Computational Analysis of Tissue Images in Cancer Diagnosis and Prognosis - Machine Learning-Based Methods for the Next Generation of Computational Pathology

Aug 3, 2026

Upload by Logic

The focus of this work is to develop machine learning systems for tissue image analysis in cancer diagnosis and prognosis. The resulting models aim to identify new prognostic markers and function as standalone clinical prediction rules by leveraging non-linear, multivariate patterns beyond conventional clinical gold standards. The research addresses major challenges created by extreme image resolution, heterogeneous microenvironments, noise and artifacts, and limited granularity of ground truth. The study evaluates handcrafted-feature approaches for prognosis, then explores deep learning methods on whole slide images, assessing performance and interpretability across colorectal and muscle-invasive bladder cancer cohorts.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages164

Reading Time6 h 53 min

AccessFree to download

Thesis Information

Candidate and Supervisor Declarations

Publication Permissions and Embargo Policy

Research Data and Digital Output Requirements

Core Study Focus

Machine Learning for Tissue Image Analysis

Challenges: Resolution, Heterogeneity, Noise, and Ground Truth

Handcrafted Feature Pipelines for Prognosis

Deep Learning Approaches and Pipeline Motivation

Evaluation on Cancer Cohorts

COMPUTATIONAL ANALYSIS OF TISSUE IMAGES IN CANCER DIAGNOSIS AND PROGNOSIS: MACHINE LEARNINGBASED METHODS FOR THE NEXT GENERATION OF COMPUTATIONAL PATHOLOGY Neofytos Dimitriou A Thesis Submitted for the Degree of PhD at the University of St Andrews 2023 Full metadata for this thesis is available in St Andrews Research Repository at: [http://research-repository.st-andrews.ac.uk/](http://research-repository.st-andrews.ac.uk/) [Identifiers to use to cite or link to this thesis:](Identifiers to use to cite or link to this thesis:) DOI: [https://doi.org/10.17630/sta/336](https://doi.org/10.17630/sta/336)[ ](https://doi.org/10.17630/sta/336)[http://hdl.handle.net/10023/27139](http://hdl.handle.net/10023/27139) This item is protected by original copyright This item is licensed under a Creative Commons License [https://creativecommons.org/licenses/by-nc/4.0](https://creativecommons.org/licenses/by-nc/4.0) Computational analysis of tissue images in cancer diagnosis and prognosis: machine learningbased methods for the next generation of computational pathology Neofytos Dimitriou This thesis is submitted in partial fulfilment for the degree of Doctor of Philosophy (PhD) at the University of St Andrews April 2022 Candidate's declaration I, Neofytos Dimitriou, do hereby certify that this thesis, submitted for the degree of PhD, which is approximately 24,787 words in length, has been written by me, and that it is the record of work carried out by me, or principally by myself in collaboration with others as acknowledged, and that it has not been submitted in any previous application for any degree. I confirm that any appendices included in my thesis contain only material permitted by the 'Assessment of Postgraduate Research Students' policy. I was admitted as a research student at the University of St Andrews in September 2017. I received funding from an organisation or institution and have acknowledged the funder(s) in the full text of my thesis. Date 30/01/2023 Signature of candidate Supervisor's declaration I hereby certify that the candidate has fulfilled the conditions of the Resolution and Regulations appropriate for the degree of PhD in the University of St Andrews and that the candidate is qualified to submit this thesis in application for that degree. I confirm that any appendices included in the thesis contain only material permitted by the 'Assessment of Postgraduate Research Students' policy. Date 30/01/2023 Signature of supervisor Permission for publication In submitting this thesis to the University of St Andrews we understand that we are giving permission for it to be made available for use in accordance with the regulations of the University Library for the time being in force, subject to any copyright vested in the work not being affected thereby. We also understand, unless exempt by an award of an embargo as requested below, that the title and the abstract will be published, and that a copy of the work may be made and supplied to any bona fide library or research worker, that this thesis will be electronically accessible for personal or research use and that the library has the right to migrate this thesis into new electronic forms as required to ensure continued access to the thesis. I, Neofytos Dimitriou, confirm that my thesis does not contain any third-party material that requires copyright clearance. The following is an agreed request by candidate and supervisor regarding the publication of this thesis: Printed copy No embargo on print copy. Electronic copy No embargo on electronic copy. Date 30/01/2023 Signature of candidate Date 30/01/2023 Signature of supervisor Underpinning Research Data or Digital Outputs Candidate's declaration I, Neofytos Dimitriou, hereby certify that no requirements to deposit original research data or digital outputs apply to this thesis and that, where appropriate, secondary data used have been referenced in the full te

FAQs

What is the main goal of the thesis?

To develop machine learning systems that analyze tissue images to support cancer diagnosis and prognosis, including discovery of prognostic markers and clinical prediction rules.

Why is tissue-image based prognosis considered challenging in this research?

Because images have extremely high resolution, the tumor microenvironment is highly heterogeneous, data contain multiple noise/artifact sources, and ground-truth labels are low in granularity.

How does the thesis compare handcrafted features with deep learning?

It investigates handcrafted feature extraction with machine learning for prognosis, and then motivates deep learning to analyze images directly, reducing labor-intensive and bias-prone feature-pipeline design.

Aug 3, 2026

Upload by Logic