Artificial Intelligence Drives Medical Imaging to New Territory

Driven by artificial intelligence and machine learning, new solutions are being found for formerly intractable problems in medical imaging, paving the way for technology advances throughout the healthcare industry.

The accelerating ramp-up of computing capabilities and processing of reams of data is driving a transformation in this sector. Healthcare researchers are now able to use the technology utilized in face-recognition to pursue more consequential markers, such as those that indicate the onset of a breast cancer tumor.

The advances in visual data application are particularly relevant for a number of medical fields, most of which currently rely on the human eye and judgment to identify and project the path of a specific disease. The introduction of artificial intelligence combined with machine learning could change all of this.

“Medical imaging is one of the fastest-moving areas of discovery, offering radiologists, pathologists, ophthalmologists, and practitioners in other image-rich disciplines the opportunity to augment their workflows with algorithms that are getting better every day,” says Jennifer BresnickOpens a new window in Xtelligent Healthcare Media.

One of the most compelling reasons for increasing the reliance on artificial intelligence is that, as advances are made in the development of applicable algorithms, AI is expected to become more reliable than human judgment.

“It’s only a matter of time before every X-ray machine is connected to the cloud and one human doctor per hospital puts his hand on your shoulder when he reads you the output from the AI algorithm,” says Nanalyze on its blog about medical imaging start-ups integrating AIOpens a new window into their strategies.

DIY Health Scans

A vast number of companies are looking to solve a range of imaging-related issues. One of the best-funded companies, Butterfly Network, is working to apply machine-learning algorithms in order to help patients conduct ultrasounds using their own iPhones. The company proposes to fit all of the imaging equipment required for ultrasounds, known as the iQ, onto a single silicon chip.

The breakthrough technology works by tethering together thousands of ultrasonic speakers to create a three-dimensional picture of images inside the body, and has already received clearance for both obstetric and cardiac exams.

The result is an ultrasound that can be conducted by a patient, vastly expanding the portability and affordability of the medical technology.

“The sooner we can put smart technologies in the hands of people at home, the sooner the right diagnosis can be made,” says John Martin, the chief medical officer for Butterfly Network. “I’ve yet to find a disease state where earlier detection didn’t lead to better outcomes.”

Another company, Zebra Medical Vision, has developed algorithms that can identify medical issues such as fatty liver and calcified arteries through the machine learning analysis of a CT scan. The company is currently partnering with Nvidia, the artificial intelligence hardware provider that offers a universal computing platform for medical imaging applications.

A California-based start-up, Arterys, is focused on applying deep-learning applications to the diagnosis of heart problems. The company say that its automated imaging analytics can diagnose heart problems in as fast as 15 seconds, up from the 30 or so minutes required using current practices.

“Arterys Inc.’s Cardio DL programOpens a new window applies deep learning, a form of artificial intelligence, to automate tasks that radiologists have been performing manually,” says Nancy Crott in Med City News. “It represents the first FDA-cleared, zero-footprint use of cloud computing and deep learning through AI in a clinical setting.”

Yet for all the breakthroughs that have already begun, one of the biggest hurdles for the application of artificial intelligence will be the confidence of those in the healthcare system that this level of computations can effectively assist – or even replace – human judgment.

“One concern among some healthcare providersOpens a new window and professionals is related to AI’s data collection and accuracy, as we are keenly aware that AI is only as good as the data it collects,” says Jeffrey Hoffmeister, the medical director at iCad. “Since AI is built on deep learning, a technique in which computers learn through example and work to better understand and process complex forms of data, there is no real way to determine its inner workings – so providers have to rely on trust.”