University of Toronto’s Patrik Rogalla, MD on how AI will handle radiologists’ more routine tasks.

We’re excited to share the latest Imaging Wire Show, featuring Commonwealth Radiology Associates’ Allan Hoffman, M.D. 

Join us for a great conversation about how CRA’s innovative approach to practice culture and hospital partnerships has allowed it to thrive while staying independent.

Imaging Wire Sponsors

Arterys  •  Bayer Radiology  •  Blackford Analysis  •  Canon Medical Systems  •  Fujifilm Healthcare  •  GE Healthcare  •  Nanox.AI  •  Novarad  •  Nuance  •  Riverain Technologies  •  Siemens Healthineers  •  United Imaging

Artificial Intelligence

The State of AI

A group of radiology leaders starred in Canon Medical’s recent State of AI in Radiology Today Roundtable, sharing insights into how imaging AI is being used, where it’s needed most, and how AI might assume a core role in medical imaging.

The panelists were largely from the user/clinical side of imaging (U of Maryland’s Eliot Siegel, MD; UC Irvine’s Peter Chang, MD; UHS Delaware’s Cindy Siegel, CRA; U of Toronto’s Patrik Rogalla, MD; and Canon’s Director of Healthcare Economics Tom Szostak), with deeper AI experience than many typical radiology team members.

Here are some of the big takeaways:

We’re Still Early – The panel started by making sure everyone agrees on the definition of AI and much of ensuing discussions focused on AI’s future potential, which says a lot about where we are in AI’s lifecycle.

Do We Need AI? – The panelists agreed that radiology does indeed need AI, largely because it can improve the patient experience (shorter scans, faster results, fewer call-backs), help solve radiology’s inefficiency problems, and improve diagnostic accuracy.

Does AI Really Improve Efficiency? – Outside of image reconstruction, none of the panelists were ready to say that AI currently makes radiologists faster. However, they still believe that AI will improve future radiology workflows and outcomes.

Finding The Killer App – Things got a lot more theoretical at the halfway point, when the conversation shifted to what “killer apps” might bring imaging AI into mainstream use, including AI tools that:

• Identify and exclude normal scans with extremely high accuracy (must be far more accurate than humans and limit false positives)
• Curate and submit all CMS quality reporting metrics (eliminates admin work, generates revenue)
• Identify early-stage diseases for population health programs (keeps current diagnostic workflows intact)
• Interpret and diagnose all X-ray exams (eliminates high volume/repetitive exams, rads don’t read some XRs in many countries)
• Improve image quality, allow faster scans, reduce dosage (aka DL image reconstruction)

AI’s Radiologist Impact – The panelists don’t see AI threatening radiologist jobs in the short to mid-term given AI’s current immaturity, the “tremendous inefficiencies” that still exist in radiology, and the pace of imaging volume growth. They also expect volume growth to drive longer term demand for both AI and rads, suggesting that AI adoption might even amplify future volume growth (if AI expands bandwidth and cuts interpretation costs, the laws of economics suggest that more scans would follow).

What AI Needs – With most of the technical parts of building algorithms now figured out, AI’s evolution will depend on getting enough training data, improving how AI is integrated into workflows, and making sure AI is solving radiology’s biggest problems. Imaging AI also needs healthcare to be open to change, which would require clear clinical, operational, and financial upsides.

Blackford’s AI Platform Playbook

Check out this Imaging Wire Show interview with Blackford Analysis founder and CEO, Ben Panter, detailing how to solve AI’s assessment and deployment problem, AI’s downstream value, and what it will take for AI to have its greatest impact.

United Imaging’s US Investment

United Imaging Healthcare started investing in the U.S. with R&D in 2013. They added offices. They hired (the best) people across the country. They launched commercially on the national stage in 2018. But the cherry on top was opening their U.S. factory, showroom, and training center in Houston – in the midst of a pandemic – one year ago. It’s a unique facility for the U.S., and they’ve loved showing it to hundreds of people in person so far, and many more virtually. Here’s to many more years of growth

The Wire

• The Medical Imaging 13: CBInsights released its 2021 Digital Health 150 list, which included 13 medical imaging companies, and brought some interesting changes from last year. The analyst firm slashed its field of AI triage/detection companies (from 7 to 3; now Lunit, Qure.ai, Shukun), while going all-in on POCUS startups (from 1 to 5; now DiA Imaging Analysis, Caption Health, Exo, Ultromics, See-Mode). CBInsights also expanded its list of imaging firms focused on disease assessment/management (from 1 to 3; now Cleerly, Elucid, Perspectum), and added its first companies from the “picks and shovels” (Centaur Labs) and non-pixel (Rad AI) sides of radiology AI.

• Physician Gender Disparities: A new Health Affairs study found that female physicians in the U.S. make $2M less than their male colleagues during a 40-year career (n = 80k, $6.2M vs. $8.3M), even after adjusting for factors like hours worked, specialty, and practice type. Female physicians’ earning disparities were greatest for surgical specialists and nonsurgical specialists (-$2.5M & -$1.6M), while female radiologists made nearly $1M less than their male counterparts. 

• Subtle + Cortechs.ai Synergies: A new study in the American Journal of Neuroradiology found that Subtle Medical’s SubtleMR image enhancement software allows 60% faster brain MRIs, without affecting the performance of Cortechs.ai’s NeuroQuant quantitative volumetric analysis software. The researchers performed standard and accelerated brain MRIs on 40 patients (enhancing the accelerated MRIs with SubtleMR), finding that NeuroQuant performed the same with the SubtleMR-enhanced accelerated MRIs and standard MRIs. A pair of neurorads also found that the Subtle-enhanced scans’ image quality was superior to the standard MRIs.

• Medicare Reprieve: American providers breathed a sigh of relief after Congress passed legislation that will soften upcoming 2022 Medicare cuts. Once president Biden signs it into law, the 2022 Medicare conversion factor rate for physicians will increase by 3%, the automatic 2% Medicare payments cuts will be suspended through June 30th (and then reduced to 1%), and the 15% reduction in clinical diagnostic lab tests will be eliminated for 2022.

• Exablate Prostate Cleared: Insightec announced the FDA clearance of its Exablate Prostate MR-guided Focused Ultrasound prostate tissue treatment system. Exablate Prostate uses Focused Ultrasound to destroy prostate tissue without surgery (using MR for targeting and temp monitoring), reducing tissue damage and potentially allowing patients to delay or avoid radical therapy. Given the achievements of Insightec’ Exablate Neuro system (global regulatory approvals, widespread plan coverage), Exablate Prostate is worth keeping an eye on.

• The Incidental Recommendation Gap: A new study out of NYU found that adopting a structured recommendation and closed-loop tracking/communication system for incidental lung nodules (ILNs), didn’t sufficiently improve their follow-up rates. The researchers analyzed ILN follow-ups before and after adopting the system (n = 255 & 1,046), revealing that follow-up imaging rates did increase (60% vs. 70%). However, follow-ups were largely associated with non-reporting factors (e.g. race, imaging site, nodule size) and 30% of follow-ups still didn’t happen. The authors suggested that improving patient communication during the discharge process might be more effective.

• The Fixed XR & Flouro Rebound: After COVID-driven declines in 2020, Signify Research forecasts solid 2021 revenue rebounds for the global fixed digital radiography (from -14% in 2020 to +10% in 2021) and fluoroscopy markets (from -19% to +8%). Fixed X-ray’s 2021 revenue rebound came at the expense of the mobile X-ray market (from +77% to -39%), and quickly returned the fixed segment to pre-pandemic levels. Meanwhile, fluoroscopy spending will remain largely procedure and hospital budget dependent, gradually returning to pre-COVID levels by 2024.

• Modest AI Generalization: UCSF and UPenn researchers found that adding a “modest” amount of relevant external data to an otherwise all-internal DL training set significantly improves generalizability. The researchers first trained a brain MRI abnormality segmentation model using 293 exams from a single institution (IN1) and then tested it against 51 patients from a second intuition (IN2), finding that performance declined with IN2 data. Then, after evaluating different training data variations (IN1, IN2, and multi-institution data), they found that training the model with 90% IN1 data and 10% IN2 data allowed equal performance when tested with larger IN1 and IN2 datasets.

• AHN & Penn State’s Reading Partnership: Allegheny Health Network (AHN) and Penn State Health announced that the Penn State radiology department is now providing imaging study reading and interpretation support for AHN (currently 1-3 rads per day). The partnership will allow AHN to absorb its significant imaging volume growth, while supporting the Penn State radiology division’s goal to expand to external health care providers. There might be other academic hospitals with this type of alliance but it’s the first we’ve ever seen, and it’s an interesting alternative to working with telerads or local private practices.

• AMRA’s Muscle Assessment 510(k): AMRA Medical announced the FDA clearance of its MAsS Scan muscle assessment solution. MAsS Scan utilizes AMRA’s rapid neck-to-knee MRI protocol, analyzing muscle and fat biomarkers, and producing reports containing patients’ Muscle Assessment Scores, body composition measurements (with insights), and segmented images.

Salem Regional’s Case for Bayer MEDRAD Stellant FLEX

Learn how Salem Regional Medical Center improved its radiology workflows and cut service and syringe expenses after adopting Bayer’s MEDRAD Stellant FLEX system.

The Resource Wire

• This Journal of Neuroimaging study found that 4D Flow MRI effectively supports cerebrovascular vasoreactivity analysis for extracranial‐to‐intracranial bypass planning and post-surgery evaluation, revealing a new use case for Arterys’ Cardio AI software.

• See how New Jersey’s Ramapo Radiology Associates overcame their CD burning problems and improved their physician and patient experiences with Novarad CryptoChart.

• This Riverain Technologies case study details how Einstein Medical Center adopted ClearRead CT enterprise-wide (all 13 CT scanners) and how the solution allowed Einstein radiologists to identify small nodules faster and more reliably.

• See how and why Nanox.AI sees a much bigger future for public health AI than many of us imagine in this Imaging Wire Q&A with Zohar Elhanani.

• Did you know 80% to 90% of sonographers experience pain while performing scans at some stage in their career? Check out this Canon Medical Systems video detailing its latest innovations that improve sonographer comfort and help reduce risk of injury.

• See how GE Healthcare’s AI-ready PACS will help radiology unleash the promise of AI. 

• When the demand for your PET/CT imaging services outpaces available appointments, what are your options? Learn how Hackensack University Medical Center optimized its clinical operations by upgrading its Biograph Horizon to TrueV technology in this new case study from Siemens Healthineers.

• See how VidiStar users have benefitted from Fujifilm Healthcare’s cardiovascular information system’s flexible SaaS-based model and leveraged its productivity advantages to drive reimbursements.

• More efficiency and accuracy – less burnout and IT overhead. Those are the key results from adopting cloud speech technology detailed by Nuance in this infographic.