Proscia and the University of California San Francisco (UCSF) are partnering to use artificial intelligence (AI) to improve the accuracy and speed of cancer diagnoses, starting with prostate cancer.

The collaboration will seek to validate the use of computational applications for pathology subspecialties such as prostate cancer, the second-leading cause of cancer deaths among U.S. males, with 191,930 new cases expected this year, according to the American Cancer Society.

For more than a century, cancer diagnoses have relied on the microscopic study of tissue biopsies. A steady decrease in the number of pathologists has made the manual practice unable to keep up with the rising number of cancer cases, AI software company Proscia said in a press release.

In prostate cancer, the excessive number of slides examined per case, complicated reporting requirements, and qualitative grading system frequently result in delayed diagnoses, additional tests, and less confidence in treatment plans.

Using digital pathology for primary diagnoses can spur quality and efficiency improvements in the process, Proscia said.

The company will use volumes of diverse, digitized data collected by UCSF, an early adopter of digital pathology. Such use will ensure that Proscia’s computational pathology app for prostate cancer accurately accounts for the variability across a gamut of diagnoses, biopsy methods, and tissue preparation, and tissue-staining and digital-scanning processes.

“As prostate cancer impacts millions of patients each year, it is critical that we improve productivity and confidence in this high-impact specialty,” said Mike Bonham, MD, PhD, Proscia’s chief medical officer. “Through our partnership with UCSF, an institution that achieves the highest standards in patient care, research and education, we are gaining the data and experience required to ensure that our AI delivers meaningful benefits in practice, where so many other solutions have struggled to perform.”

After its work in prostate cancer, the collaboration will shift its focus to other subspecialties. As digital pathology continues to grow in practice, deep-learning powered applications are expected to uncover diagnostic data that may lead to new treatments and improved patient outcomes.

“UCSF prides itself as being an institution in the intersection of research and clinical practice of medicine, continuously working to translate new findings into more effective prevention, diagnosis and treatment,” said Zoltan Laszik, MD, PhD, a UCSF pathology professor. “Proscia’s focus on delivering practical AI solutions strongly aligns with our efforts, and we are pleased to work together to improve the routine pathology workflow.”