In a new study, an international team of engineers, mathematicians and doctors develop a new breast cancer detection method to identify cancerous cells in breast cancer histopathology images.
This method is developed based on a technique used for detecting damage in underwater marine structures.
Their multidisciplinary breakthrough has the potential to automate the screening of images and improve the detection rate. The finding has been published in PLOS ONE.
Breast cancer is the most common cancer for women worldwide. Current breast cancer clinical practice and treatment mainly relies on the evaluation of the disease’s prognosis using the Bloom-Richardson grading system.
The scoring is based on a pathologist’s visual examination of a tissue biopsy specimen under microscope, but different pathologists may assign different grades to the same specimens.
Recently, digital pathology and fast digital slide scanners have opened the possibility of automating the prognosis by applying image-processing methods.
Although this represents progress, image-processing methods have struggled to analyze high-grade breast cancer cells, because these cells are often clustered together and have vague boundaries, which makes successful detection very hard.
In the current study, the new breast cancer detection method has seemingly overcome that task.
The proposed technique was previously used for detecting damaged surface areas on underwater marine structures, such as bridge piers, off-shore wind turbine platforms and pipe-lines. Now it was applied to histopathology images of breast cells.
Using the method, the researchers considered the likelihood of every point in a histopathology image either being near a cell center or a cell boundary. Using a specific estimation method, the most suitable cell boundaries could be traced out.
The study is also an excellent example of how multidisciplinary research collaborations can address important societal issues.
In the team, experts in numerical methods and image-processing liaised with medical pathologists, who were able to offer expert insight and could tell precisely what information was of value to them.
Researchers suggest that it is nice to discover some cross-over applications and find areas where they could lend their expertise. They all find it particularly rewarding to contribute towards breast cancer research.
Citation: Paramanandam M, et al. (2016). Automated Segmentation of Nuclei in Breast Cancer Histopathology Images. PLOS One, published online. DOI: 10.1371/journal.pone.0162053.
Figure legend: This Knowridge.com image is credited to Steve Snodgrass.