AI to Spot ARIA? FDA Says Yes
Quick Links
To keep patients on amyloid immunotherapy safe, doctors need to be able to spot subtle signs of ARIA on MRI scans. For memory clinics that have limited experience with these therapies, this may prove challenging. Now those clinics can consider a new tool to help, i.e. a software package called icobrain aria that uses artificial intelligence to detect and grade this side effect.
In a diagnostic study, radiologists using the software made more accurate calls for ARIA-E and ARIA-H than did radiologists reading scans without this assistance. Based on these findings, the U.S. Food and Drug Administration approved the technology for clinical use November 7.
Steve Salloway at Butler Hospital in Providence, Rhode Island, has consulted for icometrix, the company that developed icobrain aria. He is enthusiastic about the software’s potential, noting that it offers a standardized read of every scan. “It simulates the central reader we had in clinical trials. It doesn’t replace radiologists or the clinical read, but it augments them,” he told Alzforum before its FDA approval. He would like to see it widely adopted.
Other Alzheimer’s clinicians contacted by Alzforum are still unfamiliar with the technology, but interested in it. “Our health system’s neuroradiologists could consider taking it for a test run to get a feel for its utility,” Russell Swerdlow at Kansas University Medical Center, Kansas City, wrote to Alzforum. The approach makes sense to Vijay Ramanan at the Mayo Clinic in Rochester, Minnesota, but he reserved judgment about its application. “It will be interesting to see how this approach functions in real-world practice, where there can be variation in scanner type, sequences, and reader expertise,” he wrote (comments below).
Based in Leuven, Belgium, and in Boston, icometrix’s software measures factors such as the number, location, and size of areas of ARIA-E, and integrates them to produce a numerical severity score. For ARIA-H, it adds up the number of new microhemorrhages and regions of superficial siderosis.
In a clinical study, 16 radiologists read 199 retrospective MRI scans from the aducanumab Phase 2 and 3 trials either with or without the assistance of icobrain aria. The radiologists had an average of 10 years of clinical experience. The software nudged upward their ability to detect ARIA, though it was still not perfect. Sensitivity went from 71 to 87 percent for ARIA-E, and from 69 to 79 percent for ARIA-H. Specificity decreased, i.e., there were more false positives. Even so, overall accuracy went up from 0.82 to 0.87 for ARIA-E, and from 0.79 to 0.83 for ARIA-H (Sima et al., 2024).
“Particularly given that some cases of ARIA can include mild or subtle findings which can have implications for management, progress in this space is a positive,” Ramanan noted.—Madolyn Bowman Rogers
References
Therapeutics Citations
Paper Citations
- Sima DM, Phan TV, Van Eyndhoven S, Vercruyssen S, Magalhães R, Liseune A, Brys A, Frenyo P, Terzopoulos V, Maes C, Guo J, Hughes R, Gabr RE, Huijbers W, Saha-Chaudhuri P, Curiale GG, Becker A, Belachew S, Van Hecke W, Ribbens A, Smeets D. Artificial Intelligence Assistive Software Tool for Automated Detection and Quantification of Amyloid-Related Imaging Abnormalities. JAMA Netw Open. 2024 Feb 5;7(2):e2355800. PubMed.
External Citations
Further Reading
Annotate
To make an annotation you must Login or Register.
Comments
University of Kansas
Using AI to help detect ARIA is an interesting concept, and one might imagine this could represent a logical application of AI technology. As to whether the benefits of augmenting a human read are tangible, I guess that question is hard to answer. This is something maybe our health system’s neuroradiologists could consider taking for a test-run, to get a feel for its utility.
Mayo Clinic - Rochester
Accurate detection and characterization of ARIA is critical for optimizing delivery of anti-amyloid therapies. The technology behind this new tool is intriguing, and the concept of an assistive tool for image interpretation makes sense as one approach toward improved ARIA recognition.
It will be interesting to see how this approach functions in real-world practice, where there can be variation in scanner type, sequences, and reader expertise. It will also be important that this and similar tools remain adjuncts for MRI interpretation rather than substitutes.
However, particularly given that some cases of ARIA can include mild or subtle findings which can have implications for management, progress in this space is a positive.
Barrow Neurological Institute
AI-driven quantitative measures have been steadily making their way into radiological screening and decision-making. The ability to objectively quantify ARIA E and ARIA H will help physicians in managing mABs more precisely.
Columbia University Irving Medical Center
The recent approval of Icobrain ARIA represents an important step in better understanding some of the primary concerns associated with the new generation of anti-amyloid Alzheimer’s therapy. With greater adoption and approval of these therapies comes an opportunity to better understand the risk of swelling and bleeds on the corresponding neuroimaging that is required to be serially acquired.
Although moderate-to-severe ARIA is more obvious, mild ARIA may reflect important underlying processes and is more difficult to detect. Advanced neuroimaging methods, including those with AI that are rigorously tested and validated, benefit patients already familiar with, and under surveillance for, the issues surrounding these treatments. And clinicians can have a detailed, quantitative, viewer-independent assessment to support their diagnosis, as well as more accurate information on quantity and extent. So much is still unknown about AAT-induced ARIA, and software like this can help provide more insight.
Banner Alzheimer's Institute
This technology affords another way to help manage patients receiving anti-amyloid antibody therapy. It seems to me that this could be an effective tool to support clinical decision-making.
I suspect that a challenge, at least in the U.S., will be defining and continually refining the workflow in different complex care systems to optimize the utility of this and other aids (e.g. other imaging tools and biomarkers, fluid biomarkers, manual and/or digital cognitive assessments, risk disclosure methods) as well as paying for this and all the other optional tools and techniques. Put differently, different health care systems and practices are confronting the cognitive impairment/dementia tsunami in very different ways, and this variability may in turn affect uptake of this particular new tool.
Massachusetts General Hospital
Massachusetts General Hospital
Massachusetts General Hospital
This FDA authorization for an AI-driven MRI solution is an exciting step forward in assisting the detection of ARIA and supporting the safe administration of anti-amyloid therapies for Alzheimer's disease. However, it's important to note that the ARIA detection tool in question was primarily trained on GRE images, not SWI. While GRE is the current standard in guidelines, SWI is generally more sensitive, which may have implications for both patient selection and monitoring—particularly among patients who are APOE4 homozygotes, who face a higher risk of ARIA-H and ARIA-E.
At our institution, we routinely acquire both GRE and SWI sequences, allowing us to directly assess their performance head-to-head. We've observed that SWI detects ARIA-H earlier than GRE in some patients. Additionally, areas of superficial siderosis or microhemorrhages that might not have been prospectively visible on GRE often become evident with SWI, subsequently aiding retrospective GRE interpretation.
While current guidelines and this AI tool are optimized for GRE, the enhanced sensitivity of SWI presents an opportunity—and a challenge. Incorporating SWI into clinical workflows and treatment decisions will require the development of new cutoff thresholds and treatment guidelines. We are actively collecting data to better understand SWI's role in improving safety monitoring and efficacy measurement of anti-amyloid therapies.
icometrix
AI for detection, quantification, and grading of ARIA remains a supportive tool for radiologists. However, the designation as a computer-aided detection and diagnosis software reflects it can be used for localizing and characterizing diseases, disease types, severity, stage, and progression, as opposed to most AI softwares that can just highlight imaging findings.
CADe/CADx AI might help reduce the gap between academic centers and community hospitals, which is important for disease like Alzheimer's.
Disclosure: I am CTO of icometrix, the company that developed icobrain aria, their lead contact with the FDA, and senior author of Sima et al., 2024.
References:
Sima DM, Phan TV, Van Eyndhoven S, Vercruyssen S, Magalhães R, Liseune A, Brys A, Frenyo P, Terzopoulos V, Maes C, Guo J, Hughes R, Gabr RE, Huijbers W, Saha-Chaudhuri P, Curiale GG, Becker A, Belachew S, Van Hecke W, Ribbens A, Smeets D. Artificial Intelligence Assistive Software Tool for Automated Detection and Quantification of Amyloid-Related Imaging Abnormalities. JAMA Netw Open. 2024 Feb 5;7(2):e2355800. PubMed.
Stanford University
Chasing down a monster of our own creation. It's remarkable how much person-power and money is being consumed in administering these therapies of dubious efficacy and demonstrated dangers.
Make a Comment
To make a comment you must login or register.