Asymmetric decoder design for efficient convolutional encoder-decoder architectures in medical image reconstruction

Tahsin Rahman, Ali Bilgin, Sergio Cabrera

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


In recent years, significant research has been performed on developing powerful and efficient Convolutional Neural Network (CNN) architectures. To utilize these architectures in pixel-level regression tasks such as tomographic image reconstruction, a feature extraction encoder is often combined with a symmetrical decoder to generate an encoder-decoder structure, such as a U-Net. However, a more powerful decoder focusing on high-frequency features can provide higher pixel-level accuracy. In this work, we investigate the use of asymmetrical encoder-decoder architectures in medical image reconstruction tasks. The state-of-the-art EfficientNet architecture utilizes depthwise convolutions and channel attention within inverted residual bottleneck blocks to generate highly compressed features while maintaining a significant FLOPS efficiency advantage compared to regular convolutional encoders. We develop an asymmetric encoder-decoder architecture, which uses the EfficientNet as an encoder. The proposed decoder architecture combines the multi-resolution features generated by the EfficientNet encoder using an incremental feature expansion strategy, which leads to better preservation of the structural details in reconstructed images. We have tested our asymmetrical encoder-decoder approach on undersampled MRI reconstruction tasks using the Calgary Campinas multi-channel brain MR dataset. Results demonstrate that the proposed asymmetric approach vastly outperforms a symmetric Efficient U-Net, achieving a 3dB improvement in PSNR. SSIM was also improved, and the asymmetric network was found to recover small structural details more effectively. Furthermore, the proposed asymmetric Efficient U-Net provides a four-fold reduction in inference time when compared to the conventional U-Net architecture.

Original languageEnglish (US)
Title of host publicationMultimodal Biomedical Imaging XVII
EditorsFred S. Azar, Xavier Intes, Qianqian Fang
ISBN (Electronic)9781510647756
StatePublished - 2022
EventMultimodal Biomedical Imaging XVII 2022 - San Francisco, United States
Duration: Jan 22 2022Jan 27 2022

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceMultimodal Biomedical Imaging XVII 2022
Country/TerritoryUnited States
CitySan Francisco


  • CNN
  • EfficientNet
  • MRI
  • U-Net

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Asymmetric decoder design for efficient convolutional encoder-decoder architectures in medical image reconstruction'. Together they form a unique fingerprint.

Cite this