All news

Pathomorphology: a new direction in AI diagnostic imaging


The team of our service has started to work in a new direction – pathomorphology. Celsus will now be able to perform histological analysis and detect circulating tumor cells by studying breast tissue samples.

Diagnostic procedure for cancer is impossible without histological examination as it helps to identify the type of a neoplasm and its characteristics. In order to perform this analysis, a pathomorphologist should examine a tissue fragment taken from a patient. 

Tissue samples are scanned, digitized and, instead of traditional microscopic examination, they are displayed on the screen. 

Artificial intelligence can be helpful at this stage. Celsus will independently locate the areas with pathological cells and separate the affected areas from the healthy ones. Later on, we will train the system to mark suspicious areas, too.

The scientific work is being carried out in collaboration with Nizhny Novgorod Regional Clinical Oncology Center. Qualified doctors participate in the data preparation and labeling. Our database includes verified cancer cases.

Histological examination is a difficult and time-consuming study which is not available in every region of the country. Tissue samples are often sent to the laboratories of bigger cities which not only requires more time but also places an additional burden on the specialists. The use of artificial intelligence in histological examination will reduce the burden on pathomorphologists and, as a result, the risks of incorrect and inaccurate diagnosis.