BIBM2019: Tumor Segmentation Based on Deeply Supervised Multi-Scale U-Net

Published in 2019 IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM 2019), (CCF Rank B, Acceptance rate: 18%), 2019

Authors: Lei Wang, Bo Wang, Zhenghua Xu*
Abstract: Although deep learning has achieved great success in the field of medical image processing, the existing deep learning based medical image segmentation solutions still cannot obtain satisfactory performances for abdominal small organs and lesions due to their small object size and shape-variability. In this work, a Deeply Supervised Multi-Scale U-Net (DSMS U-Net) is proposed for more accurate segmentation performances on abdominal small organs images. DSMS U-Net integrate the existing UNet model with a restoration decoder module and some multiscale convolution modules. Our experiment results demonstrate that the proposed DSMS U-Net approach has much better segmentation performances than the state-of-the-art baselines.

[Download paper here]