Skip to main navigation Skip to search Skip to main content

Deep Residual Shrinkage Proximal-Point Mapping Network for Image Reconstruction

  • Yuan Xu
  • , Heng Wei Liao
  • , Da Ben Hao
  • , Yan Lin He
  • , Qun Xiong Zhu
  • , Tao Yong
  • , Zi Feng Xiao
  • , Yang Zhang
  • , Ming Qing Zhang
  • Beijing University of Chemical Technology
  • Ltd.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Image processing procedures in medical imaging are highly complex and are often affected by artifacts and noise, which impact image quality and diagnostic accuracy. To address this issue, we propose a novel deep residual shrinkage proximal-point mapping network (RSPPM-Net) aimed at enhancing image reconstruction performance through feature denoising. The innovation of RSPPM-Net lies in its integration of stochastic gradient descent modules and localized residual shrinkage proximal mapping modules, effectively reducing the interference of redundant features. Additionally, the network introduces a cascading module called the Fourier residual shrinkage block (FRSBlock) to correct potential biases between the input and output signals. FRSBlock integrates a residual FFT block and two identical adaptive blocks, each formed by cascading a global average pooling layer, a fully connected layer, a batch normalization layer, and an activation function. Through this architecture, FRSBlock can adaptively generate and adjust denoising thresholds based on the input data, achieving localized multi-level denoising and precise signal correction. To validate the effectiveness of RSPPM-Net, we conducted extensive reconstruction experiments on orthopedic joint imaging datasets. Experimental results demonstrate that RSPPM-Net exhibits superior performance in image recovery quality, significantly improving the clarity and accuracy of reconstructed images.

Original languageEnglish
Title of host publicationProceedings of the 37th Chinese Control and Decision Conference, CCDC 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3415-3420
Number of pages6
ISBN (Electronic)9798331510565
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event37th Chinese Control and Decision Conference, CCDC 2025 - Xiamen, China
Duration: 16 May 2025 → 19 May 2025

Publication series

NameProceedings of the 37th Chinese Control and Decision Conference, CCDC 2025

Conference

Conference37th Chinese Control and Decision Conference, CCDC 2025
Country/TerritoryChina
CityXiamen
Period16/05/25 → 19/05/25

Keywords

  • Deep residual shrinkage proximal-point mapping network
  • Fourier residual shrinkage block
  • Image reconstruction
  • Multi-stage cascading adaptive module

Fingerprint

Dive into the research topics of 'Deep Residual Shrinkage Proximal-Point Mapping Network for Image Reconstruction'. Together they form a unique fingerprint.

Cite this