Transfer Learning for Task Adaptation of Brain Lesion Assessment and Prediction of Brain Abnormalities Progression/Regression Using Irregularity Age Map in Brain MRI

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The Irregularity Age Map (IAM) for the unsupervised assessment of brain white matter hyperintensities (WMH) opens several opportunities in machine learning-based MRI analysis, including transfer task adaptation learning in the segmentation and prediction of brain lesion progression and regression. The lack of need for manual labels is useful for transfer learning. Whereas the nature of IAM itself can be exploited for predicting lesion progression/regression. In this study, we propose the use of task adaptation transfer learning for WMH segmentation using CNN through weakly-training UNet and UResNet using the output from IAM and the use of IAM for predicting patterns of WMH progression and regression.
Original languageEnglish
Title of host publicationPRIME: International Workshop on PRedictive Intelligence In MEdicine
Place of PublicationGranada, Spain
PublisherSpringer, Cham
Pages85-93
Number of pages9
ISBN (Electronic)978-3-030-00320-3
ISBN (Print)978-3-030-00319-7
DOIs
Publication statusPublished - 13 Sep 2018
EventPRedictive Intelligence in MEdicine 2018 - Granada, Spain
Duration: 16 Sep 201816 Sep 2018
https://basira-lab.com/events-workshops/prime-miccai18/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
Volume11121
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameImage Processing, Computer Vision, Pattern Recognition, and Graphics
Volume11121

Conference

ConferencePRedictive Intelligence in MEdicine 2018
Abbreviated titlePRIME-MICCAI 2018
CountrySpain
CityGranada
Period16/09/1816/09/18
Internet address

Fingerprint Dive into the research topics of 'Transfer Learning for Task Adaptation of Brain Lesion Assessment and Prediction of Brain Abnormalities Progression/Regression Using Irregularity Age Map in Brain MRI'. Together they form a unique fingerprint.

Cite this