PMED-Net: Pyramid-Based Multi-Scale Encoder-Decoder Network for Medical Image Segmentation

Published in IEEE Access, 2021

Our Contributions

  • We proposed an architecture that employs small pyramid-based encoder-decoder networks in a cascaded fashion for extracting complex lesions and biomarkers contained within medical images by leveraging their multi-scale feature representations.
  • We address the adaptive techniques of network size to achieve an optimal trade-off between performance and computations.
  • Features of different scales are extracted using pyramid-based encoder-decoder networks.
  • In terms of model parameters, the proposed architecture is 95.30% smaller than SegNet, 95.27% smaller than U-Net, 92.90% smaller than BCDU-Net, 91.42% smaller than CU-Net, 91.11% smaller than FCN-8s, 84.94% smaller than ORED-Net, and 79.81% smaller than MultiResUNet.

Paper Available Here