A novel method for characterizing prostate cancer that uses computer vision and artificial intelligence to help determine the best course of treatment for each patient is being rolled out this summer by the Lillian and Henry M. Stratton-Hans Popper Department of Pathology at the Icahn School of Medicine at Mount Sinai.
The platform, called Precise Medical Diagnosis™ or Precise MD, has been under development at Mount Sinai for more than three years by a team of physicians, scientists, mathematicians, engineers, and programmers. The proprietary diagnostic system creates detailed, specific data about the patient’s cancer cells using multispectral fluorescent imaging to evaluate biomarker status and architectural patterns and then uses sophisticated computer analytics to combine and create predictive models.
“Our goal is to improve the way we stratify patients into treatment groups,” says Gerardo Fernandez, MD, Associate Professor of Pathology, and Genetics and Genomic 
Sciences at the Icahn School of Medicine at Mount Sinai and Director of Precise MD. “By refining the treatment, we can save patients from unnecessary treatments and help improve the entire health care system.”
By combining multiple data sources, the new platform provides a view of cancer that is far more comprehensive than can be seen using conventional microscopes. Ultimately, this multilayered approach to analyzing and characterizing an individual’s prostate cancer may be used by pathologists as a more sophisticated alternative to a traditional grading system such as the Gleason score, which has been used since the 1960s to guide a patient’s treatment options and establish his prognosis.
“Cancer diagnoses are based on pattern recognition. But pattern recognition is imprecise,” says Carlos Cordon-Cardo, MD, PhD, the Irene Heinz Given and John LaPorte Given Professor and Chair of the Department of Pathology at the Mount Sinai Health System. “We have created a Systems Pathology approach that integrates the patient’s electronic health records, phenotype, and genotype, and overcomes the limitations of earlier technologies. This is truly the next generation in personalized medicine.”
Mount Sinai’s Department of Pathology processes more than 80 million tests a year, making it the largest department of its kind in the country. In its initial phase this summer, Precise MD will offer a test used to analyze patients who have had prostatectomies at the Milton and Carroll Petrie Department of Urology at the Icahn School of Medicine to help determine which of them will likely have a recurrence of cancer and may need additional therapy, such as chemotherapy.
A second, higher-impact test will follow in 2017, which will be used to characterize prostate cancer in newly diagnosed patients. At that time, Dr. Cordon-Cardo says all prostate cancer patients at Mount Sinai will have the option to receive this test.
In addition to the current efforts in prostate cancer, Precise MD is applying its computer vision and machine learning tools to better characterize breast cancer.
The new platform could eventually be used to characterize many disease states, including melanoma, lung, and colon cancers, and chronic conditions such as inflammatory bowel disease.
As part of the development efforts in breast cancer, Dr. Fernandez’s team is gathering between one and two petabytes of data for its archive and is employing the latest technologies in deep learning and neural networks to analyze data that is not visible to the human eye. “We expect to find features that we don’t even know exist at this point,” says Dr. Fernandez.