Voxel-wise prostate cell density prediction using multiparametric magnetic resonance imaging and machine learning

Show simple item record

dc.contributor.author Sun Y en
dc.contributor.author Reynolds HM en
dc.contributor.author Wraith D en
dc.contributor.author Williams S en
dc.contributor.author Finnegan ME en
dc.contributor.author Mitchell C en
dc.contributor.author Murphy D en
dc.contributor.author Haworth A en
dc.date.accessioned 2020-10-16T02:57:09Z
dc.date.available 2020-10-16T02:57:09Z
dc.date.issued 2018 en
dc.identifier.issn 0284-186X en
dc.identifier.uri http://hdl.handle.net/2292/53344
dc.description.abstract Background: There are currently no methods to estimate cell density in the prostate. This study aimed to develop predictive models to estimate prostate cell density from multiparametric magnetic resonance imaging (mpMRI) data at a voxel level using machine learning techniques. Material and methods: In vivo mpMRI data were collected from 30 patients before radical prostatectomy. Sequences included T2-weighted imaging, diffusion-weighted imaging and dynamic contrastenhanced imaging. Ground truth cell density maps were computed from histology and co-registered with mpMRI. Feature extraction and selection were performed on mpMRI data. Final models were fitted using three regression algorithms including multivariate adaptive regression spline (MARS), polynomial regression (PR) and generalised additive model (GAM). Model parameters were optimised using leaveone-out cross-validation on the training data and model performance was evaluated on test data using root mean square error (RMSE) measurements. Results: Predictive models to estimate voxel-wise prostate cell density were successfully trained and tested using the three algorithms. The best model (GAM) achieved a RMSE of 1.06 (±0.06) 103 cells/ mm2 and a relative deviation of 13.3±0.8%. Conclusion: Prostate cell density can be quantitatively estimated non-invasively from mpMRI data using high-quality co-registered data at a voxel level. These cell density predictions could be used for tissue classification, treatment response evaluation and personalised radiotherapy. en
dc.description.uri https://catalogue.library.auckland.ac.nz/permalink/f/t37c0t/uoa_alma51290289370002091 en
dc.relation.ispartofseries Acta Oncologica en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.subject 1112 Oncology And Carcinogenesis en
dc.title Voxel-wise prostate cell density prediction using multiparametric magnetic resonance imaging and machine learning en
dc.type Journal Article en
dc.identifier.doi 10.1080/0284186X.2018.1468084 en
pubs.issue 11 en
pubs.begin-page 1540 en
pubs.volume 57 en
dc.date.updated 2020-09-24T21:56:17Z en
dc.rights.holder Copyright: The author en
pubs.author-url https://www.tandfonline.com/doi/full/10.1080/0284186X.2018.1468084 en
pubs.end-page 1546 en
pubs.publication-status Published en
dc.rights.accessrights http://purl.org/eprint/accessRights/RestrictedAccess en
pubs.subtype Article en
pubs.elements-id 789345 en
dc.identifier.eissn 1651-226X en
pubs.online-publication-date 2018-4-26 en

Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record


Search ResearchSpace