Segmentation of head and neck tumours using modified U-net

Baixiang Zhao, John Soraghan, Gaetano Di Caterina, Derek Grose

Research output: Contribution to conferencePaperpeer-review

7 Citations (Scopus)
43 Downloads (Pure)


A new neural network for automatic head and neck cancer (HNC) segmentation from magnetic resonance imaging (MRI) is presented. The proposed neural network is based on U-net, which combines features from different resolutions to achieve end-to-end locating and segmentation of medical images. In this work, the dilated convolution is introduced into U-net, to obtain larger receptive field so that extract multi-scale features. Also, this network uses Dice loss to reduce the imbalance between classes. The proposed algorithm is trained and tested on real MRI data. The cross-validation results show that the new network outperformed the original Unet by 5% (Dice score) on head and neck tumour segmentation.
Original languageEnglish
Number of pages4
Publication statusPublished - 2 Sept 2019
Event27th European Signal Processing Conference - A Coruna, Spain
Duration: 2 Sept 20196 Sept 2019


Conference27th European Signal Processing Conference
Abbreviated titleEUSIPCO 2019
CityA Coruna
Internet address


  • MRI data
  • head and neck cancer
  • U-net
  • dilated convolution
  • semantic segmentation


Dive into the research topics of 'Segmentation of head and neck tumours using modified U-net'. Together they form a unique fingerprint.

Cite this