Oral cancer is one of the most common types of cancer that develops in the tissues of the mouth. Patients diagnosed at advanced stages have only a 40% chance of survival and commonly require painful and highly invasive surgery to remove parts of the oral cavity. In contrast, patients diagnosed early usually require minor surgery and have an 84% chance of survival. Therefore, early detection holds great promise for improving both the survival rate and quality of life of these patients.
An optical technology named Fluorescence lifetime imaging (FLIM) endoscopy is one promising imaging modality that can capture indicative parameters to discriminate lesion tissues from normal tissues. The lesion tissues can be further categorized into (1) Benign Lesions (non-cancerous), (2) Precancerous Lesions, and (3) Cancerous Lesions. Multispectral FLIM images of lesion and healthy tissues from 125 patients were acquired for the research study.
In this project, you will be applying statistical image processing and machine learning methods to discriminate the benign, precancerous, cancerous, and healthy tissues, which will eventually lead to the development of an automated framework for oral cancer diagnosis.
At the completion of the project, you will have significantly strengthened your knowledge and understanding in signal processing, modelling and machine learning, as well your programming skills in MATLAB/Julia/Python.
(a) A mathematical framework that would underpin an FLIM based automated cancer detection algorithm;
(b) Functional and tested code that implements the developed system and available for use by other researchers. If the topic were extended into an honours thesis, more would be possible
Elvis Duran-Sierra et al., Clinical label-free biochemical and metabolic fluorescence lifetime endoscopic imaging of precancerous and cancerous oral lesions, Oral Oncology, Volume 105, 2020, 104635, ISSN 1368-8375, https://doi.org/10.1016/j.oraloncology.2020.104635
Dr Beena Ahmed
Dr Vidhyasaharan Sethu (email@example.com)