3D Randomized Connection Network with Graph-based Label Inference

TL;DR

This paper introduces a novel 3D deep learning network with randomized connections and graph-based label inference for brain MRI segmentation, improving network capacity and performance.

Contribution

It proposes a new 3D network architecture with randomized connections and a graph-based label inference method, enhancing segmentation accuracy.

Findings

Achieved competitive results on public brain MRI datasets.

Demonstrated improved network capacity and segmentation performance.

Validated effectiveness of graph-based label inference.

Abstract

In this paper, a novel 3D deep learning network is proposed for brain MR image segmentation with randomized connection, which can decrease the dependency between layers and increase the network capacity. The convolutional LSTM and 3D convolution are employed as network units to capture the long-term and short-term 3D properties respectively. To assemble these two kinds of spatial-temporal information and refine the deep learning outcomes, we further introduce an efficient graph-based node selection and label inference method. Experiments have been carried out on two publicly available databases and results demonstrate that the proposed method can obtain competitive performances as compared with other state-of-the-art methods.