Show simple item record

dc.contributor.authorThakur, S.
dc.contributor.authorDoshi, J.
dc.contributor.authorAlexander, G.S.
dc.date.accessioned2020-07-15T19:33:32Z
dc.date.available2020-07-15T19:33:32Z
dc.date.issued2020
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85087366850&doi=10.1016%2fj.neuroimage.2020.117081&partnerID=40&md5=6d129b0eca145e77a4c6cad9d5f4f504
dc.identifier.urihttp://hdl.handle.net/10713/13296
dc.description.abstractBrain extraction, or skull-stripping, is an essential pre-processing step in neuro-imaging that has a direct impact on the quality of all subsequent processing and analyses steps. It is also a key requirement in multi-institutional collaborations to comply with privacy-preserving regulations. Existing automated methods, including Deep Learning (DL) based methods that have obtained state-of-the-art results in recent years, have primarily targeted brain extraction without considering pathologically-affected brains. Accordingly, they perform sub-optimally when applied on magnetic resonance imaging (MRI) brain scans with apparent pathologies such as brain tumors. Furthermore, existing methods focus on using only T1-weighted MRI scans, even though multi-parametric MRI (mpMRI) scans are routinely acquired for patients with suspected brain tumors. In this study, we present a comprehensive performance evaluation of recent deep learning architectures for brain extraction, training models on mpMRI scans of pathologically-affected brains, with a particular focus on seeking a practically-applicable, low computational footprint approach, generalizable across multiple institutions, further facilitating collaborations. We identified a large retrospective multi-institutional dataset of n=3340 mpMRI brain tumor scans, with manually-inspected and approved gold-standard segmentations, acquired during standard clinical practice under varying acquisition protocols, both from private institutional data and public (TCIA) collections. To facilitate optimal utilization of rich mpMRI data, we further introduce and evaluate a novel ‘‘modality-agnostic training’’ technique that can be applied using any available modality, without need for model retraining. Our results indicate that the modality-agnostic approach1 obtains accurate results, providing a generic and practical tool for brain extraction on scans with brain tumors. Copyright 2020 The Author(s).en_US
dc.description.sponsorshipResearch reported in this publication was partly supported by the National Institutes of Health (NIH) under award numbers NINDS:R01NS042645 , NCI:U24CA189523 , NCI:U01CA242871 .en_US
dc.description.urihttps://doi.org/10.1016/j.neuroimage.2020.117081en_US
dc.language.isoen_USen_US
dc.publisherAcademic Press Inc.en_US
dc.relation.ispartofNeuroImage
dc.subjectBrain Extractionen_US
dc.subjectBrain tumoren_US
dc.subjectDeep learningen_US
dc.subjectEvaluationen_US
dc.subjectGlioblastomaen_US
dc.subjectGliomaen_US
dc.subjectSkull-strippingen_US
dc.subjectTCIAen_US
dc.titleBrain extraction on MRI scans in presence of diffuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic trainingen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/j.neuroimage.2020.117081


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record