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

• URL: http://arxiv.org/abs/1812.00352v3
• Date: Mon, 18 Mar 2024 08:09:10 GMT
• Title: MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation
• Authors: Jiawei Zhang, Yuzhen Jin, Jilan Xu, Xiaowei Xu, Yanchun Zhang,
• Abstract summary: Deep convolutional networks (DNNs) have made significant contributions to biomedical image segmentation applications. We propose three different multi-scale dense connections (MDC) for the encoder, the decoder of U-shaped architectures, and across them. The three MDC improve U-Net performance by up to 1.8% on test A and 3.5% on test B in the MICCAI 2015 Gland dataset.
• Score: 13.666802097122396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• MAProtoNet: A Multi-scale Attentive Interpretable Prototypical Part Network for 3D Magnetic Resonance Imaging Brain Tumor Classification [25.056170817680403]
  We propose a Multi-scale Attentive Prototypical part Network, termed MAProtoNet, to provide more precise maps for attribution. Specifically, we introduce a concise multi-scale module to merge attentive features from quadruplet attention layers, and produces attribution maps. Compared to existing interpretable part networks in medical imaging, MAProtoNet can achieve state-of-the-art performance in localization.
  arXiv  Detail & Related papers  (2024-04-13T07:30:17Z)
• M$^{2}$SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation [73.10707675345253]
  We propose a general multi-scale in multi-scale subtraction network (M$2$SNet) to finish diverse segmentation from medical image. Our method performs favorably against most state-of-the-art methods under different evaluation metrics on eleven datasets of four different medical image segmentation tasks.
  arXiv  Detail & Related papers  (2023-03-20T06:26:49Z)
• Dual Multi-scale Mean Teacher Network for Semi-supervised Infection Segmentation in Chest CT Volume for COVID-19 [76.51091445670596]
  Automated detecting lung infections from computed tomography (CT) data plays an important role for combating COVID-19. Most current COVID-19 infection segmentation methods mainly relied on 2D CT images, which lack 3D sequential constraint. Existing 3D CT segmentation methods focus on single-scale representations, which do not achieve the multiple level receptive field sizes on 3D volume.
  arXiv  Detail & Related papers  (2022-11-10T13:11:21Z)
• UNet#: A UNet-like Redesigning Skip Connections for Medical Image Segmentation [13.767615201220138]
  We propose a novel network structure combining dense skip connections and full-scale skip connections, named UNet-sharp (UNet#) for its shape similar to symbol #. The proposed UNet# can aggregate feature maps of different scales in the decoder sub-network and capture fine-grained details and coarse-grained semantics from the full scale.
  arXiv  Detail & Related papers  (2022-05-24T03:40:48Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Mutual Attention-based Hybrid Dimensional Network for Multimodal Imaging Computer-aided Diagnosis [4.657804635843888]
  We propose a novel mutual attention-based hybrid dimensional network for MultiModal 3D medical image classification (MMNet) The hybrid dimensional network integrates 2D CNN with 3D convolution modules to generate deeper and more informative feature maps. We further design a mutual attention framework in the network to build the region-wise consistency in similar stereoscopic regions of different image modalities.
  arXiv  Detail & Related papers  (2022-01-24T02:31:25Z)
• DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets [102.55303521877933]
  We propose a dynamic on-demand network (DoDNet) that learns to segment multiple organs and tumors on partially labelled datasets. DoDNet consists of a shared encoder-decoder architecture, a task encoding module, a controller for generating dynamic convolution filters, and a single but dynamic segmentation head.
  arXiv  Detail & Related papers  (2020-11-20T04:56:39Z)
• KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation [71.79090083883403]
  "Traditional" encoder-decoder based approaches perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. We propose KiU-Net which has two branches: (1) an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U-Net which learns high level features. The proposed method achieves a better performance as compared to all the recent methods with an additional benefit of fewer parameters and faster convergence.
  arXiv  Detail & Related papers  (2020-10-04T19:23:33Z)
• KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations [59.65174244047216]
  We propose an over-complete architecture (Ki-Net) which involves projecting the data onto higher dimensions. This network, when augmented with U-Net, results in significant improvements in the case of segmenting small anatomical landmarks. We evaluate the proposed method on the task of brain anatomy segmentation from 2D Ultrasound of preterm neonates.
  arXiv  Detail & Related papers  (2020-06-08T18:59:24Z)
• CAggNet: Crossing Aggregation Network for Medical Image Segmentation [4.56877715768796]
  Crossing Aggregation Network (CAggNet) is a novel densely connected semantic segmentation approach for medical image analysis. In CAggNet, the simple skip connection structure of general U-Net is replaced by aggregations of multi-level down-sampling and up-sampling layers. We have evaluated and compared our CAggNet with several advanced U-Net based methods in two public medical image datasets.
  arXiv  Detail & Related papers  (2020-04-16T15:39:38Z)
• Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation [32.96604621259756]
  We propose an extension of U-Net for medical image segmentation. We take full advantages of U-Net, Squeeze and Excitation (SE) block, bi-directional ConvLSTM (BConvLSTM), and the mechanism of dense convolutions. The proposed model is evaluated on six datasets.
  arXiv  Detail & Related papers  (2020-03-10T12:29:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.