Bladder cancer is the fourth most common cancer in males and the eleventh most common in females. Cytology is taken as one of the keystone elements in the screening and diagnosis of bladder cancer. Routinely, pap stain is applied to cells separated from patient urine and the qualitative analyses of malignancy was traditionally determined by a Cytopathologist.
Cell counting is not usually undertaken in such instances. The application of minichromosome maintenance protein (MCM), as an index of cell cycling and possible epithelial malignancy, has been used to determine the presence of cancer and cell numbers are important in such diagnostics.
This was a study undertaken by Cytosystems in conjunction with the NHS in Scotland in the early 2000’s. The objective was to explore the viability of using machine vision to automate the counting of MCM proteins in cytology samples.
Dan and Jamie first worked together on this project whilst Jamie was a postgraduate at Robert Gordon University, working towards his PhD. Dan spent many hours in Aberdeen, sitting with the Pathologists to learn and to translate their manual diagnostics know-how into a machine vision algorithm.
The results were promising, as the published academic paper at the time concluded that; ‘Preliminary data confirm that MCM stained cell counts in urinary cell deposits from patients under investigation for bladder cancer is manually demanding but may be improved using an automated digital cell counting system.’
Of course, automated cell counting systems are commonplace today and with the use of AI these diagnostic systems are very powerful.
Our team wasn’t in a position to pursue the project any further but we were certainly pioneers!