AI tool helps grade cancer based on cell divisions

In numerous cancer types, counting the number of cells undergoing division, known as mitotic figures, serves as a key indicator of cancer aggressiveness, or grade. This information helps inform treatment pathways, making it a crucial asessment tool.

Traditional mitosis counting is both time-consuming and plagued by poor reliability. To address this, scientists have developed a new tool, MitPro, which uses AI to count and profile mitosis.

Histofy, a spin-out company from The University of Warwick that is leading developer of AI solutions for pathology, has engineered the tool to accurately profile mitosis throughout the entire tumour sample. This identifies the most suitable areas for further analysis. The tool enhances the current standard of care for grading various cancers, such as breast cancer and sarcomas, by accurately identifying dividing cancer cells. In this context, an elevated count of dividing cells indicates a fast-growing or highly aggressive tumour. Traditionally, pathologists perform this cell counting, but due to time constraints, it is limited to a small portion of the tumour. With the power of AI, MitPro can count these dividing cells more accurately and over the entire tumour, providing a better indication for the cancer grade and leading to enhanced patient care and management.

Article • Revolution through AI

Pixel analysis: the new era of digital pathology

As reporting workload for pathology departments continues to rise rapidly, artificial Intelligence (AI) solutions are set to play an increasing role in daily practice. ‘I see this as the future of digital pathology,’ said histopathologist Professor David Snead at the Digital Pathology and Artificial Intelligence Congress held in London.

Professor David Snead, Chief Medical Officer at Histofy, and a Consultant Pathologist at the University Hospitals Coventry and Warwickshire (UHCW) said: “Despite its paramount importance, mitosis assessment can be laborious and suffers from reproducibility issues. We are thrilled to introduce MitPro, a solution that not only improves current practice, but also enables detailed profiling of cell proliferation across the entire tumour.”

Chief Technology Officer at Histofy, Simon Graham, Department of Computer Science at the University of Warwick, said: “AI holds tremendous potential in facilitating better cancer care. MitPro helps to improve current grading systems across a range of cancers by more accurately assessing the rate in which cancer cells are dividing.”

To facilitate the widespread adoption of AI in clinical settings, Histofy is integrating with established pathology image management systems, including Sectra.

Source: University of Warwick

02.02.2024