MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation

Abstract

Biomedical image segmentation plays a central role in quantitative analysis, clinical diagnosis, and medical intervention. In the light of the fully convolutional networks (FCN) and U-Net, deep convolutional networks (DNNs) have made significant contributions to biomedical image segmentation applications. In this paper, we propose three different multi-scale dense connections (MDC) for the encoder, the decoder of U-shaped architectures, and across them. Based on three dense connections, we propose a multi-scale densely connected U-Net (MDU-Net) for biomedical image segmentation. MDU-Net directly fuses the neighboring feature maps with different scales from both higher layers and lower layers to strengthen feature propagation in the current layer. Multi-scale dense connections, which contain shorter connections between layers close to the input and output, also make a much deeper U-Net possible. Besides, we introduce quantization to alleviate the potential overfitting in dense connections, and further improve the segmentation performance. We evaluate our proposed model on the MICCAI 2015 Gland Segmentation (GlaS) dataset. The three MDC improve U-Net performance by up to 1.8% on test A and 3.5% on test B in the MICCAI Gland dataset. Meanwhile, the MDU-Net with quantization obviously improves the segmentation performance of original U-Net.

arXiv comment10 pages, 5 figures, 6 tables, published in the Health Information Science and Systems journal

References in corpus (3)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal

Cited by in corpus (5)

• R2U++: A Multiscale Recurrent Residual U-Net with Dense Skip Connections for Medical Image Segmentation
• RRCANet: Recurrent Reusable-Convolution Attention Network for Infrared Small Target Detection
• Deep Negative Volume Segmentation
• Multiclass Segmentation using Teeth Attention Modules for Dental X-ray Images
• IODeep: an IOD for the introduction of deep learning in the DICOM standard