Name one industry, and artificial intelligence is shaking it up. However, some of the biggest changes are taking place in the quietest areas of the market.

One of them is medical imaging. While it may not be as glamorous as autonomous vehicles, AI-powered imaging is doing something even more important: saving lives. Companies like CureMetrix are changing image analysis from a guessing game to a data-driven process.

The typical radiology patient does not see doctors using the technology of Curemetrics. All they know is that their treatment depends on an accurate diagnosis.

What’s going on behind the scenes, and what’s next for the medical imaging industry? To find out, we sat down with CureMetrix CEO Navid Alipore. It turns out that the answer is just as exciting as those self-driving cars. And no, robots aren’t taking over anytime soon.

A revolution in medical imaging
To understand how much AI is changing the world of medical imaging, it’s important to understand what a low-tech process looks like.

“Not long ago, medical imaging was like ‘Where’s Waldo’?” Alipore explains. “Basically, specialists will scan the images and then look for small irregularities that could signal things like cancerous lesions.”

Despite all the training of doctors and radiologists, they make mistakes. Studies suggest that the error rate of human-only analysis can be around 35 percent.

Think about it: without the help of AI, a third of patients undergoing radiology are headed in the wrong direction. And for various reasons, errors in any direction are dangerous.

If something is missed – a false negative – the patient does not receive treatment, and the cancer continues to grow. Many conditions that require imaging are time sensitive. Every day when a cancerous tumor goes unnoticed, it grows larger and increases the risk of metastasis.

On the other hand, a false positive – meaning that the radiologist mistakes a benign feature for a medical issue – can expose patients to unnecessarily invasive procedures. For example, biopsies are painful and expensive. On average, 70-80 percent of them come back negative for breast cancer, while putting emotional strain on the patient, as well as her family.

How does CureMetrix reduce errors, and more importantly, what does this mean for patients?

second pair of eyes
Think of CureMetrix’s cmTriage like another set of eyes. AI can’t replace the person using the tool — the radiologist — but it can help him learn which cases might be suspicious.

Although AI will not replace radiologists, it will not replace those who use AI. Already, radiologists and mammography specialists are in short supply, resulting in overwork, burnout and costly errors – which can eventually lead to lawsuits.

CureMetrix empowers radiologists with data, serving as another arrow in their quiver in the fight against cancer.

Approved by the FDA as a triage tool for breast cancer screening, cmTriage provides a pre-read for radiologists to help identify suspected cases. The result is likely greater sensitivity, as well as fewer patient recalls.

When it comes to detecting breast cancer, radiologists have an average sensitivity of 84.4 percent, with 9.6 percent of cases requiring a second look. At 84.4 percent sensitivity, CureMetrix would have indicated that a total of 6.4 percent of the tests were suspicious. Even in default mode, AI works at higher specificity than radiologist.

Even more powerful is the fact that cmTriage can operate at high sensitivity. Its default setting is 93 percent, but it can be set up to a maximum of 99 percent.

Combining deep learning and computer vision, cmTriage helps radiologists identify suspicious changes, helping people with breast cancer get early treatment. Equally important, it helps radiologists identify cases that are less suspicious or potentially common, reducing the likelihood that patients will be subjected to multiple visits or risky treatments.

breast cancer onset
Currently, CureMetrix is ​​only available for breast cancer detection. But why breast cancer, and what other conditions can it help?

When I asked Alipore, she pointed to two things: scale and the unique challenges of breast cancer — the most complex of all cancers to detect.

About 300,000 Americans are diagnosed with breast cancer each year, with about 30 percent of women diagnosed with cancer.

Secondly, an estimated $4 billion is spent annually on mammography false positives. Biopsy, often the second step in detection, displays an astonishing 75 percent false-positive rate.

“We can’t ignore such numbers,” says Alipore. “There are so many different cancers out there, but few are as expensive — in human or monetary terms — as breast cancer.

Leave a Reply

Your email address will not be published.