composed of a trinity of
volumetric layers viz. input, intermediate and output layers
inter-connected using an S-connected third-order neighborhood-based
topology for voxel-wise processing of 3D medical image data suitable for
semantic segmentation. Each of the volumetric layers contains quantum
neurons designated by qubits or quantum bits. The incorporation of
tensor decomposition in quantum formalism leads to faster convergence of
the network operations to preclude the inherent slow convergence
problems faced by the classical supervised and self-supervised networks.
The segmented volumes are obtained once the network converges. The
suggested 3D-QNet is tailored and tested on the BRATS 2019 Brain MR
image data set and Liver Tumor Segmentation Challenge (LiTS17) data set
extensively in our experiments. 3D-QNet has achieved promising dice
similarity as compared to the intensively supervised convolutional
network-based models like 3D-UNet, Vox-ResNet, DRINet, and 3D-ESPNet,
showing a potential advantage of our self-supervised shallow network on
facilitating semantic segmentation.