DT-Net: A novel network based on multi-directional integrated convolution and threshold convolution

TL;DR

DT-Net introduces multi-directional integrated convolution and threshold convolution strategies to improve feature extraction and reduce redundancy, achieving state-of-the-art medical image segmentation results with enhanced robustness.

Contribution

The paper proposes DT-Net, a novel end-to-end segmentation network utilizing multi-directional integrated convolution and a thresholding strategy for better feature mining and redundancy reduction.

Findings

Achieves state-of-the-art results on public datasets.

Improves robustness over existing segmentation algorithms.

Effectively reduces redundant features and computational complexity.

Abstract

Since medical image data sets contain few samples and singular features, lesions are viewed as highly similar to other tissues. The traditional neural network has a limited ability to learn features. Even if a host of feature maps is expanded to obtain more semantic information, the accuracy of segmenting the final medical image is slightly improved, and the features are excessively redundant. To solve the above problems, in this paper, we propose a novel end-to-end semantic segmentation algorithm, DT-Net, and use two new convolution strategies to better achieve end-to-end semantic segmentation of medical images. 1. In the feature mining and feature fusion stage, we construct a multi-directional integrated convolution (MDIC). The core idea is to use the multi-scale convolution to enhance the local multi-directional feature maps to generate enhanced feature maps and to mine the generated features that contain more semantics without increasing the number of feature maps. 2. We also aim to further excavate and retain more meaningful deep features reduce a host of noise features in the training process. Therefore, we propose a convolution thresholding strategy. The central idea is to set a threshold to eliminate a large number of redundant features and reduce computational complexity. Through the two strategies proposed above, the algorithm proposed in this paper produces state-of-the-art results on two public medical image datasets. We prove in detail that our proposed strategy plays an important role in feature mining and eliminating redundant features. Compared with the existing semantic segmentation algorithms, our proposed algorithm has better robustness.