Abstract
Researchers from the Brigham and Women's Hospital have developed a deep-learning based algorithm that can accurately predict the origin of primary tumors based on imaging data.
Although the origin of most primary tumors is known, in around 1-2% of cancer cases where multiple tumors are present at diagnosis it is difficult to know where the cancer originated.
To try and simplify diagnosis in these cases, Faisal Mahmood, an assistant professor at Harvard Medical School, and his team used diagnostic histology slide images to train their deep learning algorithm to accurately predict the location of a patients primary tumor.
“Our work provides a way to leverage universally acquired data and the power of artificial intelligence to improve diagnosis for these complicated cases that typically require extensive diagnostic work-ups,” says Mahmood, lead author on the paper describing the work in Nature.
Before testing their algorithm on for diagnostic purposes, the researchers first trained the model using slide images from 22,000 patients with cancer, followed by images from 6,500 cases with a known location of their primary tumor.
The model was 83% accurate at identifying the correct primary cancer in the group where the primary tumor origin was known and the correct diagnosis was in the top three options selected by the algorithm 96% of the time.
In 317 cancer cases where the primary tumor location was unknown, the algorithm agreed with a differential diagnosis given by a pathologist 61% of the time and the diagnosis was in the top three computer-selected options 82% of the time.