Name an industry, and AI is shaking it up. a number of the most important changes, however, are happening within the quietest areas of the market.
One of those is medical imaging. Although it’s going to not be as glamorous as autonomous vehicles, AI-driven imaging is doing something even more important: saving lives. Companies like CureMetrix are turning image analysis from a game into a data-driven process.
The typical radiology patient doesn’t see doctors using CureMetrix’s technology. All they know is that their treatment depends on an accurate diagnosis.
What’s happening behind the scenes, and what’s next for the medical imaging industry? to seek out out, we sat down with CureMetrix CEO Navid Alipour. It seems the solution is equally as exciting as those self-driving cars. And no, the robots aren’t taking up any time soon.
A Revolution in Medical Imaging
To grasp just what proportion AI is changing the planet of medical imaging, it’s important to know what the low-tech process seems like.
“Not that way back, medical imaging was tons like ‘Where’s Waldo?’” Alipour explains. “Basically, experts would scan images then look for tiny irregularities that would signal things like cancerous lesions.”
Despite all the training doctors and radiologists undergo, they create mistakes. Studies suggest error rates of human-only analysis could also be around 35 percent.
Think about that: Without the assistance of AI, a 3rd of patients who undergo radiology are steered in the wrong direction. And for various reasons, errors in either direction are dangerous.
If something is missed — a false negative — the patient doesn’t receive treatment, and therefore cancer continues to grow. Many conditions that need imaging are time-sensitive. a day that a cancerous tumor goes unnoticed, it grows larger, and therefore the risk of metastasis increases.
On the opposite hand, a false positive — meaning the radiologist mistakes a benign feature for a medical issue — can expose patients to invasive procedures unnecessarily. Biopsies, for instance, are painful and dear . on average, 70-80 percent of them come negative within the look for carcinoma while placing emotional stress on the patient, also as her family.
How does CureMetrix minimize errors, and more importantly, what does that mean for patients?
The Second Pair of Eyes
Think of CureMetrix’s carriage sort of the second set of eyes. The AI can’t supplant the person using the tool — the radiologist — but it can help him or she know which cases could also be suspicious.
Although AI won’t replace radiologists, those using AI will replace those who aren’t. Already, radiologists and mammography experts briefly supply, leading to overwork, burnout, and dear errors — which may ultimately cause lawsuits. CureMetrix empowers radiologists with data, serving as another arrow within their quiver in the fight against cancer.
Cleared by the FDA as a triage tool for carcinoma screening, carriage provides a pre-read for the radiologist, helping to spot suspicious cases. The result’s the potential for greater sensitivity, also as fewer patient recalls.
When it involves detecting carcinoma, the typical sensitivity of a radiologist is 84.4 percent, with 9.6 percent of cases requiring a re-evaluation. At 84.4 percent sensitivity, CureMetrix would have indicated that a complete of 6.4 percent of the exams are suspicious. Even in default mode, the AI operates at higher specificity than radiologists.
Even more powerful is that the incontrovertible fact that carriage can operate at higher sensitivities. It is default setting is 93 percent, but it is often set as high as 99 percent.
By combining deep learning and computer vision, carriage helps radiologists identify suspicious changes, enabling those with carcinoma to urge treatment sooner. even as importantly, it helps radiologists identify cases that are less suspicious or potentially normal, decreasing the prospect that patients are going to be subjected to multiple visits or risky treatments.
Beginning with carcinoma
Currently, CureMetrix is out there just for carcinoma detection. But why carcinoma, and what other conditions might it help with?
When I asked Alipour, he pointed to 2 things: scale and therefore the unique challenges of carcinoma — the foremost complex of all cancers to detect.
Close to 300,000 Americans are diagnosed annually with carcinoma, comprising almost 30 percent of all cancer diagnoses in women. Secondly, an estimated $4 billion is spent annually on mammography false positives. Biopsies, often the second step in detection, exhibit a shocking 75 percent false-positive rate.
“We just couldn’t ignore numbers like that,” Alipour says. “There are tons of various cancers out there, but few are as costly — in human or in monetary terms — as carcinoma .”
Fortunately for other cancer patients, mammography is merely the beginning of AI’s medical imaging makeover. CureMetrix plans to expand its AI into other areas of medical imaging.
A One-Size-Fits-All Detection Tool?
Imaging may be a critical tool in cancer detection, but it’s not the sole one. Other methods, like methylation analysis, also can be augmented by deep learning tools.
“One advantage of deep learning,” Alipour notes, “is that it can affect unstructured data. If fed the proper training data, such an algorithm could spot cancer in other ways, like watching chemical signatures.”
As an example, Alipour mentions a recent case at any University Langone Health. A lass was diagnosed with supported tissue pathology with recurrent medulloblastoma, one sort of brain cancer. With the assistance of AI, however, her doctors discovered it had been actually another variety: glioblastoma.
Underscoring the importance of correct diagnosis is that the girl’s cancer may are the result of radiation wont to fight primary cancer. Had she been treated again within the same way, the treatment could have harmed her without actually destroying new cancer.
Despite diagnostic breakthroughs in carcinoma, Alipour makes it clear that a universal cancer detection tool remains years away. How we get there, however, is strictly what CureMetrix is doing: starting with the foremost complex cancer, and building from there.