Transfer Learning for Brain Segmentation: Pre-task Selection and Data Limitations

Jack Weatheritt, Daniel Rueckert, Robin Wolz

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

4 Scopus citations

Abstract

Manual segmentations of anatomical regions in the brain are time consuming and costly to acquire. In a clinical trial setting, this is prohibitive and automated methods are needed for routine application. We propose a deep-learning architecture that automatically delineates sub-cortical regions in the brain (example biomarkers for monitoring the development of Huntington’s disease). Neural networks, despite typically reaching state-of-the-art performance, are sensitive to differing scanner protocols and pre-processing methods. To address this challenge, one can pre-train a model on an existing data set and then fine-tune this model using a small amount of labelled data from the target domain. This work investigates the impact of the pre-training task and the amount of data required via a systematic study. We show that use of just a few samples from the same task (but a different domain) can achieve state-of-the-art performance. Further, this pre-training task utilises automated labels, meaning the pipeline requires very few manually segmented data points. On the other hand, using a different task for pre-training is shown to be less successful. We then conclude, by showing that, whilst fine-tuning is very powerful for a specific data distribution, models developed in this fashion are considerably more fragile when used on completely unseen data.

Original languageEnglish
Title of host publicationMedical Image Understanding and Analysis - 24th Annual Conference, MIUA 2020, Proceedings
EditorsBartlomiej W. Papiez, Ana I.L. Namburete, Mohammad Yaqub, J. Alison Noble, Mohammad Yaqub
PublisherSpringer
Pages118-130
Number of pages13
ISBN (Print)9783030527907
DOIs
StatePublished - 2020
Externally publishedYes
Event24th Annual Conference on Medical Image Understanding and Analysis, MIUA 2020 - Oxford, United Kingdom
Duration: 15 Jul 202017 Jul 2020

Publication series

NameCommunications in Computer and Information Science
Volume1248 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference24th Annual Conference on Medical Image Understanding and Analysis, MIUA 2020
Country/TerritoryUnited Kingdom
CityOxford
Period15/07/2017/07/20

Keywords

  • Brain segmentation
  • Deep learning
  • Transfer learning

Fingerprint

Dive into the research topics of 'Transfer Learning for Brain Segmentation: Pre-task Selection and Data Limitations'. Together they form a unique fingerprint.

Cite this