About 2% to 3% of cancers diagnosed each year in France are cancers “of unknown origin” or “of unknown primary”.
Clear : these cancers (which affect around 7000 patients per year in France) are only detected at the metastatic stage, that is to say when the disease begins to spread in the tissues of the body without being able to identify the first organ affected.
Unfortunately, these cancers are particularly difficult to treat: diagnosed at an advanced stage, they are only treated with non-specific broad-spectrum chemotherapy. “Without knowing the origin of cancer, it is impossible to find the most suitable treatment” specifies Institut Curie.
An intelligent algorithm capable of identifying the origin of a tumor
Precisely: researchers from the Institut Curie have just developed an artificial intelligence capable of identifying the origin of cancer of unknown primary. This algorithm of deep learning (read: deep learning) sequences all of the genes expressed in a tumor to relate its profile to a specific organ or tissue.
And it works. The Institut Curie submitted genetic data concerning 48 tumors of unknown origin to the algorithm: in 79% of cases, the algorithm was able to identify a tissue of origin. And among 11 patients just diagnosed, 8 were able to receive a treatment chosen according to this result; all of them benefited from the treatment. Hope for affected patients …
Source:
Identification of Tissue of Origin and Guided Therapeutic Applications in Cancers of Unknown Primary Using Deep Learning and RNA Sequencing (TransCUPtomics), Journal of Molecular Diagnostics, July 26, 2021.
Read also :
- Cancer: what exactly is immunotherapy?
- Blue Mars: colorectal cancer screening in 9 questions / answers
- Breast cancer screenings drop in 2020