Nature Sub-Journal: Using Artificial Intelligence to Detect Colorectal Cancer

According to a new study in the journal Nature Communications, a researcher at Tulane University found that artificial intelligence can accurately detect and diagnose colorectal cancer through tissue scans.

This research was conducted by researchers from Tulane University, Central South University of China, University of Oklahoma Health Science Center, Temple University, and Florida State University to test whether artificial intelligence can be used as a tool to help pathologists Keep up with the increasing demand for its services

Pathologists regularly evaluate and mark thousands of histopathological images to determine whether someone has cancer

"Although a lot of their work is repetitive, most pathologists are very busy because there is a huge demand for the work they do, but there is a lack of qualified pathologists in the world, especially in many developing countries.

To conduct this study, Deng and his team collected more than 13,000 colorectal cancer images from 8,803 subjects and 13 independent cancer centers in China, Germany, and the United States

"The challenge of this research comes from the complex large image size, complex shape, texture, and histological changes in nuclear staining," Deng said

The area under the receiver operating characteristic (ROC) curve (AUC) is a performance measurement tool used by Deng and his team to determine the success of research

Using artificial intelligence to identify cancer is an emerging technology that has not yet been widely accepted

"It is still in the research stage, and we have not commercialized it yet because we need to make it more convenient to use, and test and implement it in more clinical settings