8 min read

How Artificial Intelligence is Revolutionizing Radiology

Featured Image

The number of life science papers describing artificial intelligence (AI) rose from 596 in 2010 to 12,422 in 2019—increasing more than 2,084 percent in only ten years. According to a paper in the life science publication Nature Partner Journals, “AI shows potential for diagnosing, managing and treating a wide variety of medical conditions.”[1] Nowhere is this potential more apparent than in radiology.

Over the last decade, publications on AI for medical imaging have increased from 100-150 per year to 700-800 per year. Magnetic resonance imaging and computed tomography account for about half of these publications; neuroradiology, roughly a third. However, experts predict that AI will soon revolutionize every type of radiology, with applications for image acquisition, processing, interpretation, reporting, and more.[2] 

Recent events support this speculation. In 2020, the U.S. Food and Drug Administration approved 100 AI-enabled medical devices. In 2021, it published a 350-item list of approved AI medical devices, including 70 percent for medical imaging.[3] 

What is driving this growth?

Radiology’s natural abundance of visual data makes it well-suited to the early application of data-driven technologies like AI. Moreover, AI offers convenient solutions to two of the industry’s top challenges:

#1 - Accuracy & Precision. Reading medical images can be like searching for a need in a haystack. Nodules, lesions, and other health indicators targeted by medical imaging can be small and subtle—sometimes even invisible to the human eye.

AI can help radiologists read medical images by augmenting their human expertise with the accuracy of machine vision and the power of computer processing. A study published in Clinical Radiology found that AI helped radiologists reduce the rate of missed lung cancers in chest X-rays by 60 percent.[4] Another found that AI could help radiologists identify microscopic fractures invisible to the human eye with a 90 percent success rate.[5]

#2 - Workload. Experts estimate a shortage of 9.9 million healthcare professionals by 2030.[6] This labor crisis is already in effect; one study found that the average on-call workload for radiologists more than quadrupled between January 2006 and 2020.[7]

AI can help radiologists do more work in less time, reducing their workload (and subsequent burnout) by automating tasks and, where automation is impossible, streamlining and optimizing tasks for efficiency. A paper in Pediatric Radiology suggests that “computer-aided detection (CAD) can decrease reading time by making the diagnostic process easier” and “[AI-enabled] image enhancement could not only shorten image acquisition time but also ease detection.”[8] A different paper notes: “from an MRI perspective, deep learning algorithms have shown the ability to reduce scan time by improving reconstruction efficiency.”[9]

AI is the future of radiology. Publication, approval, and adoption rates have risen dramatically over the last decade, to the benefit of patients and practitioners. Moreover, experts forecast that this growth will not slow. AI will continue to increase diagnostic accuracy and precision, reduce workload, and otherwise optimize radiologists’ work across specialties. AI in radiology is not just promising; it’s inevitable.


About Synaptiq

Synaptiq is an AI and data science consulting firm with extensive experience in radiology and the broader healthcare industry. Recently, we partnered with Vasolabs Incorporated—a company that specializes in ultrasound diagnostics—to develop an AI solution for the earlier and more efficient detection of cardiovascular disease.

How does it work?

 The operator (presumably a member of a patient’s care team) inputs DICOM* images, and our solution applies machine vision to measure intima-media thickness and detect plaques at four key locations in the carotid arteries. Output is delivered within minutes via digital report directly to the patient’s care team.

Why should you care?

Our goal is to provide a novel early-warning system for cardiovascular disease: the leading cause of death globally, with 17.9 million victims each year.[10] More research is needed, but our solution is  an exciting step forward in the fight against a prolific killer.

We keep our AI on people because AI is how we do it, humanity is why we do it.

[1] https://www.nature.com/articles/s41746-020-00324-0https://www.nature.com/articles/s41746-020-00324-0

[2] https://eurradiolexp.springeropen.com/articles/10.1186/s41747-018-0061-6

[3] https://www.iqvia.com/locations/united-states/blogs/2021/10/fda-publishes-approved-list-of-ai-ml-enabled-medical-devices

[4] https://www.sciencedirect.com/science/article/abs/pii/S0009926021002373#!

[5] https://www.radiologybusiness.com/topics/medical-imaging/radiography/artificial-intelligence-small-bone-fractures-x-rays

[6] https://www.mckinsey.com/industries/healthcare-systems-and-services/our-insights/transforming-healthcare-with-ai

[7] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7683675/

[8] https://link.springer.com/article/10.1007/s00247-021-05114-8

[9] https://pubmed.ncbi.nlm.nih.gov/30399618/

[10] https://www.who.int/health-topics/cardiovascular-diseases

Additional Reading:

The Apple of Your AI

The appeal of artificial intelligence (AI) lies in its ability to generate useful insights from data, which Food &...

AI Can Help Large-Scale Food & Beverage Businesses Improve ESG

An organization’s environmental, social, and governance (ESG) score evaluates its performance on various sustainability...

Artificial Intelligence & Machine Learning: What's the Difference?

Artificial intelligence (AI) and machine learning (ML) aren't synonymous. It’s a common mistake to use these terms...