dc.contributor.author |
Dutta, Arpita |
|
dc.contributor.author |
Chan, Joseph |
|
dc.contributor.author |
Haworth, Annette |
|
dc.contributor.author |
Dubowitz, David J |
|
dc.contributor.author |
Kneebone, Andrew |
|
dc.contributor.author |
Reynolds, Hayley M |
|
dc.coverage.spatial |
Netherlands |
|
dc.date.accessioned |
2024-03-13T21:58:15Z |
|
dc.date.available |
2024-03-13T21:58:15Z |
|
dc.date.issued |
2024-01 |
|
dc.identifier.citation |
(2024). Physics and Imaging in Radiation Oncology, 29, 100530-. |
|
dc.identifier.issn |
2405-6316 |
|
dc.identifier.uri |
https://hdl.handle.net/2292/67697 |
|
dc.description.abstract |
<h4>Background and purpose</h4>Radiomic features from MRI and PET are an emerging tool with potential to improve prostate cancer outcomes. However, feature robustness due to image segmentation variations is currently unknown. Therefore, this study aimed to evaluate the robustness of radiomic features with segmentation variations and their impact on predicting biochemical recurrence (BCR).<h4>Materials and methods</h4>Multi-scanner, pre-radiation therapy imaging from 142 patients with localised prostate cancer was used. Imaging included T2-weighted (T2), apparent diffusion coefficient (ADC) MRI, and prostate-specific membrane antigen (PSMA)-PET. The prostate gland and intraprostatic tumours were manually and automatically segmented, and differences were quantified using Dice Coefficient (DC). Radiomic features including shape, first-order, and texture features were extracted for each segmentation from original and filtered images. Intraclass Correlation Coefficient (ICC) and Mean Absolute Percentage Difference (MAPD) were used to assess feature robustness. Random forest (RF) models were developed for each segmentation using robust features to predict BCR.<h4>Results</h4>Prostate gland segmentations were more consistent (mean DC = 0.78) than tumour segmentations (mean DC = 0.46). 112 (3.6 %) radiomic features demonstrated 'excellent' robustness (ICC > 0.9 and MAPD < 1 %), and 480 features (15.4 %) demonstrated 'good' robustness (ICC > 0.75 and MAPD < 5 %). PET imaging provided more features with excellent robustness than T2 and ADC. RF models showed strong predictive power for BCR with a mean area under the receiver-operator-characteristics curve (AUC) of 0.89 (range 0.85-0.93).<h4>Conclusion</h4>When using radiomic features for predictive modelling, segmentation variability should be considered. To develop BCR predictive models, radiomic features from the entire prostate gland are preferable over tumour segmentation-based features. |
|
dc.format.medium |
Electronic-eCollection |
|
dc.language |
eng |
|
dc.publisher |
Elsevier |
|
dc.relation.ispartofseries |
Physics and imaging in radiation oncology |
|
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. |
|
dc.rights.uri |
https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm |
|
dc.rights.uri |
https://creativecommons.org/licenses/by-nc-nd/4.0/ |
|
dc.subject |
MRI |
|
dc.subject |
PET |
|
dc.subject |
Prostate cancer |
|
dc.subject |
Radiomics |
|
dc.subject |
Recurrence prediction |
|
dc.subject |
Robustness |
|
dc.subject |
32 Biomedical and Clinical Sciences |
|
dc.subject |
3202 Clinical Sciences |
|
dc.subject |
3211 Oncology and Carcinogenesis |
|
dc.subject |
Urologic Diseases |
|
dc.subject |
Bioengineering |
|
dc.subject |
Cancer |
|
dc.subject |
Biomedical Imaging |
|
dc.subject |
Science & Technology |
|
dc.subject |
Life Sciences & Biomedicine |
|
dc.subject |
Oncology |
|
dc.subject |
Radiology, Nuclear Medicine & Medical Imaging |
|
dc.subject |
RADIOTHERAPY |
|
dc.subject |
5105 Medical and biological physics |
|
dc.title |
Robustness of magnetic resonance imaging and positron emission tomography radiomic features in prostate cancer: Impact on recurrence prediction after radiation therapy. |
|
dc.type |
Journal Article |
|
dc.identifier.doi |
10.1016/j.phro.2023.100530 |
|
pubs.begin-page |
100530 |
|
pubs.volume |
29 |
|
dc.date.updated |
2024-02-13T20:47:41Z |
|
dc.rights.holder |
Copyright: The authors |
en |
dc.identifier.pmid |
38275002 (pubmed) |
|
pubs.author-url |
https://www.ncbi.nlm.nih.gov/pubmed/38275002 |
|
pubs.publication-status |
Published |
|
dc.rights.accessrights |
http://purl.org/eprint/accessRights/OpenAccess |
en |
pubs.subtype |
research-article |
|
pubs.subtype |
Journal Article |
|
pubs.elements-id |
1005866 |
|
pubs.org-id |
Bioengineering Institute |
|
dc.identifier.eissn |
2405-6316 |
|
dc.identifier.pii |
S2405-6316(23)00121-5 |
|
pubs.number |
100530 |
|
pubs.record-created-at-source-date |
2024-02-14 |
|
pubs.online-publication-date |
2023-12-31 |
|