A powerful way of predicting patient outcome. Researchers have developed a software tool that uses Artificial Intelligence (AI) to recognize cancer cells from digital pathology images.<\/p>\n
<\/p>\n
(People Also Like To Read: <\/strong>India is in an Advanced Stage of Developing a Vaccine for Dengue: Health Minister<\/a>)<\/strong><\/em><\/p>\n <\/p>\n The spatial distribution of different types of cells can reveal cancer’s growth pattern and their relation with the surrounding micro-environment as well as the body’s immune response<\/a>.<\/p>\n <\/p>\n The manual process of identifying all the cells in a pathology slide is extremely labor-intensive plus error-prone as well.<\/p>\n <\/p>\n The corresponding author of a study published in E-bioMedicine<\/a>, Dr. Guanghua “Andy” Xiao said, “To make a diagnosis, pathologists usually only examine several ‘representative’ regions in detail, rather than the whole slide. However, some important details could be missed by this approach.”<\/p>\n <\/p>\n How to automatically classify different types of cells and quantify their spatial distributions is a major technical challenge in systematically studying the tumor micro-environment.<\/p>\n <\/p>\n To overcomes these obstacles by using AI to classify cell types from lung cancer pathology images. The AI algorithm that Dr. Xiao and his team developed, called “ConvPath”.<\/p>\n <\/p>\n AI algorithm learns from human pathologists. The algorithm can look at cells and identify their types based on their appearance in the pathology images.<\/p>\n <\/p>\n The pathologists can obtain the most accurate cancer cell analysis in a much faster way with the help of the algorithm.<\/p>\n <\/p>\n Dr. Xiao said, “It is time-consuming and difficult for pathologists to locate very small tumor regions in tissue images, so this could greatly reduce the time that pathologists need to spend on each image.”<\/p>\n <\/p>\n