Researchers at the University of Pittsburgh and the University of Pittsburgh Medical Center (UPMC) trained an artificial intelligence (AI) program to recognize and characterize prostate cancer, achieving the highest accuracy rate to date.
The researchers used images from more than 1 million parts of stained tissue slides taken from patient biopsies to train the AI, then tested the algorithm on a set of 1,600 slides from 100 consecutive patients seen for suspected prostate cancer.
The AI demonstrated 98% sensitivity and 97% specificity at detecting prostate cancer.
The algorithm also is the first to achieve high performance for tumor grading, sizing, and invasion of the surrounding nerves.
Said UPMC's Rajiv Dhir, "Algorithms like this are especially useful in lesions that are atypical. A nonspecialized person may not be able to make the correct assessment."
Dhir added that new algorithms will need to be trained to detect other types of cancer.
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found