Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.595629
Title: Machine learning for systems pathology
Author: Verleyen, Wim
Awarding Body: University of St Andrews
Current Institution: University of St Andrews
Date of Award: 2013
Availability of Full Text:
Access from EThOS:
Access from Institution:
Abstract:
Systems pathology attempts to introduce more holistic approaches towards pathology and attempts to integrate clinicopathological information with “-omics” technology. This doctorate researches two examples of a systems approach for pathology: (1) a personalized patient output prediction for ovarian cancer and (2) an analytical approach differentiates between individual and collective tumour invasion. During the personalized patient output prediction for ovarian cancer study, clinicopathological measurements and proteomic biomarkers are analysed with a set of newly engineered bioinformatic tools. These tools are based upon feature selection, survival analysis with Cox proportional hazards regression, and a novel Monte Carlo approach. Clinical and pathological data proves to have highly significant information content, as expected; however, molecular data has little information content alone, and is only significant when selected most-informative variables are placed in the context of the patient's clinical and pathological measures. Furthermore, classifiers based on support vector machines (SVMs) that predict one-year PFS and three-year OS with high accuracy, show how the addition of carefully selected molecular measures to clinical and pathological knowledge can enable personalized prognosis predictions. Finally, the high-performance of these classifiers are validated on an additional data set. A second study, an analytical approach differentiates between individual and collective tumour invasion, analyses a set of morphological measures. These morphological measurements are collected with a newly developed process using automated imaging analysis for data collection in combination with a Bayesian network analysis to probabilistically connect morphological variables with tumour invasion modes. Between an individual and collective invasion mode, cell-cell contact is the most discriminating morphological feature. Smaller invading groups were typified by smoother cellular surfaces than those invading collectively in larger groups. Interestingly, elongation was evident in all invading cell groups and was not a specific feature of single cell invasion as a surrogate of epithelialmesenchymal transition. In conclusion, the combination of automated imaging analysis and Bayesian network analysis provides an insight into morphological variables associated with transition of cancer cells between invasion modes. We show that only two morphologically distinct modes of invasion exist. The two studies performed in this thesis illustrate the potential of a systems approach for pathology and illustrate the need of quantitative approaches in order to reveal the system behind pathology.
Supervisor: Stokes, Anne Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.595629  DOI: Not available
Keywords: R859.7D35V4 ; Medical informatics--Statistical methods ; Cancer invasiveness--Measurement--Statistical methods ; Machine learning ; Pathology--Statistical methods ; Ovaries--Tumors--Diagnosis--Statistical methods ; System theory
Share: