Artificial Intelligence to Determine Lung Cancer Type

Research works in the area of lung cancer continues to bring new innovations. These days, the role of artificial intelligence is in full swing and it is now working to identify the types of lung cancer as well. Yes, you read it right! According to the study described in Journal Nature Medicine, an AI approach can instantly determine the cancer subtype and mutational profiles to get patients for targeted therapies.

The study led by researchers at NYU School of Medicine has found that a type of artificial intelligence could distinguish with 97 percent accuracy between adenocarcinoma and squamous cell carcinoma. These are the two types of lung cancer that are considered difficult to distinguish without confirmatory tests.

The AI was able to determine whether abnormal versions of six genes are linked to lung cancer such as EGFR, KRAS and TP53 with an accuracy ranging from 73% to 86%, depending on the gene. It could identify genetic changes related to abnormal growth of tumors. This type of identification is essential for the use of targeted treatments that act only against cancer cells with specific mutations.

Another useful feature of this new AI tool is that it provides results instantly as compared to existing tests for detection of such mutations that take weeks to offer results. In this study, the researchers have analyzed tumor images from the Cancer Genome Atlas, a database of images where cancer diagnoses had already been determined. Surprisingly, the study found that about half of the small percentage of tumor images misclassified by study AI programme was also misclassified by the pathologists. This highlights the difficulty in distinguishing between the two lung cancer types.

Narges Razavian, an assistant professor at NYU said, “In our study, we were excited to improve on pathologist-level accuracies, and to show that AI can discover previously unknown patterns in the visible features of cancer cells and the tissues around them.” “The synergy between data and computational power is creating unprecedented opportunities to improve both the practice and the science of medicine,” he added.

The team plans to keep training its AI program in the diagnosis of several cancer types.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.