Quantitative Nuclear Grading to Increase Reliability and Consistency in Bladder Cancer Diagnoses: Model Construction and Validation

dc.contributor.authorSlotman, Avaen
dc.contributor.departmentPathology and Molecular Medicineen
dc.contributor.supervisorBerman, David M
dc.contributor.supervisorGooding, Robert J
dc.date.accessioned2023-06-21T19:48:11Z
dc.date.available2023-06-21T19:48:11Z
dc.degree.grantorQueen's University at Kingstonen
dc.description.abstractBladder cancer, with a simple yet subjective and unreliable grading scheme, is a prime candidate for the development of a reproducible and quantitative grading model. In the early form of the disease, tumours are separated into low- and high-grade based on qualitative histological differences. Unfortunately, these criteria exist on a spectrum without standardized thresholds, resulting in unacceptable amounts of inter-observer variability. To counteract this unreliability and irreproducibility, we developed internally cross-validated and externally validated quantitative grading models. Using two large non-muscle-invasive bladder cancer cohorts from different continents, we analyzed the histological features in 1023 low-grade and 199 high-grade images taken from 774 cases. Images underwent consensus grading according to the 2004 World Health Organization and International Society of Urological Pathology guidelines. Lymphocytes served as an internal control to standardize cohort image magnifications. Tissue regions and nuclei were identified using automated image analysis software and the size, shape, and mitotic rate were generated for all nuclei. We found consistent differences in size-related features across cohorts, specifically, the standard deviation of nuclear area could differentiate between the two grades with > 80% balanced accuracy. In contrast, there were large discrepancies in mitotic index and shape-related features between cohorts which may be a result of technical errors or sampling differences. We used the first cohort to train a variety of classification models, many of which performed impressively well on the training data. However, out of all multivariate models, only the random forest generalized well to a validation cohort and achieved a balanced accuracy of 80%. Using a discovery-validation approach with two distinct datasets, these findings strongly support the use of a random forest model to help standardize bladder cancer grading.en
dc.description.degreeM.Sc.en
dc.embargo.liftdate2028-06-20T13:57:50Z
dc.embargo.termsSignificant parts of this thesis are currently in the process of being turned into a manuscript for publication in a scientific journal. Moreover, this thesis describes in great detail models and tools that we currently are in the process of submitting patents for. In order to allow for the manuscript to be published and patents be put in place to protect the intellectual property of the models we request that this thesis be embargoed/restricted for the 5-year period.en
dc.identifier.urihttp://hdl.handle.net/1974/31730
dc.language.isoengen
dc.relation.ispartofseriesCanadian thesesen
dc.rightsQueen's University's Thesis/Dissertation Non-Exclusive License for Deposit to QSpace and Library and Archives Canadaen
dc.rightsProQuest PhD and Master's Theses International Dissemination Agreementen
dc.rightsIntellectual Property Guidelines at Queen's Universityen
dc.rightsCopying and Preserving Your Thesisen
dc.rightsThis publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.en
dc.subjectartificial intelligenceen
dc.subjectbladder canceren
dc.subjectgradingen
dc.subjecturothelial carcinomaen
dc.subjectdigital pathologyen
dc.subjectvalidationen
dc.titleQuantitative Nuclear Grading to Increase Reliability and Consistency in Bladder Cancer Diagnoses: Model Construction and Validationen
dc.typethesisen
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Slotman_Ava_M_202306_MSC.pdf
Size:
27.06 MB
Format:
Adobe Portable Document Format
Description:
Thesis document
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.67 KB
Format:
Item-specific license agreed upon to submission
Description: