Augmenting the clinical approach to glioblastoma: investigating the potential of automatic segmentation and radiomics to improve patient management

Nathaniel Barry

doi:10.26182/c9k5-8f90

Augmenting the clinical approach to glioblastoma: investigating the potential of automatic segmentation and radiomics to improve patient management

Nathaniel Barry

School of Physics, Mathematics and Computing

Research output: Thesis › Doctoral Thesis

19 Downloads (Pure)

Abstract

Glioblastoma has a dismal prognosis and current treatment aims to maximise survival and quality of life. O-(2-[18F]Fluoroethyl)-L-tyrosine (FET) positron emission tomography (PET) has become a popular supplemental imaging modality to improve patient management of this disease and the road to widespread clinical implementation of FET-PET requires in-depth quantitative analysis. The aims of this thesis are to: (1) understand how multi-observer FET-PET interpretation/segmentation for radiotherapy and response assessment may vary in the context of a national clinical trial, (2) evaluate automatic segmentation approaches to reduce variability, and (3) to identify statistically robust and reproducible radiomics study design for modelling underlying pathophysiology.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	The University of Western Australia
Supervisors/Advisors	Rowshan Farzad, Pejman, Supervisor Ebert, Martin, Supervisor Kendrick, Jake, Supervisor Francis, Roslyn, Supervisor Hassan, Mubashar, Supervisor
Thesis sponsors	Australian Government Research Training Program
Award date	1 Oct 2025
DOIs	https://doi.org/10.26182/c9k5-8f90
Publication status	Unpublished - 2025

Embargo information

Embargoed from 30/09/2025 to 15/12/2025. Made publicly available on 15/12/2025.

Access to Document

10.26182/c9k5-8f90

THESIS - DOCTOR OF PHILOSOPHY - BARRY Nathaniel David George - 2025
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

4 Article

An External, Independent Validation of an O-(2-[18F]Fluoroethyl)-l-Tyrosine PET Automatic Segmentation Network on a Single-Center, Prospective Dataset of Patients with Glioblastoma
Barry, N., Kendrick, J., Rowshan Farzad, P., Hassan, M., Francis, R., Bucknell, N., Koh, E.-S., Scott, A. M., Gutsche, R., Galldiks, N., Langen, K.-J. & Lohmann, P., 1 Jun 2025, In: The Journal of Nuclear Medicine. 66, 6, p. 948-953 6 p.
Research output: Contribution to journal › Article › peer-review
3 Link opens in a new tab Citations (Scopus)
Evaluating the impact of the Radiomics Quality Score: a systematic review and meta-analysis
Barry, N., Kendrick, J., Molin, K., Li, S., Rowshanfarzad, P., Hassan, G. M., Dowling, J., Parizel, P. M., Hofman, M. S. & Ebert, M. A., Mar 2025, In: European Radiology. 35, 3, p. 1701-1713 13 p., e240262.
Research output: Contribution to journal › Article › peer-review

Open Access
33 Link opens in a new tab Citations (Scopus)
[18]F-fluoroethyl-L-tyrosine positron emission tomography for radiotherapy target delineation: Results from a Radiation Oncology credentialing program
Barry, N., Koh, E. S., Ebert, M. A., Moore, A., Francis, R. J., Rowshanfarzad, P., Hassan, G. M., Ng, S. P., Back, M., Chua, B., Pinkham, M. B., Pullar, A., Phillips, C., Sia, J., Gorayski, P., Le, H., Gill, S., Croker, J., Bucknell, N. & Bettington, C. & 11 others, Syed, F., Jung, K., Chang, J., Bece, A., Clark, C., Wada, M., Cook, O., Whitehead, A., Rossi, A., Grose, A. & Scott, A. M., Apr 2024, In: Physics and Imaging in Radiation Oncology. 30, 100568.
Research output: Contribution to journal › Article › peer-review

Open Access
4 Link opens in a new tab Citations (Scopus)

Cite this

@phdthesis{5a30d176029c416081a3ba9dfe33447c,

title = "Augmenting the clinical approach to glioblastoma: investigating the potential of automatic segmentation and radiomics to improve patient management",

abstract = "Glioblastoma has a dismal prognosis and current treatment aims to maximise survival and quality of life. O-(2-[18F]Fluoroethyl)-L-tyrosine (FET) positron emission tomography (PET) has become a popular supplemental imaging modality to improve patient management of this disease and the road to widespread clinical implementation of FET-PET requires in-depth quantitative analysis. The aims of this thesis are to: (1) understand how multi-observer FET-PET interpretation/segmentation for radiotherapy and response assessment may vary in the context of a national clinical trial, (2) evaluate automatic segmentation approaches to reduce variability, and (3) to identify statistically robust and reproducible radiomics study design for modelling underlying pathophysiology.",

keywords = "Glioblastoma, artificial intelligence, clinical trials, radiomics",

author = "Nathaniel Barry",

year = "2025",

doi = "10.26182/c9k5-8f90",

language = "English",

school = "The University of Western Australia",

}

TY - BOOK

T1 - Augmenting the clinical approach to glioblastoma: investigating the potential of automatic segmentation and radiomics to improve patient management

AU - Barry, Nathaniel

PY - 2025

Y1 - 2025

N2 - Glioblastoma has a dismal prognosis and current treatment aims to maximise survival and quality of life. O-(2-[18F]Fluoroethyl)-L-tyrosine (FET) positron emission tomography (PET) has become a popular supplemental imaging modality to improve patient management of this disease and the road to widespread clinical implementation of FET-PET requires in-depth quantitative analysis. The aims of this thesis are to: (1) understand how multi-observer FET-PET interpretation/segmentation for radiotherapy and response assessment may vary in the context of a national clinical trial, (2) evaluate automatic segmentation approaches to reduce variability, and (3) to identify statistically robust and reproducible radiomics study design for modelling underlying pathophysiology.

AB - Glioblastoma has a dismal prognosis and current treatment aims to maximise survival and quality of life. O-(2-[18F]Fluoroethyl)-L-tyrosine (FET) positron emission tomography (PET) has become a popular supplemental imaging modality to improve patient management of this disease and the road to widespread clinical implementation of FET-PET requires in-depth quantitative analysis. The aims of this thesis are to: (1) understand how multi-observer FET-PET interpretation/segmentation for radiotherapy and response assessment may vary in the context of a national clinical trial, (2) evaluate automatic segmentation approaches to reduce variability, and (3) to identify statistically robust and reproducible radiomics study design for modelling underlying pathophysiology.

KW - Glioblastoma

KW - artificial intelligence

KW - clinical trials

KW - radiomics

U2 - 10.26182/c9k5-8f90

DO - 10.26182/c9k5-8f90

M3 - Doctoral Thesis

ER -

Augmenting the clinical approach to glioblastoma: investigating the potential of automatic segmentation and radiomics to improve patient management

Abstract

Embargo information

Access to Document

Fingerprint

Research output

An External, Independent Validation of an O-(2-[18F]Fluoroethyl)-l-Tyrosine PET Automatic Segmentation Network on a Single-Center, Prospective Dataset of Patients with Glioblastoma

Evaluating the impact of the Radiomics Quality Score: a systematic review and meta-analysis

[18]F-fluoroethyl-L-tyrosine positron emission tomography for radiotherapy target delineation: Results from a Radiation Oncology credentialing program

Cite this