We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.
Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
BUTLER TILL MEDIA

Download Mobile App




New AI System Performs As Well As Radiologists in Detecting Prostate Cancer

By HospiMedica International staff writers
Posted on 24 Apr 2019
Print article
Image: The new artificial intelligence system is designed to help radiologists improve their ability to diagnose prostate cancer (Photo courtesy of Shutterstock).
Image: The new artificial intelligence system is designed to help radiologists improve their ability to diagnose prostate cancer (Photo courtesy of Shutterstock).
Researchers from the University of California {(UCLA), Los Angeles, CA, USA} have developed a new artificial intelligence (AI) system to help radiologists improve their ability to diagnose prostate cancer. The system, called FocalNet, helps identify and predict the aggressiveness of the disease evaluating magnetic resonance imaging (MRI) scans with almost the same level of accuracy as experienced radiologists.

Typically, radiologists use MRI to detect and assess the aggressiveness of malignant prostate tumors. However, this requires practicing on thousands of scans to learn how to accurately determine whether a tumor is cancerous or benign and to accurately estimate the grade of the cancer. Additionally, many hospitals lack the resources to implement the highly specialized training required for detecting cancer from MRIs.

FocalNet is an artificial neural network that can help radiologists improve their ability to diagnose prostate cancer by using an algorithm comprising over one million trainable variables. The UCLA researchers trained the system by making it analyze MRI scans of 417 men with prostate cancer. The scans were fed into the system so that it could learn to assess and classify tumors in a consistent way and have it compare the results to the actual pathology specimen. The researchers tested FocalNet and found it to be 80.5% accurate in reading MRIs, as compared to radiologists having at least 10 years of experience who were 83.9% accurate. This suggests that an AI system could save time and potentially provide diagnostic guidance to less-experienced radiologists.

Related Links:
University of California Los Angeles



Print article

Channels

Copyright © 2000-2019 Globetech Media. All rights reserved.