Show simple item record

dc.contributor.authorZormpas-Petridis, K
dc.contributor.authorFailmezger, H
dc.contributor.authorRaza, SEA
dc.contributor.authorRoxanis, I
dc.contributor.authorJamin, Y
dc.contributor.authorYuan, Y
dc.date.accessioned2020-05-28T11:51:29Z
dc.date.issued2019-01
dc.identifier.citationFrontiers in oncology, 2019, 9 pp. 1045 - ?
dc.identifier.issn2234-943X
dc.identifier.urihttps://repository.icr.ac.uk/handle/internal/3655
dc.identifier.eissn2234-943X
dc.identifier.doi10.3389/fonc.2019.01045
dc.description.abstractComputational pathology-based cell classification algorithms are revolutionizing the study of the tumor microenvironment and can provide novel predictive/prognosis biomarkers crucial for the delivery of precision oncology. Current algorithms used on hematoxylin and eosin slides are based on individual cell nuclei morphology with limited local context features. Here, we propose a novel multi-resolution hierarchical framework (SuperCRF) inspired by the way pathologists perceive regional tissue architecture to improve cell classification and demonstrate its clinical applications. We develop SuperCRF by training a state-of-art deep learning spatially constrained- convolution neural network (SC-CNN) to detect and classify cells from 105 high-resolution (20×) H&E-stained slides of The Cancer Genome Atlas melanoma dataset and subsequently, a conditional random field (CRF) by combining cellular neighborhood with tumor regional classification from lower resolution images (5, 1.25×) given by a superpixel-based machine learning framework. SuperCRF led to an 11.85% overall improvement in the accuracy of the state-of-art deep learning SC-CNN cell classifier. Consistent with a stroma-mediated immune suppressive microenvironment, SuperCRF demonstrated that (i) a high ratio of lymphocytes to all lymphocytes within the stromal compartment (p = 0.026) and (ii) a high ratio of stromal cells to all cells (p < 0.0001 compared to p = 0.039 for SC-CNN only) are associated with poor survival in patients with melanoma. SuperCRF improves cell classification by introducing global and local context-based information and can be implemented in combination with any single-cell classifier. SuperCRF provides valuable tools to study the tumor microenvironment and identify predictors of survival and response to therapy.
dc.formatElectronic-eCollection
dc.format.extent1045 - ?
dc.languageeng
dc.language.isoeng
dc.rights.urihttps://creativecommons.org/licenses/by/4.0
dc.titleSuperpixel-Based Conditional Random Fields (SuperCRF): Incorporating Global and Local Context for Enhanced Deep Learning in Melanoma Histopathology.
dc.typeJournal Article
dcterms.dateAccepted2019-09-25
rioxxterms.versionofrecord10.3389/fonc.2019.01045
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0
rioxxterms.licenseref.startdate2019-01
rioxxterms.typeJournal Article/Review
dc.relation.isPartOfFrontiers in oncology
pubs.notesNot known
pubs.organisational-group/ICR
pubs.organisational-group/ICR/Primary Group
pubs.organisational-group/ICR/Primary Group/ICR Divisions
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Molecular Pathology
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Molecular Pathology/Computational Pathology & Integrated Genomics
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Computational Imaging
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Pre-Clinical MRI
pubs.organisational-group/ICR/Students
pubs.organisational-group/ICR/Students/PhD and MPhil
pubs.organisational-group/ICR/Students/PhD and MPhil/16/17 Starting Cohort
pubs.organisational-group/ICR
pubs.organisational-group/ICR/Primary Group
pubs.organisational-group/ICR/Primary Group/ICR Divisions
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Molecular Pathology
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Molecular Pathology/Computational Pathology & Integrated Genomics
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Computational Imaging
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Pre-Clinical MRI
pubs.organisational-group/ICR/Students
pubs.organisational-group/ICR/Students/PhD and MPhil
pubs.organisational-group/ICR/Students/PhD and MPhil/16/17 Starting Cohort
pubs.publication-statusPublished
pubs.volume9
pubs.embargo.termsNot known
icr.researchteamComputational Pathology & Integrated Genomicsen_US
icr.researchteamComputational Imagingen_US
icr.researchteamPre-Clinical MRIen_US
dc.contributor.icrauthorZormpas Petridis, Konstantinosen
dc.contributor.icrauthorJamin, Yannen
dc.contributor.icrauthorYuan, Yinyinen


Files in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record

https://creativecommons.org/licenses/by/4.0
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0