Image Source: Genetic Engineering and Biotechnology
Artificial intelligence in identifying cancer is an emerging technology. Many researchers have worked and conducted dozens of experiments on the power of AI to detect cancer and have shown how the integration of AI technology in cancer care could improve the accuracy and speed of diagnosis, and lead to better health outcomes.
Researchers from Tulane, Central South University in China, Temple University, the University of Oklahoma Health Sciences Center, and Florida State University have collaborated to determine whether AI could be a helpful tool to assist pathologists to detect colorectal cancer.
Colorectal Cancer (CRC) is the second most common cause of cancer death in Europe and America. Pathological diagnosis is one of the most authoritative methods for diagnosing CRC, which requires a pathologist to visually examine digital full-scale whole slide images (WSI).
The researcher gathered over 13,000 images of colorectal cancer from 8,803 subjects and 13 independent cancer centers in China, Germany, and the United States. After a long struggle researchers have developed a machine-assisted pathological recognition program that allows a computer to recognize images that show colorectal cancer.
Image Source: CIO
The researchers said that their work has confirmed unlabeled data could improve the accuracy of insufficient labeled pathological images. We showed that SSL (semi-supervised learning) with a small amount of labeled data of three cancers achieved comparable prediction accuracy as that of SL with massive labeled data and that of experienced pathologists concluded the researchers.
It is still in the research phase and researchers have not commercialized it yet because wanted to make it more friendly and test and implement it in more clinical settings. They also hope for further modification hopefully it can be used for different types of cancer in the future. Using AI to cure and diagnose cancer can accelerate the whole process and will save a lot of time for both patients and clinicians.