Check out two recent articles from Science and the Los Angeles Times, featuring personal stories from MSK researchers.
Category Archives: In the News
When Artificial Intelligence Meets Pathology
In a recent Nature Medicine article, MSK’s Dr. Thomas Fuchs and his colleagues describe how they trained artificial intelligence (AI) to process pathology slides at large scale. The research was completed with the start-up Paige.AI and is reported by The Cancer Letter, Tech Crunch, Becker’s Healthcare, and 360 DX.
Dr. Thomas Fuchs. Credit: Richard DeWitt
To train deep learning systems, researchers typically need to manually curate data, a time-consuming process that has previously prevented large-scale AI applications to pathology datasets. In this study, researchers instead trained the system using only the slide-level diagnostic information already in the electronic health record. The study included 44,732 slides of prostate, skin, or axillary lymph node tissue from 15,187 patients at 800 institutions. Their calculations indicate that the model could reduce a pathologist’s workload by up to 75%, classifying cancer without sacrificing sensitivity.
To learn more about artificial intelligence, including a list of the latest AI-related publications from MSK authors, check out the Library’s new LibGuide.
Predicting Immunotherapy Response, Cancer Relapse and More
- The researchers at Fred Hutchinson Cancer Research Center discovered that cancer cells express DUX4, a gene responsible for certain muscular dystrophies, to protect themselves from the effects of immunotherapy, in particular – from immune checkpoint inhibitors. The implications of this research would be development of therapies that would target DUX4 and thus make treatment with immune checkpoint inhibitors more efficient. The study is due to be published in Developmental Cell.
- Researchers from the University of Western Australia in collaboration with Telethon Kids Institute and 13 health research organizations looked into the genes in cancer samples and devised a way of using cancer samples to identify potential response to immune checkpoint inhibitors therapy before initiating immunotherapy treatment. This could help identify drugs that improve response to checkpoint inhibitors. The study was published in Science Translational Medicine.
- Researchers from the City of Hope Comprehensive Cancer Center have come close to developing a blood test, based on a patient’s immune response, which may predict relapse of breast cancer. The study was published in Nature Immunology.
- It is known that cancer cells spread in the body by feeding on sugar. British researchers discovered that if deprived of sugar, cancer cells switch, with the help of a protein called AKR1B10, to fatty acids as a source of energy to boost their spread. The implications could be for diagnosis, as increased levels AKR1B10 may predict metastatic spread; and for management, which means development of new treatments that would prevent cancer cells from using fatty acids. This preclinical study was published in Nature Communications.