• AI is at the forefront of radiology, but clinicians are still adapting to its use.
  • Advances in technology may one day help predict the response to the disease.
  • Proper training can prepare future physicians for this rapidly changing field.
  • This article is part of the “Health Innovation” series, highlighting what healthcare professionals need to do to cope with this technological moment.

Developments in artificial intelligence open up new perspectives in radiology. Advances are helping physicians make more accurate diagnoses and predict patient outcomes.

“These are really exciting times for medicine,” said Dr. Yvonne W. Lui, associate professor of radiology and associate chair for artificial intelligence at the NYU Grossman School of Medicine. “We are seeing the implementation of AI or machine learning tools in all disciplines, and diagnostic imaging has always been at the forefront of these technological advances. “

In a Membership survey 2020, the American College of Radiology (ACR) found that 30% of radiologists use AI in clinical practice to improve the interpretation of images of intracranial bleeding, blocked arteries in the lungs, and breast abnormalities. The 20% of practices not using AI indicated that they plan to integrate the technology into the clinic in the next few years. RTAs Institute of Data Science also publishes a shopping list FDA approved AI radiology technologies.

Radiology is still adapting to the clinic’s AI tools, Lui said. “There is no roadmap at the moment. I think people are trying to figure out what is the best way to go and how to use certain tools.”

Patient diagnostics could be the start of AI’s potential in radiology, says Dr. Anant Madabhushi, director of the Center for Computational Imaging and Personalized Diagnostics at Cleveland’s Case School of Engineering. “The opportunities around treatment management, monitoring and response prediction will potentially be even greater than the diagnostic implications,” he said. Training the next generation of radiologists in AI is important to ensure that the technology is applied correctly in the clinic, he added.

Diagnose patients beyond illness

Much of the buzz around AI in radiology has focused on classification tools. For example, clinicians use AI to determine whether a result in an image is normal or abnormal, such as whether there is a pneumothorax – or an air leak between the lungs and the chest wall – or no pneumothorax. .

This technology can help clinicians analyze millions of tiny pieces of information. Researchers are developing an AI that can speed up and make the task of interpreting an image more precise. Quantifying and identifying tumor volume, new lesions, and tissue changes over time can be particularly helpful, she said.

Scientists are also trying to determine how AI can evaluate images in new ways. “We ask if the images contain information that we have not been sensitive to before,” said Lui. His own research is evaluating whether AI can help detect a signal on images of concussion patients to help identify injuries and monitor recovery.

AI could perhaps help predict the cellular response to cancer treatment and treatment monitoring, which could help avoid the need for invasive biopsies, Madabhushi said. “There are several different scenarios where the imaging features are so subtle that it really becomes impossible to distinguish between a confounder of treatment and a disease,” he said.

For example, benign radiation necrosis, which is a lesion that forms at the tumor site as a result of radiation therapy or chemoradiation, can be difficult to distinguish from tumor recurrence. AI can be an important supporting tool for radiologists to make this distinction and avoid the need for an invasive biopsy, Madabhushi said.

In her own research, Madabhushi is studying how AI in radiology can non-invasively identify prostate cancer and stratify its aggressiveness based on risk on an MRI to help guide treatment decisions. “What we’re trying to do is actually create a virtual biopsy,” he said.

AI in radiology training

The Radiological Society of North America offers continuing medical education in artificial intelligence and imaging, webinars, and an AI certificate program. The American Academy of Radiology Institute for Data Science (DSI ACR) also offers lectures on the use of AI in clinical practice, evaluation of AI algorithms and a variety of online use cases.

NYU Grossman School of Medicine offers a formal biomedical imaging AI program for radiology residents. Courses in machine learning in radiology are also available for medical students and fellows, while research opportunities in radiology are open to doctoral students.

Madabhushi encourages medical students interested in AI in radiology to seek opportunities within their institutions to work with biomedical engineers and computer scientists specializing in bioinformatics.

“You want the students to have an idea of ​​what it takes to train AI algorithms in radiology, how to interact with AI and understand its limitations,” he said. “This collaboration shatters some of the misconceptions about what AI can and cannot do.”

Source link