News | Artificial Intelligence | April 18, 2019

Artificial Intelligence Performs As Well As Experienced Radiologists in Detecting Prostate Cancer

FocalNet artificial neural network achieves 80.5 percent accuracy in reading MRI scans for prostate cancer, compared to 83.9 percent for experienced radiologists

Artificial Intelligence Performs As Well As Experienced Radiologists in Detecting Prostate Cancer

April 18, 2019 — University of California Los Angeles (UCLA) researchers 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 by evaluating magnetic resonance imaging (MRI) scans, and it does so with nearly the same level of accuracy as experienced radiologists. In tests, FocalNet was 80.5 percent accurate in reading MRIs, while radiologists with at least 10 years of experience were 83.9 percent accurate.

Radiologists use MRI to detect and assess the aggressiveness of malignant prostate tumors. However, it typically takes 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. In addition, many hospitals do not have the resources to implement the highly specialized training required for detecting cancer from MRIs.

FocalNet is an artificial neural network that uses an algorithm that comprises more than a million trainable variables; it was developed by the UCLA researchers. The team trained the system by having it analyze MRI scans of 417 men with prostate cancer; 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. Researchers compared the artificial intelligence system’s results with readings by UCLA radiologists who had more than 10 years of experience.

The research suggests that an artificial intelligence system could save time and potentially provide diagnostic guidance to less-experienced radiologists.

The study’s senior authors are Kyung Sung, assistant professor of radiology at the David Geffen School of Medicine at UCLA; Steven Raman, M.D., a UCLA clinical professor of radiology and a member of the UCLA Jonsson Comprehensive Cancer Center; and Dieter Enzmann, M.D., chair of radiology at UCLA. The lead author is Ruiming Cao, a UCLA graduate student. Other authors are Amirhossein Bajgiran, Sohrab Mirak, Sepideh Shakeri and Xinran Zhong, all from UCLA.

The research is published in IEEE Transactions on Medical Imaging,1 and was presented at the IEEE International Symposium on Biomedical Imaging (ISBI), April 8-11 in Venice, Italy, where it was selected as the runner up-for best paper.

For more information: www.ieeexplore.ieee.org

 

Reference

1. Cao R., Bajgiran A.M., Mirak S.A., et al. Joint Prostate Cancer Detection and Gleason Score Prediction in mp-MRI via FocalNet. IEEE Transactions on Medical Imaging, published online Feb. 27, 2019. DOI: 10.1109/TMI.2019.2901928

Related Content

MRI Metal Artifact Reduction Poses Minimal Thermal Risk to Hip Arthroplasty Implants
News | Magnetic Resonance Imaging (MRI) | May 23, 2019
Clinical metal artifact reduction sequence (MARS) magnetic resonance imaging (MRI) protocols at 3 Tesla (3T) on hip...
VolparaDensity With Tyrer-Cuzick Model Improves Breast Cancer Risk Stratification
News | Breast Density | May 22, 2019
Research has demonstrated use of Volpara Solutions' VolparaDensity software in combination with the Tyrer-Cuzick Breast...
Henry Ford Hospital's ViewRay MRIdian linear accelerator system allows real-time MRI-guided radiotherapy. Shown is the support staff for this system. In the center of the photo is Benjamin Movsas, M.D., chair of radiation oncology at Henry Ford Cancer Institute. Second from the right is Carrie Glide-Hurst, Ph.D., director of translational research, radiation oncology.

Henry Ford Hospital's ViewRay MRIdian linear accelerator system allows real-time MRI-guided radiotherapy. Shown is the support staff for this system. In the center of the photo is Benjamin Movsas, M.D., chair of radiation oncology at Henry Ford Cancer Institute. Second from the right is Carri Glide-Hurst, Ph.D., director of translational research, radiation oncology.

Feature | Henry Ford Hospital | May 21, 2019 | Dave Fornell, Editor
Henry Ford Hospital thought leaders regularly speak at the radiation oncology and radiology conferences about new res
MaxQ AI Launches Accipio Ax Slice-Level Intracranial Hemorrhage Detection
Technology | Computer-Aided Detection Software | May 21, 2019
Medical diagnostic artificial intelligence (AI) company MaxQ AI announced that Accipio Ax will begin shipping in August...
Videos | Radiation Therapy | May 21, 2019
This is a walk through of the ViewRay MRIdian MRI-guided radiotherapy system installed at ...
AI Detects Unsuspected Lung Cancer in Radiology Reports, Augments Clinical Follow-up
News | Artificial Intelligence | May 20, 2019
Digital Reasoning announced results from its automated radiology report analytics research. In a series of experiments...
360 Photos | Magnetic Resonance Imaging (MRI) | May 17, 2019
This is a dedicated cardiac Siemens 1.5T MRI system installed at the Baylor Scott White Heart Hospital in Dallas.
Miami Cardiac and Vascular Institute Implements Philips Ingenia Ambition X 1.5T MRI
News | Magnetic Resonance Imaging (MRI) | May 17, 2019
Miami Cardiac & Vascular Institute announced the implementation of Philips’ Ingenia Ambition X 1.5T MR, the world’s...
Brain images that have been pre-reviewed by the Viz.AI artificial intelligence software to identify a stroke. The software automatically sends and alert to the attending physician's smartphone with links to the imaging for a final human assessment to help speed the time to diagnosis and treatment. Depending on the type of stroke, quick action is needed to either activate the neuro-interventional lab or to administer tPA. Photo by Dave Fornell.

Brain images that have been pre-reviewed by the Viz.AI artificial intelligence software to identify a stroke. The software automatically sends and alert to the attending physician's smartphone with links to the imaging for a final human assessment to help speed the time to diagnosis and treatment. Depending on the type of stroke, quick action is needed to either activate the neuro-interventional lab or to administer tPA. Photo by Dave Fornell.

Feature | Artificial Intelligence | May 17, 2019 | Inga Shugalo
With its increasing role in medical imaging,...