Technology

Neurology CT

Cardiac CT

Women's Health CT

Oncology CT

Facility Management

Neurology MRI

Oncology MRI

Women's Health MRI

Cardiac MRI

Mammography

Molecular Imaging

Women's Health Ultrasound

Oncology Ultrasound

Cardiac Ultrasound

Ultrasound

Orthopedic X-Ray

X-Ray

News

All News

Blogs

Media

Around the Practice 

Between the Lines

Image IQ

Medical World News

Podcasts

Rad-View

Videos

Conferences

Conference Coverage

Conference Listing

DI Executive

Resources

CME/CE

E-books

Education

Interactive Tool Kits

Partners

Subscribe

Advertise

About

Contact Us

Editorial

Editorial Board

Do Not Sell My Personal Information 

Privacy

Terms and Conditions

Diagnostic Imaging

Facebook

LinkedIn

YouTube

Spotlight

Disease Spotlight: Prostate Cancer

Image IQ Quiz

RSNA 2023

Rad View: PSMA PET Imaging Recommendations

Rad-View: Generic Contrast Agents 

Unlock AI-Powered Imaging

Topics

View More

1rem

Authors

Reader Feedback

Many outstanding radiology teaching resources are now available on the Internet. The huge number of such Web sites is increasing on an almost daily basis.

Web sites provide boost for radiology training

The last decade spawned great changes throughout Europe affecting junior radiologists as well as those in many other specialties. New technical and subspecialty developments increase demands on junior radiologists but also create entirely new opportunities.

ECR offers trainees opportunities to expand knowledge base

The use of artificial intelligence (AI) tools to provide quantitative coronary tomography (AI-QCT) and coronary plaque analysis (AI-CPA) based on coronary computed tomography angiography (CCTA) will soon be covered by four Medicare administrative contractors (MACs).

Starting on November 24, the MACs Palmetto GBA, National Government Services (NGS), CGS Administrators and WPS administrative groups will cover the use of AI-QCT and AI-CPA for Medicare beneficiaries with acute or stable chest pain, and no known coronary artery disease (CAD), according to a recently updated local coverage determination (LCD) issued by the Centers for Medicare and Medicaid Services (CMS).

The LCD noted coverage of AI tools will be provided for the testing of patients deemed to be at intermediate risk for CAD, or those classified by the Coronary Artery Disease Reporting and Data System (CAD-RADS) as having CAD-RADS 1, CAD-RADS 2 or CAD-RADS 3, based on CCTA findings. The coverage will also apply for those who have had negative or inconclusive evaluation for acute coronary syndrome (ACS), according to the LCD.

The use of the FDA-cleared AI modalities 

“Coronary artery disease is the underlying cause of about 50% of deaths,” noted Ron Blankstein, M.D., the director of cardiac computed tomography at Brigham and Women's Hospital and a professor of medicine at Harvard Medical School in Boston. “Medicare coverage of HeartFlow Plaque Analysis is a major step forward in improving coronary artery disease management. The earlier we can diagnose and use tools to provide accurate plaque quantification, the earlier we can provide tailored treatments, potentially improving outcomes for patients.”

“We are also extremely thankful to the many physicians and medical society partners who used their voices to advocate for this essential AI-QCT technology. Until Cleerly, health-care providers have not had a way to easily and completely assess the primary cause of heart attacks, atherosclerotic plaque burden and type in a non-invasive way, which is especially important for our senior population,” noted James L. Kim, M.D., the CEO and founder of Cleerly. “This decision by the MACs represents a significant step in advancing the field of cardiology and providing the best possible care for our seniors.”

(Editor’s note: For related content, see “

FDA Clears Software for Enhancing CCTA Assessment of Atherosclerosis

Coronary CT Angiography Study Shows Link Between Major Cardiovascular Events and High Lipid Core Burden

Meta-Analysis Shows Superiority of CT Angiography Over SPECT and Functional Testing for Obstructive CAD

1. Centers for Medicare and Medicaid Services (CMS). Artificial intelligence enabled CT based quantitative coronary topography (AI-QCT)/coronary plaque analysis (AI-CPA). Available at: 

https://www.cms.gov/medicare-coverage-database/view/lcd.aspx?lcdid=39851&ver=10

 . Published October 10, 2024. Accessed October 14, 2024.

2. Cleerly. Medicare administrative contractors approve coverage of Cleerly heart scans to Medicare recipients. Business Wire. Available at: 

https://www.businesswire.com/news/home/20241014694634/en/Medicare-Administrative-Contractors-Approve-Coverage-of-Cleerly-Heart-Scans-to-Medicare-Recipients

 . Published October 14, 2024. Accessed October 14, 2024.

3. HeartFlow. HeartFlow announces favorable coverage determination for plaque analysis by four Medicare administrative contractors. GlobeNewswire. Available at: 

https://www.globenewswire.com/news-release/2024/10/11/2962144/0/en/HeartFlow-Announces-Favorable-Coverage-Determination-for-Plaque-Analysis-by-Four-Medicare-Administrative-Contractors.html

4. Elucid. Elucid announces favorable Medicare coverage of AI coronary plaque analysis. Business Wire. Available at: 

https://www.businesswire.com/news/home/20241015489543/en/Elucid-Announces-Favorable-Medicare-Coverage-of-AI-Coronary-Plaque-Analysis

 . Published October 15, 2024. Accessed October 15, 2024.

Four Medicare administrative contractors (MACs) will provide coverage of AI-enabled coronary plaque analysis and quantitative coronary tomography assessment of coronary computed tomography angiography (CCTA) for Medicare beneficiaries starting in November 2024.

Topic

Medicare to Cover AI-Powered, CCTA-Based Coronary Plaque Analysis and Quantitative Coronary Topography 

The Food and Drug Administration (FDA) has granted 510(k) clearance for AngioFlow™, an artificial intelligence (AI)-enabled perfusion imaging software that may facilitate more timely assessments of perfusion status prior to endovascular procedures.

Offering color-coded perfusion mapping that identifies regions with reduced cerebral blood flow and blood volume, 

 provides results within minutes of a cone-beam computed tomography (CT) scan, according to RapidAI, the manufacturer of AngioFlow.

In addition to potential cost savings by reducing redundant imaging, RaidAI emphasized that AngioFlow’s timely assessments may reduce long-term disability risks and facilitate life-saving interventions for patients in need of acute stroke care.

“AngioFlow by RapidAI will allow physicians to assess the need for additional imaging immediately in the interventional suite. By avoiding unnecessary scans, stroke patients can receive the timely care that can be the difference between being able to walk out of a hospital to their homes versus being discharged to a skilled nursing facility,” said Abhishek Singh, MD, DABPN, DUCNS, who is affiliated with the Creighton University School of Medicine in Omaha, Nebraska.

The company added that AngioFlow has been validated in more than 10 clinical trials.

Reportedly validated in more than 10 clinical trials, the AngioFlow perfusion imaging software enables timely identification of brain regions with cerebral blood flow reduction and those with significant hypoperfusion.

FDA Clears AI-Powered Qualitative Perfusion Mapping for Cone-Beam CT

Artificial intelligence has been transforming modern radiology in diagnostic accuracy, efficiency, and patient outcomes. What do the leading AI innovations offer in advancing imaging in practices? 

79% healthcare organizations presently utilize AI technology

In a recent long-term study evaluating the use of active surveillance in over 2,100 men with low-risk prostate cancer (PCa), researchers found that nearly half of the study participants had no disease progression a decade after initial diagnosis and less than two percent of the cohort experienced metastatic disease.

 demonstrates that long-term active surveillance in men with localized PCa significantly reduces unnecessary biopsies and over-treatment, according to Lisa F. Newcomb, PhD, the deputy director of the Canary Prostate Active Surveillance Study at the University of Washington and Fred Hutchinson Cancer Center in Seattle.

In a recent interview with our sister publication 

, Dr. Newcomb shared her insights from the study.

(This article has been adapted with permission from its original publication in 

Please describe the background for this study.

The Canary Prostate Active Surveillance Study (PASS) is a protocol-directed multicenter study. We're enrolling patients at 10 sites throughout the United States and Canada. The protocol was written and conceived in 2007, and we started enrolling patients in 2008. This was a period when there was a large recognition of overtreatment of indolent 

 that would not cause harm if left untreated. This had come about with the era of prostate-specific antigen (PSA) screening. PSA screening started in the 1990s, and at this time, there were several studies that were starting to show that low-risk prostate cancers would not cause harm if they were left untreated. But 90 percent of low-risk cancers were being treated immediately by radiation or surgery, usually, and so active surveillance was being introduced as a management strategy that mitigates the effects of overtreatment. With active surveillance, participants have PSAs regularly, every six months to a year, periodic prostate biopsies, and more recently, MRI has been incorporated in surveillance protocols. The goal is to avoid treatment if there are no signs of progression, or treat when there are signs of progression, but not before that.

Today, all clinical guidelines recommend active surveillance as a preferred management strategy for favorable-risk or low-risk cancers. But yet, the uptake in the United States is still only about 60 percent for low-risk cancers, and the uptake varies a lot by clinical practice and even by urologists or practitioners within a specific practice. So it was in this setting that we evaluated active surveillance as a long-term management strategy for favorable-risk cancers, and we did this by assessing the outcomes of the 2155 patients who were enrolled in Canary PASS over the past 15 years.

What were some of the notable findings? Were any of them surprising to you and your coauthors?

I think one of the important findings was that at 10 years, about 50% of the men in our cohort had received treatment. This was not surprising. It's pretty in line with many surveillance or monitoring studies. We also found that during the same time frame, less than 2% of participants had developed metastatic cancer, and well less than 1% — 0.2% — had died of their prostate cancer, while during that same time frame, the overall mortality was a little over 5%.

One of the unique and important findings from our study is we looked at the adverse outcomes of men who were treated, reclassified, and then treated at the confirmatory biopsy, or the first biopsy after the diagnostic biopsy. This was a median of one and a half years after prostate cancer diagnosis. We compared them to the men who were treated later during surveillance, so after a median of four and a half years, they received two to three additional surveillance biopsies. We found that there were very similar rates of adverse outcomes. The rate of adverse pathology in the people who received surgery was virtually identical, about 31 percent in both groups. Recurrence after treatment was, again, virtually identical; about 10% of men had their cancer recur within five years after receiving delayed treatment. And, if anything, the rates of metastasis were higher in the people treated early after the confirmatory biopsy. Fourteen of the 21 metastases that occurred in our cohort, which is 75 percent of the metastases, occurred after either upgrading or treatment after the confirmatory biopsy, the first biopsy after diagnosis. So very few of the metastases were recurring later during this surveillance regimen, which we were happily surprised (to see).

What do you consider to be the most significant findings regarding the long-term oncologic outcomes of patients on active surveillance?

The most important finding is that the rates of adverse outcomes that we don't ever want to see are very low. They're not zero, but they're very low, and our findings really support the use of active surveillance compared with immediate treatment for favorable-risk prostate cancer.

How do the results of this study compare with previous research on active surveillance for prostate cancer?

The rates of our adverse outcomes are lower than in many — not all —studies. Comparing studies is difficult. There are several factors that can contribute to rates, such as the enrollment criteria in the study and the follow-up regimens. For example, Canary PASS has broad eligibility criteria. There are no Gleason requirements. There are no PSA requirements. This was deliberately intended to capture all men using active surveillance. In comparison, Johns Hopkins, which has a very well-established active surveillance series, has much stricter eligibility criteria. They have lower risk men in their cohort, and they (have) the one study that has slightly lower rates of metastasis and death than we find.

Another factor that contributes to outcomes in men using surveillance is the follow-up protocol, and Canary PASS does have protocol-directed biopsies, and it has high compliance to those biopsies. In the published work, we had an every-2-year biopsy schedule after that first confirmatory biopsy, which we always recommend within a year after diagnosis. We've recently extended our biopsy schedule to four years, so there's a recognition that a super-stringent biopsy schedule is not necessary, but we do think that the high adherence to surveillance biopsies in our cohort probably contributes to lower rates of adverse outcomes in the long run.

What are some potential limitations of the study, and how might these limitations be addressed in future research?

That's an important question. One of the largest limitations in our study is that our cohort spans the era of multiparametric MRI being introduced into prostate cancer care. We have always collected data on the use of MRI, and we have recently added MRI as a requirement before any biopsy in our protocol. Although about half of our cohort has had an MRI during surveillance, the other half hasn't. And it is possible that increased use of MRI, especially early, around diagnosis, could reduce the rates of adverse outcomes such as recurrence or metastasis even further.

Another limitation of our study is that we only have 7% Black participants in our study, and we have previously published that the rates of upgrading on surveillance biopsies are similar in Black and White men, but larger studies do need to be done to assess the long-term outcomes of Black men (undergoing) active surveillance. Lastly, our median follow-up is 7.2 years, which is longer than most published active surveillance studies. Yet, in the natural history of prostate cancer, it's still relatively short, and I do expect that with more time, we will see more recurrence and metastasis and probably a few more prostate cancer deaths in our cohort.

What are your plans for future research in this area, and how might the results of this study inform future research?

We are really focusing on better stratifying the risk in these favorable-risk diagnoses. We've learned from this study that at least 50% of the men in our cohort do not need as frequent biopsies as they have been receiving, so we're focusing on better ways to identify those men early, so they can be spared the morbidities of biopsies. Likewise, there's about 10% to 15% that have reclassification to grade group 3 or recur after treatment or did metastasize. We would like to identify those men even earlier, so they could be treated earlier. To do both of these techniques of risk stratification, we're looking at a number of biomarkers—tissue based, blood based, urine based. We're doing a deep dive into histologic features such as cribriform. There's a fair amount of evidence that Gleason pattern 4 disease that has cribriform has worse outcomes than pattern 4 that does not have cribriform. We're working with a number of companies to evaluate AI strategies for histology and for MR imaging.

What would you say is the take home message of the paper?

These prostate cancers that are diagnosed as grade group 1, many of the grade group 2, PSA levels less than 10 to 20 (ng/mL), do not need immediate treatment. They can safely be surveilled with regular PSA, periodic biopsies, and periodic MRI, and only treated if there's signs of progression.

My hope is that the results of our study improve the uptake of active surveillance, further reducing unnecessary treatments, and this, combined with the improving reflex tests, may change the risk-benefit of PSA screening. I really hope that there is more uptake of PSA screening. With the U.S. Preventive Services Task Force recommendations of a D and now a C rating for PSA screening, there has been increasing rates of metastasis and mortality. PSA is not a perfect biomarker. It lacks specificity, but it is the most available early-detection biomarker for prostate cancer. I would like to see a greater use of PSA screening.

1. Newcomb LF, Schenk JM, Zheng Y, et al. Long-term outcomes in patients using protocol-directed active surveillance for prostate cancer. 

2024;331(24):2084-2093. doi:10.1001/jama.2024.6695

In a recent interview, Lisa F. Newcomb, Ph.D., discussed the merits of active surveillance for low-risk prostate cancer (PCa) and key findings from multicenter research involving over 2,100 men with localized PCa.

Clinical

Current Concepts in Active Surveillance for Prostate Cancer

Emerging research suggests an artificial intelligence (AI) platform may improve prostate cancer (PCa) detection on multiparametric magnetic resonance imaging (mpMRI).

In a retrospective study, recently published in the 

software (Mediaire) in 123 men (mean age of 66.8 years) who had mpMRI and subsequent biopsies. Fifty-five men in the cohort had clinically significant 

 (csPCa), 53 participants had no PCa and 15 patients had non-significant PCa, according to the study.

The researchers found that the AI software had a 100 percent sensitivity rate and a 100 percent negative predictive value at a cutoff of PI-RADS 

“In a clinical workflow, this could potentially reduce the number of unnecessary biopsies, thereby minimizing patient discomfort, reducing healthcare costs, and allowing for more focused attention on cases with higher suspicion of malignancy,” wrote lead study author Nadine Bayerl, M.D., who is affiliated with the Institute of Radiology at the University Hospital Erlangen in Erlangen, Germany, and colleagues.

Noting low specificity at the PI-RADS > 2 threshold (7.5 percent for PCa with a Gleason score 

 6), the study authors also examined the capability of the AI software at higher PI-RADS cutoffs. Employing a PI-RADS 

 3 cutoff, the researchers noted an 85.5 percent sensitivity and 60.3 percent specificity for the 

software for diagnosing csPCa. The study authors found similar sensitivity (85.5 percent) and specificity (63.2 percent) for the PI-RADS 

“One of the primary advantages of AI tools like 

 is their `potential to reduce intra- and interreader variability in prostate MRI interpretation. The automated nature of the 

 algorithm ensures consistent application of PI–RADS scoring criteria, enhancing the reproducibility of prostate MRI evaluations,” emphasized Bayerl and colleagues.

The researchers also pointed out that while the AI software offered 8.5 to 10.5 percent lower sensitivity rates than PI-RADS 

 3 assessments reported in two meta-analyses, the specificity rate for those assessments with the 

software ranged between 4.3 to 17.3 percent higher (60.3 percent vs. 56 percent and 43 percent).1-3

MRI Study Suggests Deep Learning Model Offers Equivalent Detection of csPCa as Experienced Radiologists

PSMA PET/CT or mpMRI: Which is Better for Diagnosing Biochemical Recurrence of PCa?

How Effective is mpMRI at Detecting PCa in Biopsy-Naïve Patients?

Beyond the inherent limitations of a retrospective study, the authors acknowledged the small cohort size and the lack of direct comparison of the AI software to radiologist interpretation with the PI-RADS 2.1 classification system. They also conceded a lack of differentiation between zonal locations of the prostate lesions.

1. Bayerl N, Adams LC, Cavallaro A, et al. Assessment of a fully-automated diagnostic AI software in prostate MRI: clinical evaluation and histopathological correlation. 

https://www.ejradiology.com/article/S0720-048X(24)00506-0/fulltext

 . Published October 14, 2024. Accessed October 16, 2024.

2. Park KJ, Choi SH, Hyun KM, Kim JK, Jeong IG. Performance of Prostate Imaging Reporting and Data System, version 2.1 for diagnosis of prostate cancer: a systematic review and meta-analysis. 

3. Oerther B, Nedelcu A, Engel H. Update on PI-RADS version 2.1 diagnostic performance benchmarks for prostate MRI: systematic review and meta-analysis. 

When employing a PI-RADS > 4 cutoff, researchers found that the mdprostate software provided an 85.5 percent sensitivity rate for diagnosing clinically significant prostate cancer on mpMRI.

Emerging AI Platform Shows Promise for Prostate Cancer Detection on mpMRI

A 12-year-old boy presents to the emergency department with acute pain in the medial aspect of his right elbow after pitching in a baseball game. He also complains of dull lateral elbow pain that has been present for weeks. AP, oblique, and lateral radiographs of the right elbow were obtained.

Medial and lateral epicondyle avulsion fractures

Medial epicondyle avulsion fracture and osteochondritis dissecans of the capitellum

A 12-year-old boy presents to the emergency department with acute pain in the medial aspect of his right elbow after pitching in a baseball game. 

Christiane Nyhsen, MD

Articles

Latest Updated Articles