AI for Brain MRI

What if you could speed up brain MRI exams by performing fast scans for most patients, and reserving complex sequences for the patients who need them? A hint of that future comes from a new study in which AI showed progress in helping radiologists interpret scans with fewer sequences.

MRI can visualize minute structures in the body, especially in the brain, but it’s one of the trickiest imaging modalities to operate.

  • There’s an alphabet soup of MRI pulse sequences, and the modality’s complexity is multiplied when contrast has to be used. 

Breast MRI experts have been experimenting with abbreviated scanning protocols that speed up image acquisition and interpretation by using fewer and less complex sequences.

  • Researchers applied that concept to MRI brain imaging in a new European Journal of Radiology paper in which they tested Cerebriu’s Apollo AI algorithm with 414 patients from four hospitals in Denmark.

Apollo processes three brain MRI sequences (DWI, SWI or T2* GRE, and T2-FLAIR) and can detect critical findings like brain infarcts and intracranial hemorrhages and tumors while the patient is still on the table.

  • If an abnormality is detected, Apollo prompts technologists to acquire a fourth sequence, such as T1-weighted imaging.

That sounds great, but how well does Apollo work in the real world? 

  • Researchers compared the algorithm’s performance to that of expert neuroradiologists in multiple workflows, such as reading three- and four-sequence MRI scans with and without AI assistance. 

Compared to neuroradiologists using the four-sequence MRI protocol without AI assistance, they found…

  • Apollo’s sensitivity was better than neuroradiologists for brain infarcts (94% vs. 89%) and intracranial tumors (74% vs. 71%) but slightly lower for intracranial hemorrhages (82% vs. 83%).
  • AI’s specificity was somewhat lower, however, for brain infarcts (86% vs. 99%), intracranial hemorrhages (84% vs. 99%), and intracranial tumors (62% vs. 97%). 
  • When neuroradiologists had AI findings in addition to the four-sequence protocol, tumor detection sensitivity improved slightly, but specificity fell. 

While Apollo’s sensitivity was a benefit, the researchers said its low specificity “presents a challenge” and could result in unnecessary additional sequences or contrast administration. 

  • Specificity could be affected by age-related changes in older patients, as well as differences in MRI scanner models used.

The Takeaway

The new findings show that AI-aided MRI scan assistance still needs refinement. But it’s still early days for Cerebriu and Apollo (which has the CE Mark but not FDA clearance), so watch this space for more updates. 

MRI of Bullet Fragments Is Possible

Radiology has a renewed focus on MRI safety following the tragic death of a New York man in an MRI accident last month. With that in mind, a new JACR study looks at adverse MRI events caused by an uncommon but still important phenomenon: retained bullet fragments in patients getting scans. 

MRI is radiology’s most powerful modality, but its strong magnetic fields can be hazardous – and on extremely rare occasions even fatal – for both patients and medical personnel.

  • Patients are supposed to be screened for metallic implants, jewelry, and other contraindications, but how often do providers know to ask about retained bullet fragments?

Having a retained bullet fragment on its own isn’t a contraindication for MRI, but providers do need to know where fragments are located and how large they are.

  • If pre-scan screening discovers a patient with a retained fragment, they typically receive X-rays of the involved area to determine location and size – scans should be aborted if the fragment is in a solid organ or within 5 mm of an important artery or vein.

If all these steps are taken and the scan goes ahead, how often do adverse MRI events occur? 

  • MGH researchers reviewed 6.1k X-ray reports that contained the terms “bullet” or “shrapnel” over 13 years, finding 284 patients who got an MRI scan after a retained fragment was found on radiography.

They found…

  • Only four patients (1.8%) experienced symptoms during MRI scans.
  • Each of the exams was terminated early due to patient discomfort, with three patients reporting burning and one general discomfort.
  • None of the symptomatic exams had the bullet in the MRI field of view.
  • No serious injury and no follow-up care was required. 

The Takeaway

The new findings are encouraging by showing that with careful patient screening and monitoring, MRI scans can be performed on patients with retained bullet fragments. But as always, MRI operators must remain vigilant and adhere to published MRI safety guidelines.

Unpacking Heartflow IPO’s Lessons for AI Firms

Cardiac AI specialist Heartflow went public last week, and the IPO was a watershed moment for the imaging AI segment. The question is whether Heartflow is blazing a path to be followed by other AI developers or if the company is a shooting star that’s more likely to be admired from afar than emulated.

First the details: Heartflow went public August 8, raising $317M by issuing 16.7M shares at $19 each – and finishing up 50% for the day. 

  • The IPO beat analyst expectations, which originally estimated gross proceeds of $215M, and put the company’s market capitalization at $2.5B – well within the mid-cap stock category. 

So what’s so special about this IPO? Heartflow’s flagship product is FFRCT Analysis, which uses AI-based software to calculate fractional flow reserve – a measure of heart health – from coronary CT angiography scans. 

  • This eliminates the need for an invasive pressure-wire catheter to be threaded into the heart.

Heartflow got an early start in the FFR-CT segment by nabbing FDA clearance for Heartflow FFRCT Analysis in 2014, and since then has been the single most successful AI company in winning reimbursement from both CMS and private payors.

  • In fact, a 2023 analysis of AI reimbursement found that FFRCT Analysis was the top AI product by number of submitted CPT claims, at 67.3k claims – over 4X more than the next product on the list.

That’s created a revenue stream for Heartflow that clearly bucks the myth that clinicians aren’t getting paid for AI.

  • And in an IPO filing with the SEC, Heartflow revealed how reimbursement is driving revenue growth, which was up 44% in 2024 over 2023 ($125.8M vs. $87.2M, respectively). 

But it’s not all sunshine and rainbows at the Mountain View, California company, which posted significant net losses for both 2024 and 2023 ($96.4M and $95.7M).

  • As a public company, Heartflow may have a shorter leash in getting to profitability had it remained privately held.

But the bigger picture is what Heartflow’s IPO means for the imaging AI segment as a whole. 

  • It’s easily the biggest IPO by a pure-play imaging IT vendor in years, and dispels the conventional wisdom that investors are shying away from the sector.

The Takeaway

Heartflow’s IPO shows that in spite of clinical AI’s shortcomings (slow adoption, sluggish reimbursement, etc.), it’s still generating significant investor interest. The company’s focus on achieving both clinical and financial milestones (i.e. reimbursement) should be an example for other AI developers.

AI Predicts Radiology Workload

AI is touted as a tool that can help radiologists lighten their workload. But what if you could use AI to predict when you’ll need help the most? Researchers in Academic Radiology tried that with an AI algorithm that predicted radiology workload based on three key factors. 

Imaging practices are facing pressure from a variety of forces that include rising imaging volume and workforce shortages, with one recent study documenting a sharp workload increase over the past 10 years.

  • Many industry observers believe AI can assist radiologists in reaching faster diagnoses, or by removing studies most likely to be normal from the worklist based on AI analysis. 

But researchers and vendors are also developing AI algorithms for operational use – arguably where radiology practices need the most help.

  • AI can predict equipment utilization, or even create a virtual twin of a radiology facility where administrators can adjust various factors like staffing to visualize their impact on operations.

In the new study, researchers from Mass General Brigham Hospital developed six machine learning algorithms based on a year of imaging exam volumes from two academic medical centers.

The group entered 707 features into the models, but ultimately settled on three main operational factors that best predicted the next weekday’s imaging workload, in particular for outpatient exams…

  • The current number of unread exams.
  • The number of exams scheduled to be performed after 5 p.m.
  • The number of exams scheduled to be performed the next day.

The algorithm’s predictions were put into clinical use with a Tableau dashboard that pulled data from 5 p.m. to 7 a.m. the following day, computed workload predictions, and output its forecast in an online interface they called “BusyBot.”

  • But if you’re only analyzing three factors, do you really need AI to predict the next day’s workload? 

The authors answered this question by comparing the best-performing AI model to estimates made by radiologists from just looking at EHR data. 

  • Humans either underestimated or overestimated the next day’s volume compared to actual numbers, leading the authors to conclude that AI did a better job of calculating dynamics and weighting variables to produce accurate estimates.

The Takeaway

Using AI to predict the next day’s radiology workload is an intriguing twist on the argument that AI can help make radiologists more efficient. Better yet, this use case helps imagers without requiring them to change the way they work. What’s not to like?

AI for Bone Density Screening with X-Ray

Screening women for osteoporosis using AI analysis of chest X-rays acquired for other clinical indications meets U.S. thresholds for cost-effectiveness. That’s according to a new study in JACR that highlights the potential of radiography AI for opportunistic screening.

Osteoporosis screening is already performed using DEXA scanners that detect bone density loss in women.

  • But DEXA scanners aren’t always available, and dedicated screening for just one condition can be expensive. 

Using AI to analyze chest X-rays that women might be getting for other conditions could expand the pool of women being screened for osteoporosis without incurring significant additional costs.

  • Indeed, Japanese researchers recently published a study honing in on the best techniques for AI-enhanced osteoporosis screening with radiography.

In the new study, researchers performed a modeling analysis that simulated the cost-effectiveness of an osteoporosis screening program based on AI-enhanced chest radiographs for U.S. women aged 50 and up. 

  • The cost analysis compared osteoporosis screening plus treatment versus treatment alone, incorporating standard fracture treatment and imaging costs ($66 for DEXA scans, $20 for chest X-rays).

In a sample of 1k women, AI-enhanced X-ray osteoporosis screening…

  • Had an ICER of $72.1k per QALY, below the U.S. cost-effectiveness thresholds of $100k to $150k per QALY.
  • Would produce healthcare savings of $99k, offset by treatment costs of $208k.
  • Would prevent 2.8 fractures and increase QALYs by 1.5.
  • Would remain cost-effective as long as AI’s cost did not exceed $62 per patient.

Adjusting the model’s parameters produced even better performance for AI-based screening. 

  • If medication adherence improved by 50%, the ICER was reduced to $28.6k.

The Takeaway

The new research offers more support for opportunistic osteoporosis screening, this time perhaps from the most important angle of all: cost-effectiveness. If confirmed with other studies, AI-based bone density analysis could make routine chest X-rays even more valuable.

Radiologist Pay Jumps Nearly 8% in New Survey

Radiologist pay jumped nearly 8% in 2024 in the latest salary survey from Doximity. That’s the good news. The bad news is that radiology actually slipped a couple notches compared to other highly paid medical specialties.

In its latest survey, Doximity found that radiologists had an average annual salary of $572k in 2024. 

  • That’s up 7.5% compared to $532k in last year’s edition of the survey, giving radiologists the fourth-largest salary increase among medical specialties. 

Radiology’s salary growth accelerated in 2024 compared to 2023, when radiology pay grew 5.6%. 

  • And the growth rate is up sharply compared to 2022, when rad salaries grew only 1.6% in a year when many doctors saw salary declines.

Diagnostic radiology occupied the 11th spot on Doximity’s list of highest-compensated specialties in 2024, slipping a couple positions compared to the 9th spot in last year’s survey. 

  • Moving ahead of radiology were pediatric (general) surgery and interventional radiology, two new physician categories added with this year’s survey.

Overall, the Doximity report found that physician compensation growth slowed last year compared to 2023 (3.7% vs. 5.9%), and the report also noted several other broad healthcare trends…

  • The gender gap for doctor compensation worsened in 2024, with men now making 26% more than women compared to 23% more in 2023.
  • Medicare and Medicaid reimbursement cuts are weighing heavily on physicians, with nearly one-third of doctors saying they have already (17%) or plan to in the future (13%) reduce how many of these patients they see. 
  • And the vast majority agreed (33%) or strongly agreed (48%) that current reimbursement policy is contributing to the decline of private-practice medicine. 
  • Burnout levels appear to be easing from the peak a few years ago, with fewer doctors saying they feel overworked (62% vs. 67%) and fewer saying they are thinking about leaving clinical practice (39% vs. 50%).

The Takeaway

Industry observers can complain about how AI and private equity are ruining radiology (see our title quote above), but the fact is that radiologists are still enjoying salary levels and compensation growth rates near the top of medicine. It’s not a bad price to pay.

Obesity Drives CT Radiation Dose Higher

The proportion of patients getting CT scans with high radiation doses more than tripled over a five-year period. That’s according to a new study in British Journal of Radiology that found the rate of high-dose CT rising along with growing obesity rates – despite technical advances in CT instrumentation.

CT radiation dose has been closely watched due to its potential to cause cancer.

  • A controversial paper published earlier this year in JAMA Internal Medicine estimated that all the CT scans performed in a year in the U.S. would cause 100k cancers.
  • And another recent paper made a connection between the number of CT scanners installed in a country and the number of patients with high cumulative radiation exposure (over 100 mSv) over five years.

In the new paper, a research team led by radiation safety expert Madan Rehani, PhD, tracked radiation exposure to patients who got CT exams at Massachusetts General Hospital from 2013 to 2022. 

  • They defined high-dose CT exams as those in which individual exam radiation dose exceeded 50 mSv. 

Over a 10-year period, nearly 1.4 million CT exams were performed on 382k patients, revealing that the rate of CT exams with effective doses ≥ 50 mSv…

  • Was less than 1%, but more than tripled from 2017 to 2022 (0.25% to 0.86%).
  • 59% of high-dose exams were multiphase studies (≥ 3 phases).
  • The rate of high-dose CT exams rose 7X faster in overweight and obese patients than in their underweight or normal-weight counterparts in a subset of 5k patients with available BMI data.

There was a close association between obesity and radiation dose, as patients with larger body habitus require more radiation to penetrate deeper for diagnostic-quality images. 

  • Ironically, the introduction of CT scanners with higher table weight capacity and larger gantry diameter may have contributed to the increase by making it possible to scan patients who previously were too large to be imaged.

Researchers also believe the rise in radiation dose starting in 2018 occurred around the same time as MGH’s introduction of more advanced CT scanners with more powerful X-ray tubes.

The Takeaway

The new findings on CT radiation dose illustrate the balancing act that imaging providers face between radiation safety and achieving optimal image quality. With obesity rates steadily rising, it’s a choice that will become increasingly common. 

MRI Reveals Junk Food’s Toll on Carotid Arteries

As the U.S. government weighs a regulatory crackdown on ultra-processed food, a new study indicates the feds may be on to something. Researchers used MRI to discover that people who consumed more ultra-processed food had higher levels of carotid arterial plaque – a risk factor for cardiovascular disease. 

The FDA and the USDA on July 23 announced the start of a new initiative to investigate the risks of ultra-processed foods and their relationship to chronic diseases such as obesity, heart disease, and cancer. 

  • The project is widely seen as a priority of HHS Secretary Robert F. Kennedy, Jr. and his Make America Healthy Again movement. 

Meanwhile, arterial plaque buildup is a sign of atherosclerosis and has been linked to multiple clinical conditions, from stroke to intraplaque hemorrhage

In the new paper in American Journal of Preventive Cardiology, researchers noted the established association between adverse cardiovascular events and consumption of ultra-processed food and beverages, but the association with subclinical disease hasn’t been explored. 

  • So researchers reviewed carotid MRI scans of 768 participants from the Atherosclerosis Risk in Communities study, in which subjects also described their dietary intake with a 148-item questionnaire. 

MRI scans were correlated with dietary habits, finding that compared to the lowest quartile, people in the highest quartile of ultra-processed food consumption had…

  • Greater total arterial wall volume. 
  • Greater total lipid core volume and maximum lipid core area.
  • Higher maximum segmental wall thickness.

No correlation was found between arterial plaque and other types of diet measures, such as carbohydrate and fat intake or glycemic load index.

  • The findings suggest that much of the negative health effect from ultra-processed foods comes from their contribution to arterial plaque buildup, which could occur through their unfavorable nutrient profile leading to alterations in blood lipids.

The Takeaway

In today’s hyperpolarized political environment – in which scientific inquiry is often subordinated to already-solidified beliefs – the new findings connecting MRI measurements of carotid artery plaque to ultra-processed foods offer a foundation for public policy changes that could indeed improve the health of Americans.

MRI Accident Turns Deadly

A tragic MRI accident in Long Island, New York, has turned deadly. A man who was pulled into a mobile MRI scanner by a heavy chain he was wearing died of his injuries. 

Keith McAllister was waiting outside a mobile MRI trailer operated by Nassau Open MRI on Long Island as his wife received a knee scan.

  • McAllister was wearing a weight-training chain around his neck that weighed some 20 pounds.

When he entered the trailer to help his wife get off the scanner table, the system’s powerful 1.5T magnetic field drew him against the magnet. It took staff an hour to free him.

Investigators are still looking into the details of the episode, but it underscores the shortcomings in how MRI safety is regulated in the U.S., where fatal MRI accidents are extremely rare but still do occur.  

  • That’s according to MRI safety expert Tobias Gilk, vice president at architectural firm Radiology Planning and founder of Gilk Radiology Consultants, who spoke to The Imaging Wire about the accident.

The U.S. has some of the most comprehensive and sophisticated guidelines on MRI safety, encapsulated in the ACR Manual on MR Safety.

  • What’s more, the radiology community including ACR, ISMRM, ASRT, and others are currently observing their annual MR Safety Week to promote safe MRI scanning – an event that started just a few days after McAllister died.

But despite the great leaps in knowledge about MRI safety, Gilk believes that keeping patients safe is complicated by the exponential growth in the modality’s complexity, while actual enforcement of safety standards is lacking. 

  • Many state health departments don’t even address MRI safety as they focus more aggressively on regulating ionizing imaging modalities like CT and X-ray, and healthcare certification bodies like the Joint Commission lack enforcement teeth.

Instead, MRI safety often becomes the responsibility of technologists who frequently must juggle multiple tasks as they manage both patients and scanner operations.

  • This can be particularly challenging in mobile MRI coaches, often staffed by a single MRI technologist where the only barrier between the outside world and the scanning environment is just a single – often unlocked – door. 

The Takeaway

The tragic death of Keith McAllister in a mobile MRI trailer shows that all the guidelines and safety events in the world won’t keep patients safe unless accompanied by stronger enforcement of the knowledge the radiology community already has. We can do better.

Prostate AI Improves Biparametric MRI

Researchers continue to hone in on the best way to use MRI for patients suspected of having prostate cancer, and AI is helping the effort. A new study in AJR shows that AI can improve the diagnostic accuracy and consistency of prostate MRI – while making it easier to perform.

Multiparametric MRI is the gold standard for prostate cancer imaging, but requires the use of three different MRI sequences as well as contrast administration, making it more complex and time-intensive to perform. 

  • On the other hand, biparametric MRI uses just two sequences – T2-weighted and diffusion-weighted imaging – and omits the contrast entirely, leading to shorter scan times and lower cost.

But what are you losing with bpMRI – and can AI help you get it back? Researchers addressed this question in the new study in which six radiologists interpreted bpMRI scans of 180 patients from multiple centers. 

  • Radiologists used a deep learning algorithm developed at the NIH to interpret bpMRI scans acquired on 3T scanners. The open-source algorithm generates binary prostate cancer prediction maps that are overlaid on T2-weighted images.

Researchers found that radiologists using the bpMRI AI algorithm to detect clinically significant prostate cancer had…

  • An increase in lesion-level positive predictive value (77% vs. 67%).
  • But lower lesion-level sensitivity (44% vs. 48%). 
  • And no statistically significant difference in patient-level AUC (0.82 vs. 0.83, p = 0.61).
  • While inter-reader agreement scores improved for lesion-level and patient-level PI-RADS scores and lesion size measurements. 

What to make of the numbers? The authors pointed out that the study design – in which AI was used as a first reader – may have reduced AI’s performance.

  • In real clinical practice, AI would most likely be used as a sort of clinical spell checker, with AI results overlaid on images that radiologists had already seen. 

The researchers said the results on improved positive predictive value and inter-reader agreement show that AI can improve the diagnostic accuracy and consistency of bpMRI for prostate cancer. 

The Takeaway

The new findings echo other research like the PI-CAI study highlighting the growing role of AI in prostate cancer detection. If validated with other studies, they show AI-assisted bpMRI could be ready to take on mpMRI for a broader role.

Get every issue of The Imaging Wire, delivered right to your inbox.

You might also like..

Select All

You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team

You're all set!