A new automated non-invasive technique for diagnosing eye surface cancer (ocular surface squamous neoplasia or OSSN) has been developed by CNBP researchers and collaborators. The technique has the potential to reduce the need for biopsies, prevent therapy delays and make treatment far more effective for patients.
Reported in a clinical journal ‘The Ocular Surface’, the innovative method comprises the custom-building of an advanced imaging microscope in association with state-of-the-art computing and artificial intelligence operation. The result is an automated system that is able to successfully identify between diseased and non-diseased eye tissue, in real-time, through a simple scanning process.
“Clinical symptoms of OSSN are known to be variable and in early stages can be extremely hard to detect so patients may experience delays in treatment or be inaccurately diagnosed,” says Mr Habibalahi, Researcher at the ARC Centre of Excellence for Nanoscale BioPhotonics (CNBP) and lead scientist on the project.
“The early detection of OSSN is critical as it supports simple and more curative treatments such as topical therapies whereas advanced lesions may require eye surgery or even the removal of the eye, and also has the risk of mortality,” he says.
What Mr Habibalahi and the research team have developed is a technological approach that utilises the power of both microscopy and cutting-edge machine learning.
“Our hi-tech system scans the natural light given off by specific cells of the eye, after being stimulated by safe levels of artificial light. Diseased cells have their own specific ‘light-wave’ signature which our specially designed computational algorithm is then able to identify providing a quick and efficient diagnosis,” says Mr Habibalahi.
Read the full media release here.
Journal: The Ocular Surface.
Authors: Abbas Habibalahi, Chandra Bala, Alexandra Allende, Ayad G.Anwer, Ewa M.Goldys.
Diagnosing Ocular surface squamous neoplasia (OSSN) using newly designed multispectral imaging technique.
Eighteen patients with histopathological diagnosis of Ocular Surface Squamous Neoplasia (OSSN) were recruited. Their previously collected biopsy specimens of OSSN were reprocessed without staining to obtain auto fluorescence multispectral microscopy images. This technique involved a custom-built spectral imaging system with 38 spectral channels. Inter and intra-patient frameworks were deployed to automatically detect and delineate OSSN using machine learning methods. Different machine learning methods were evaluated, with K nearest neighbor and Support Vector Machine chosen as preferred classifiers for intra- and inter-patient frameworks, respectively. The performance of the technique was evaluated against a pathological assessment.
Quantitative analysis of the spectral images provided a strong multispectral signature of a relative difference between neoplastic and normal tissue both within each patient (at p < 0.0005) and between patients (at p < 0.001). Our fully automated diagnostic method based on machine learning produces maps of the relatively well circumscribed neoplastic-non neoplastic interface. Such maps can be rapidly generated in quasi-real time and used for intraoperative assessment. Generally, OSSN could be detected using multispectral analysis in all patients investigated here. The cancer margins detected by multispectral analysis were in close and reasonable agreement with the margins observed in the H&E sections in intra- and inter-patient classification, respectively.
This study shows the feasibility of using multispectral auto-florescence imaging to detect and find the boundary of human OSSN. Fully automated analysis of multispectral images based on machine learning methods provides a promising diagnostic tool for OSSN which can be translated to future clinical applications.