Automated tech can detect eye surface cancer

Researchers have developed an automated, non-invasive technique for diagnosing eye surface cancer, which may reduce the need for biopsies, prevent therapy delays and make treatment far more effective for patients.

The method, described in the journal The Ocular Surface, 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 ocular surface squamous neoplasia (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," said Abbas Habibalahi, a researcher at the Australian Research Council (ARC) Centre of Excellence for Nanoscale BioPhotonics (CNBP).

"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," said Habibalahi, lead scientist on the project.

Researchers 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," said Habibalahi.

"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," he said.

Tissue samples from eighteen patients with OSSN were tested.

"We successfully identified the diseased cells in all eighteen cases. A quick test using our automated system is all that is necessary to pick up early warning signs of OSSN," said Habibalahi.

A key benefit of the innovative setup is that the OSSN diagnosis foregoes the need for a biopsy approach.

"This benefits both the patient and the doctor. Biopsies of the eye can be traumatic and can also be costly and time intensive with samples needing to be sent to a laboratory for testing," Habibalahi said.

In addition to the early-detection and non-invasive benefits, the technology is able to precisely map the location of abnormal tissue margins on the eye.

"Next steps are to make our system practical and workable in a clinical setting. We hope to do this by incorporating our system into a standard retinal camera setup -- similar to that used by opticians and optometrists when undertaking regular eye examinations," he said.