UNET-based multi-task architecture for brain lesion segmentation

Ava Assadi Abolvardi, Len Hamey, Kevin Ho-Shon

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

1 Citation (Scopus)


Image segmentation is the task of extracting the region of interest in images and is one of the main applications of computer vision in the medical domain. Like other computer vision tasks, deep learning is the main solution to image segmentation problems. Deep learning methods are data-hungry and need a huge amount of data for training. On the other side, data shortage is always a problem, especially in the medical domain. Multi-task learning is a technique which helps the deep model to learn better representation from data distribution by introducing related auxiliary tasks. In this study, we investigate a research question to whether it is better to provide this auxiliary information as an input to the network, or is it better to use this task and design a multi-output network. Our findings suggest that however, the multi-output manner improves the overall performance, but the best result achieves when this extra information serves as auxiliary input information.

Original languageEnglish
Title of host publicationDigital Image Computing
Subtitle of host publicationTechniques and Applications, DICTA 2020
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages7
ISBN (Electronic)9781728191089
Publication statusPublished - 2020
Event2020 Digital Image Computing: Techniques and Applications, DICTA 2020 - Melbourne, Australia
Duration: 29 Nov 20202 Dec 2020

Publication series

Name2020 Digital Image Computing: Techniques and Applications, DICTA 2020


Conference2020 Digital Image Computing: Techniques and Applications, DICTA 2020


  • computer vision
  • Deep Learning
  • image segmentation
  • Multi-task learning


Dive into the research topics of 'UNET-based multi-task architecture for brain lesion segmentation'. Together they form a unique fingerprint.

Cite this