UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Technological Advances in the Diagnosis and Management of Pigmented Fundus Tumours

AlHarbi, Lamis; (2022) Technological Advances in the Diagnosis and Management of Pigmented Fundus Tumours. Doctoral thesis (Ph.D), UCL (University College London). Green open access

[thumbnail of Alwan Alharbi_10161763_Thesis_id_removed.pdf]
Alwan Alharbi_10161763_Thesis_id_removed.pdf

Download (5MB) | Preview


Choroidal naevi are the most common intraocular tumour. They can be pigmented or non-pigmented and have a predilection for the posterior uvea. The majority remain undetected and cause no harm but are increasingly found on routine community optometry examinations. Rarely does a naevus demonstrate growth or the onset of suspicious features to fulfil the criteria for a malignant melanoma. Because of this very small risk, optometrists commonly refer these patients to hospital eye units for a second opinion, triggering specialist examination and investigation, causing significant anxiety to patients and stretching medical resources. This PhD thesis introduces the MOLES acronym and scoring system that has been devised to categorise the risk of malignancy in choroidal melanocytic tumours according to Mushroom tumour shape, Orange pigment, Large tumour size, Enlarging tumour and Subretinal fluid. This is a simplified system that can be used without sophisticated imaging, and hence its main utility lies in the screening of patients with choroidal pigmented lesions in the community and general ophthalmology clinics. Under this system, lesions were categorised by a scoring system as ‘common naevus’, ‘low-risk naevus’, ‘high-risk naevus’ and ‘probable melanoma.’ According to the sum total of the scores, the MOLES system correlates well with ocular oncologists’ final diagnosis. The PhD thesis also describes a model of managing such lesions in a virtual pathway, showing that images of choroidal naevi evaluated remotely using a decision-making algorithm by masked non-medical graders or masked ophthalmologists is safe. This work prospectively validates a virtual naevus clinic model focusing on patient safety as the primary consideration. The idea of a virtual naevus clinic as a fast, one-stop, streamlined and comprehensive service is attractive for patients and healthcare systems, including an optimised patient experience with reduced delays and inconvenience from repeated visits. A safe, standardised model ensures homogeneous management of cases, appropriate and prompt return of care closer to home to community-based optometrists. This research work and strategies, such as the MOLES scoring system for triage, could empower community-based providers to deliver management of benign choroidal naevi without referral to specialist units. Based on the positive outcome of this prospective study and the MOLES studies, a ‘Virtual Naevus Clinic’ has been designed and adapted at Moorfields Eye Hospital (MEH) to prove its feasibility as a response to the COVID-19 pandemic, and with the purpose of reducing in-hospital patient journey times and increasing the capacity of the naevus clinics, while providing safe and efficient clinical care for patients. This PhD chapter describes the design, pathways, and operating procedures for the digitally enabled naevus clinics in Moorfields Eye Hospital, including what this service provides and how it will be delivered and supported. The author will share the current experience and future plan. Finally, the PhD thesis will cover a chapter that discusses the potential role of artificial intelligence (AI) in differentiating benign choroidal naevus from choroidal melanoma. The published clinical and imaging risk factors for malignant transformation of choroidal naevus will be reviewed in the context of how AI applied to existing ophthalmic imaging systems might be able to determine features on medical images in an automated way. The thesis will include current knowledge to date and describe potential benefits, limitations and key issues that could arise with this technology in the ophthalmic field. Regulatory concerns will be addressed with possible solutions on how AI could be implemented in clinical practice and embedded into existing imaging technology with the potential to improve patient care and the diagnostic process. The PhD will also explore the feasibility of developed automated deep learning models and investigate the performance of these models in diagnosing choroidal naevomelanocytic lesions based on medical imaging, including colour fundus and autofluorescence fundus photographs. This research aimed to determine the sensitivity and specificity of an automated deep learning algorithm used for binary classification to differentiate choroidal melanomas from choroidal naevi and prove that a differentiation concept utilising a machine learning algorithm is feasible.

Type: Thesis (Doctoral)
Qualification: Ph.D
Title: Technological Advances in the Diagnosis and Management of Pigmented Fundus Tumours
Open access status: An open access version is available from UCL Discovery
Language: English
Additional information: Copyright © The Author 2021. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > Institute of Ophthalmology
URI: https://discovery.ucl.ac.uk/id/eprint/10161763
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item