Researchers at the University of Warwick have developed new statistical image analysis method for automatic mitotic cell detection for cancer diagnosis.
The new method enables segmenting tumor regions and detecting dividing cells in tissue samples thereby facilitating breast cancer grading.
The University of Warwick computer science department associate professor Dr Nasir Rajpoot said that there is a need to increase objectivity in the cancer grading process.
"This grading process determines the treatment offered to people who have been diagnosed with cancer, so it's vital to get it right in order to prevent patients undergoing unnecessarily aggressive treatments," Dr Rajpoot added.
"We believe our method takes a significant step towards this by offering an objective, automatic technique to assist the pathologists in grading of breast cancer."
The first step in the three-step method includes segmenting the tumor margins for the precise detection of the mitotic cell.
Second step involves the statistically modelling of the intensity distribution of the mitotic and non-mitotic cells in tumor areas that help in detecting potential mitotic cells in tumor areas.
As a final step, the surrounding architecture of the potential mitotic cells will be observed to check them if they are mitotic cells to reduce the number of possible false alarms.
