Revolutionizing Lung Cancer Detection With Self-Taught AI

Commentary
Video

Aristotelis Tsirigos, PhD, discusses a self-taught artificial intelligence tool being developed to accurately diagnose cases of adenocarcinoma.

Aristotelis Tsirigos, PhD, study co-senior investigator, professor in the Departments of Pathology and Medicine at NYU Grossman School of Medicine and Perlmutter Cancer Center, and co-director of precision medicine and director of its Applied Bioinformatics Laboratories, discusses a self-taught artificial intelligence (AI) tool being developed to accurately diagnose cases of adenocarcinoma.

According to a new study performed and developed by researchers at NYU Langone Health's Perlmutter Cancer Center and the University of Glasgow, the computer program provides an unbiased, detailed, and reliable second opinion for patients and oncologists regarding cancer presence and prognosis. Findings from the study were published in Nature Communications and showed that the AI tool could accurately distinguish between similar lung cancers 99% of the time, including adenocarcinoma and squamous cell cancers.

Transcription:

0:09 | This is one of the AI tools that you may have heard about out there. The difference with this tool is that it is self-taught. I think that is the main message of the paper. And that is very important because typically, when you train a machine learning model, you need to know what the diagnosis is in the medical space. But that requires quite a bit of effort from the pathologist side.

0:38 | So here, we decided to do it in a completely unsupervised way, which means the machine, the algorithm itself, would have to teach itself what the important parts of the image are so it could go ahead and do the diagnostics. But this tool can be used in different contexts for different diseases. We are focused on lung cancer, but of course, it is applicable to different types of cancer.

Transcription created with AI and edited for clarity.

REFERENCE:
Claudio Quiros A, Coudray N, Yeaton A, et al. Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unannotated pathology slides. Nat Commun. 2024;15(1):4596. Published 2024 Jun 11. doi:10.1038/s41467-024-48666-7
Recent Videos
The Oncology Brothers with Joshua K. Sabari, MD, presenting slides
The Oncology Brothers with Joshua K. Sabari, MD, presenting slides
The Oncology Brothers with Joshua K. Sabari, MD, presenting slides
The Oncology Brothers with Joshua K. Sabari, MD, presenting slides
The Oncology Brothers with Joshua K. Sabari, MD, presenting slides
Related Content