Is AI-enabled radiomics the next frontier in oncology?
Many professionals in healthcare information technology might not yet be familiar with radiomics, but the emerging technology could potentially have a big impact on the future of cancer care.
Radiomics might be most easily explained as "imaging analytics." The technology uses AI and machine learning to extract high-dimensional data from standard medical images such as CT, MRI and PET scans to provide more than 1,500 data points that deliver new insights about the tumors or lesions in those images that cannot be obtained via traditional approaches.
Healthcare IT News asked Rose Higgins, CEO of radiomics pioneer HealthMyne, for a primer on radiomics, and to discuss its place in the realm of health IT.
Q: Please explain what radiomics is, and how it works.
A: Radiomics is a cutting-edge approach that extracts a wealth of invaluable, high-dimensional data from standard medical imaging. When you hear "radiomics," think "advanced imaging analytics." The problem radiomics solves is that [the] traditional methods radiologists have used to analyze medical images are limited to just two dimensions – the long and short axes.
As a result, the primary method of evaluating a lesion's progress has been simply measuring the vertical and horizontal axes to ascertain any changes, which leaves a great deal of important information out of the equation.
In contrast, radiomics uses AI-driven analytics to extract meaningful data from traditional imaging modalities such as CT, MRI or PET scans. It then curates, annotates and analyzes that quantitative data to deliver a wealth of information that cannot be observed visually in an image.
With radiomics, providers gain accurate readings of a lesion's depth, volume, density, doubling size, textures and many other quantitative features, all the while comparing those measurements to an AI-enabled model based on thousands of images.
The result is that providers not only gain a view of lesion progression that formerly could only be achieved through invasive surgeries such as biopsies; they also receive information about lesion changes that have never been available by any means.
Q: How can providers use radiomics to personalize treatment plans for individual cancer patients?
A: Radiomics uses tumor biology to define a novel set of quantifiable patterns, known as imaging biomarkers. These markers – which provide clinical signatures as unique as each cancer patient – act as a catalyst to develop individualized treatment plans, evaluate disease progression, monitor therapy response and predict clinical outcomes.
"By basing a patient's treatment plan on approaches that worked for other patients who exhibited similar genetic and phenotypic characteristics, clinicians can develop personalized treatment plans with far more precision and accuracy."
Rose Higgins, HealthMyne
By leveraging this rich set of previously undiscoverable data, providers can personalize treatment across the patient's entire care journey from early identification to treatment and recovery.
Q: How can providers use radiomics to combine patients' phenotypic information with their genetic data to obtain insights into treatments outcomes for patients with similar profiles?
A: When a lesion is discovered, providers can use the patient's genetic information along with phenotype data from radiomics to match the patient to others with similar profiles. They can then review the outcomes those previous patients achieved with various treatment plans to determine which yielded the best results on a consistent basis.
This then becomes the starting point for treatment. By basing a patient's treatment plan on approaches that worked for other patients who exhibited similar genetic and phenotypic characteristics, clinicians can develop personalized treatment plans with far more precision and accuracy.
When combined, radiomics, genomic data and clinical data provide a holistic and powerful tool kit for tackling complex diseases like cancer.
Q: How can providers use radiomics to quickly adjust treatment plans midstream while monitoring thousands of data points quantifying patient responses?
A: An added advantage of radiomics is that providers can continue to monitor the effect a treatment is having across thousands of data points. If the treatment is not achieving the intended results at certain checkpoints, providers can change the treatment plan immediately rather than waiting until it is completed.
They can then continue this same process of monitoring and adjusting to ensure they deliver the best possible results for each patient based on their individual response to the treatment plan.
The Diverse Roles of AI & ML
Machine learning applications are proliferating and improving, and this month we'll explore the many ways they're being put to work.