News, Analysis, Trends, Management Innovations for
Clinical Laboratories and Pathology Groups

Hosted by Robert Michel

News, Analysis, Trends, Management Innovations for
Clinical Laboratories and Pathology Groups

Hosted by Robert Michel
Sign In

UPMC Researchers Develop Artificial Intelligence Algorithm That Detects Prostate Cancer with ‘Near Perfect Accuracy’ in Effort to Improve How Pathologists Diagnose Cancer

Working from tissue slides similar to those used by surgical pathologists, the algorithm accurately detects prostate cancer with an impressive 98% sensitivity

It could be that a new milestone has been reached on the road to using artificial intelligence (AI) to help anatomic pathologists diagnose cancer and other diseases. A research collaboration between a major American university and an Israeli company recently published a study about the ability of an AI algorithm to correctly diagnose prostate cancer.

The collaboration involved researchers at the University of Pittsburgh Medical Center (UPMC) and at Ibex Medical Analytics of Israel. The research team created an AI algorithm dubbed the Galen Prostate (part of the Galen Platform). In the study, the Galen Prostate AI accurately detected prostate cancer with 98% sensitivity and 97% specificity.

Researchers noted that this level of diagnostic sensitivity and specificity was significantly higher, compared to previously tested cancer-detecting algorithms that utilized tissue slides. The UPMC scientists published their findings in The Lancet Digital Health, titled, “An Artificial Intelligence Algorithm for Prostate Cancer Diagnosis in Whole Slide Images of Core Needle Biopsies: A Blinded Clinical Validation and Deployment Study.”

AI Show and Tell in Anatomic Pathology

The scientists trained the Galen Prostate AI to recognize prostate cancer by having it examine images from over a million parts of stained tissue slides taken from patient biopsies. Expert pathologists labeled each image to teach the algorithm how to distinguish between healthy and abnormal tissue. The AI was then tested on 1,600 different tissue slide images that had been collected from 100 patients seen at UPMC who were suspected of having prostate cancer.  

“Humans are good at recognizing anomalies, but they have their own biases or past experience,” said Rajiv Dhir, MD, Chief Pathologist and Vice Chair of Pathology at UPMC Shadyside Hospital, Professor of Biomedical Informatics at University of Pittsburgh, and senior author of the study, in a UPMC news release. “Machines are detached from the whole story. There’s definitely an element of standardizing care.”

Ibex Galen Prostate AI solution
The image above is “of prostate cancer (represented by the heatmap) detected by the Ibex Galen Prostate [AI] solution on a biopsy that was previously diagnosed as benign by the pathologist,” stated an Ibex news release announcing the UPMC study. (Photo copyright: Ibex.)

UPMC Algorithm Goes Beyond Cancer Detection, Exceeds Human Pathologists

The researchers also noted that this is the first algorithm to extend beyond cancer detection. It reported high performance for tumor grading, sizing, and invasion of surrounding nerves—clinically important features of pathology reports.  

“Algorithms like this are especially useful in lesions that are atypical,” Dhir said. “A nonspecialized person may not be able to make the correct assessment. That’s a major advantage of this kind of system.”

The algorithm also flagged six slides as potentially containing abnormal tissue that were not flagged by human pathologists. However, the researchers pointed out that this difference does not mean the AI is better than humans at detecting prostate cancer. It is probable, for example, that the pathologists simply saw enough evidence of malignancy elsewhere in the patients’ samples to recommend treatment.

Other Studies Where AI Detected Prostate Cancer

The UPMC researchers are not the first to use AI to detect prostate cancer. In February, The Lancet Oncology published a study from researchers at Radboud University Medical Center (RUMC) in the Netherlands who developed a deep learning AI system that could determine the aggressiveness of prostate cancer in certain patients. 

For that research, the RUMC scientists collected 6,000 biopsies from more than 1,200 men. They then showed the biopsy images along with the original pathology reports to their AI system. Using deep learning, the AI was able to detect and grade prostate cancer according to the Gleason Grading System (aka, Gleason Score), which is used to rate prostate cancer and choose appropriate treatment options. The Gleason Score ranges from one to five and most cancers obtain a score of three or higher. 

“Systems such as ours can be used in different ways. First, it can be used to screen biopsies and to filter out the easy (benign) cases. This could reduce the workload for pathologists,” said Wouter Bulten, a PhD candidate at Radboud who worked on the study, in an interview with HemOnc Today. “Second, the system can be used as a second opinion after the pathologist’s initial read. The system can flag a case if its opinion differs from that of the pathologist. It also can give feedback during the first read, showing the pathologist where to look. In this case, the pathologist needs only to confirm the opinion of the AI system.” 

Can Today’s AI Outperform Human Pathologists?

In their research, the Radboud team discovered that their AI system was able to achieve pathologist-level performance and, in some cases, even performed better than human pathologists. However, they do not foresee AI replacing the need for pathologists, but rather emerging as another method to use in cancer detection and treatment.  

“We see our system as an additional tool that the pathologist can use. Although our system performs very well, it still makes mistakes,” stated Bulten. “These mistakes are often different from those a human would make. We believe that when you merge the expertise of the pathologist with the second opinion of an AI system, you get the best of both worlds.” 

According to the American Cancer Society, prostate cancer is the second most common cancer among men in the US, after skin cancer. The organization estimates there will be approximately 191,930 new cases of prostate cancer diagnosed and about 33,330 deaths from the disease in the US in 2020. 

Though the UPMC study focused only on prostate cancer, the scientists believe their algorithm can be trained to detect other types of cancer as well. AI in clinical diagnostics is clearly progressing, however more studies will be required. Nevertheless, if AI can truly become a useful tool for anatomic pathologists to detect cancer earlier, we may see a welcomed reduction in cancer deaths.   

—JP Schlingman

Related Information:

Newly Developed AI Capable of Identifying Prostate Cancer with “Near-perfect Accuracy”

An Artificial Intelligence Algorithm for Prostate Cancer Diagnosis in Whole Slide Images of Core Needle Biopsies: A Blinded Clinical Validation and Deployment Study

Artificial Intelligence Identifies Prostate Cancer

The Lancet Reports Outstanding Performance of Ibex Medical Analytics’ AI-based Algorithm in a Study at UPMC

Prostate Cancer Can Now be Diagnosed Better Using Artificial Intelligence

AI System Outperforms Pathologists in Identifying Prostate Cancer Aggressiveness

Automated Deep-learning System for Gleason Grading of Prostate Cancer using Biopsies: A Diagnostic Study

New AI Technology Helps Pathologists Spot Cancer

Hospitals Worldwide Are Deploying Artificial Intelligence and Predictive Analytics Systems for Early Detection of Sepsis in a Trend That Could Help Clinical Laboratories, Microbiologists

CMS Considers Using Artificial Intelligence to Battle Fraud; Medical Laboratories Must Ensure Billing Practices Comply with New Federal Affiliation Regulations

Mobile Device Software Companies Are Developing Smartphone Apps That Use Artificial Intelligence to Test for COVID-19, Potentially Bypassing the Clinical Laboratory Altogether

Is New Cervical Cancer Test Better Than a Pap Smear?

Intense research into cervical cancer detection and treatment has yielded significant progress in the past decade. One common cause of such cancer is the human papillomavirus (HPV). New developments involving HPV have produced thin-layer Pap smears, HPV testing, and HPV vaccines. Now, researchers in Italy are reporting a new twist in HPV screening and detection. In research published in the journal Lancet Oncology, Guglielmo Ronco, a cancer epidemiologist at the Centre for Cancer Prevention in Turin, reported that a new way to test for cervical cancer is more accurate than a pap smear alone and identified more dangerous lesions.

Clinicians can improve the specificity of DNA tests for HPV by testing for the presence of a protein that is over-expressed in cervical cancer cells, the new research shows. The molecular test tends to give more false positives, increasing the number of unneeded referrals for colposcopy, Ronco and colleagues reported online in the journal Lancet Oncology. (Carozzi F, et al “Use of p16-INK4A overexpression to increase the specificity of human papillomavirus testing: a nested substudy of the NTCC randomised controlled trial” Lancet Oncology 2008; DOI: 10.1016/S1470-2045(08)70208-0.)

DNA tests for HPV are more likely to pick up cases of high-grade cervical intraepithelial neoplasia (CIN) than conventional cytology, Ronco and colleagues reported. Since the molecular method gives more false positives, it tends to increase the number of unneeded referrals for colposcopy, Dr. Ronco and colleagues reported. To improve specificity, the researchers considered the cyclin-dependent kinase inhibitor p16-INK4A (p16), which is considered to be a marker of HPV infection, according to a report on the findings at

Since only a small percentage of women who have an HPV infection actually develop cancer, the challenge for researchers is to identify those who have the highest risk for developing the disease. By testing for a the presence of P16, the researchers said they had identified a biomarker showing cell changes that indicated whether a woman was likely to have pre-cancerous lesions, Ronco and colleagues reported. “The marker shows there was some sort of disruption by the HPV virus,” Ronco said.

“Our data show that in HPV-positive women, p16-INK4A over-expression is strongly associated with the presence of histologically confirmed CIN2+, suggesting that it actually is a marker of progression,” Dr. Ronco said. “This study supports the application of triage by P16INK4A immunostaining in HPV-positive women,” he added.

Data from the U.S. National Cancer Institute show that an estimated 11,000 women in the United States would be diagnosed with this type of cancer and nearly 4,000 would die from it last year. Cervical cancer strikes nearly half a million women each year worldwide, claiming a quarter of a million lives. Studies show 26% of women aged 14 to 59 will contract HPV.

For More Information: