Zihan Chen’s research while affiliated with Beijing University of Chemical Technology and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (3)


Rolling-Unet: Revitalizing MLP’s Ability to Efficiently Extract Long-Distance Dependencies for Medical Image Segmentation
  • Article

March 2024

·

5 Reads

·

4 Citations

Proceedings of the AAAI Conference on Artificial Intelligence

Yutong Liu

·

Haijiang Zhu

·

Mengting Liu

·

[...]

·

Jie Gao

Medical image segmentation methods based on deep learning network are mainly divided into CNN and Transformer. However, CNN struggles to capture long-distance dependencies, while Transformer suffers from high computational complexity and poor local feature learning. To efficiently extract and fuse local features and long-range dependencies, this paper proposes Rolling-Unet, which is a CNN model combined with MLP. Specifically, we propose the core R-MLP module, which is responsible for learning the long-distance dependency in a single direction of the whole image. By controlling and combining R-MLP modules in different directions, OR-MLP and DOR-MLP modules are formed to capture long-distance dependencies in multiple directions. Further, Lo2 block is proposed to encode both local context information and long-distance dependencies without excessive computational burden. Lo2 block has the same parameter size and computational complexity as a 3×3 convolution. The experimental results on four public datasets show that Rolling-Unet achieves superior performance compared to the state-of-the-art methods.


MSCA-UNet
Multi-scale module
Channel attention module
Global feature module
Segmentation results of each model on Suprapatellar Bursa Data set

+5

MSCA-UNet: multi-scale channel attention-based UNet for segmentation of medical ultrasound images
  • Article
  • Publisher preview available

March 2024

·

83 Reads

·

4 Citations

Cluster Computing

Since deep learning is introduced to medical image segmentation, UNet and its variants have been extensively applied in medical image analysis. This paper proposes a multi-scale channel attention UNet (MSCA-UNet) to raise the accuracy of the segmentation in medical ultrasound images. Specifically, a multi-scale module is constructed to connect and to enhance the feature maps with different scales extracted by convolution. Subsequently, A channel attention mechanism is designed to compress feature maps through learnable depth separable convolutions. Eventually, we have explored the global feature module to establish the dependency between multi-level features. The proposed method is thoroughly evaluated and compared with the existing methods on four medical ultrasound image datasets. The experiments indicate that our method outperforms the SOTA method in accuracy on four medical ultrasound image datasets. Compared with UNet network, the parameters of our model have decreased 29.82%. In addition, visual comparisons further demonstrate the proposed method.

View access options

Image-Based Measurement of Hand Parameters for Burn and Scald Treatments

October 2022

·

158 Reads

The therapeutic elastic gloves are of great help in the treatment of hand burns and scalds, making superficial and mild burns heal quickly without residual scars or damage to a patient’s functional ability. However, the hand data used to create the elastic gloves for burns and scalds are usually measured by workers. This manual measurement method has a high cost, large error, and unreliable results. In this paper, we propose an image-based parameter measurement method and establish a portable measuring system for finger and palm parameters; these parameters are then applied to create therapeutic gloves for burn and scald treatments. The proposed method can provide an accurate and rapid measurement of the finger and palm parameters. The experimental results for normal hand parameters and injured hand parameters show the effectiveness of the proposed method.

Citations (2)


... The architecture of our proposed TSFNet is shown in Fig. 1(a), extending the encoder-decoder structure with two main components: TIA-attention for effective text-image interaction and SFPM for spatial and frequency domain texture perception. The initial encoder-decoder layers employ standard 3x3 convolutions, while the fourth and bottleneck layers utilize RollingUnet's DOR-MLP (Double Orthogonal Rolling-MLP) [11] to capture long-range dependencies, enhanced by spatial awareness modules for finer texture details. Compared to Transformer-based architectures, this design significantly reduces computational complexity. ...

Reference:

TexLiverNet: Leveraging Medical Knowledge and Spatial-Frequency Perception for Enhanced Liver Tumor Segmentation
Rolling-Unet: Revitalizing MLP’s Ability to Efficiently Extract Long-Distance Dependencies for Medical Image Segmentation
  • Citing Article
  • March 2024

Proceedings of the AAAI Conference on Artificial Intelligence

... In the conventional UNet model, its core structure features a symmetrical encoder-decoder architecture equipped with skip connections to preserve feature information during the encoding process. This design has been widely modified and applied in segmentation tasks in fields such as medical imaging to optimize the capture of details and the utilization of contextual information [62][63][64]. However, the encoder part of the traditional UNet typically employs simple stacked convolutional layers, which may limit the performance of the model in processing complex images. ...

MSCA-UNet: multi-scale channel attention-based UNet for segmentation of medical ultrasound images

Cluster Computing