Researchers at the Mahmood Laboratory at Brigham and Women’s Hospital have developed an artificial intelligence system that uses routinely acquired histology slides to precisely find the origin of tumors .
This new approach would improve the diagnosis of patients with complex metastatic cancers, especially those in low-resource settings.
Determining the primary tumor site
In 1 to 2 percent of cancer cases, the primary site of origin of the tumor cannot be determined . To receive a more specific diagnosis, patients often must undergo extensive diagnostic tests that may include additional laboratory tests, biopsies, and endoscopy procedures, which delay treatment.
This situation would improve with an algorithm based on deep learning developed by the researchers, called Tumor Origin Assessment via Deep Learning (TOAD), which simultaneously identifies the tumor as primary or metastatic and predicts its site of origin.
The researchers trained their model with gigapixel pathology full-slide images of tumors from more than 22,000 cancer cases , and then tested TOAD in approximately 6,500 cases with known primaries and analyzed increasingly complicated metastatic cancers to establish the utility of the model.
For tumors with known primary origins, the model correctly identified the cancer 83 percent of the time and listed the diagnosis among its top three predictions 96 percent of the time.