VolumeNet: A Lightweight Parallel Network for Super-Resolution of Medical Volumetric Data

TL;DR

VolumeNet is a lightweight 3D CNN designed for super-resolution of medical volumetric data, achieving high accuracy with fewer parameters by using parallel connections and a novel Queue module.

Contribution

The paper introduces VolumeNet, a novel lightweight 3D CNN with parallel connections and a new Queue module for efficient super-resolution of medical volumetric data.

Findings

VolumeNet reduces model parameters significantly.

Achieves high super-resolution accuracy on medical data.

Outperforms state-of-the-art methods in precision.

Abstract

Deep learning-based super-resolution (SR) techniques have generally achieved excellent performance in the computer vision field. Recently, it has been proven that three-dimensional (3D) SR for medical volumetric data delivers better visual results than conventional two-dimensional (2D) processing. However, deepening and widening 3D networks increases training difficulty significantly due to the large number of parameters and small number of training samples. Thus, we propose a 3D convolutional neural network (CNN) for SR of medical volumetric data called ParallelNet using parallel connections. We construct a parallel connection structure based on the group convolution and feature aggregation to build a 3D CNN that is as wide as possible with few parameters. As a result, the model thoroughly learns more feature maps with larger receptive fields. In addition, to further improve accuracy, we present an efficient version of ParallelNet (called VolumeNet), which reduces the number of parameters and deepens ParallelNet using a proposed lightweight building block module called the Queue module. Unlike most lightweight CNNs based on depthwise convolutions, the Queue module is primarily constructed using separable 2D cross-channel convolutions. As a result, the number of network parameters and computational complexity can be reduced significantly while maintaining accuracy due to full channel fusion. Experimental results demonstrate that the proposed VolumeNet significantly reduces the number of model parameters and achieves high precision results compared to state-of-the-art methods.