An unnamed physician suggesting that AI should focus on detection and diagnostic support, but leave treatment decisions up to human experts.

Imaging Wire Sponsors

Arterys  •  Bayer Radiology  •  Blackford Analysis  •  Canon Medical Systems  •  CARPL.ai  •  Change Healthcare  •  Fujifilm Healthcare  •  GE Healthcare  •  Intelerad  •  Novarad  •  Nuance  •  Riverain Technologies  •  Siemens Healthineers  •  United Imaging  •  Us2.ai

Artificial Intelligence

AI-Assisted Radiographers

A new European Radiology study provided what might be the first insights into whether AI can allow radiographers to independently read lung cancer screening exams, while alleviating the resource challenges that have slowed LDCT screening program rollouts.

This is the type of study that makes some radiologists uncomfortable, but its results suggest that rads’ role in lung cancer screening remains very secure.

The researchers had two trained UK-based radiographers read 716 LDCT exams using a computer-assisted detection AI solution (158 w/ significant pulmonary nodules), and compared them with interpretations from radiologists who didn’t have CADe assistance.

The radiographers had significantly lower sensitivity than the radiologists (68% & 73.7%; p < 0.001), leading to 61 false negative exams. However, the two CADe-assisted radiographers did achieve:

• Good sensitivity with cancers confirmed from baseline scans – 83.3% & 100%
• Relatively high specificity – 92.1% & 92.7%
• Low false-positive rates – 7.9% and 7.3%

The CADe AI solution might have both helped and hurt the radiographers’ performance, as CADe missed 20 of the radiographers’ 40 false negative nodules, and four of their seven false negative malignant nodules. 

Even as LDCT CADe tools become far more accurate, they might not be able to fill in radiographers’ incidental findings knowledge gap. The radiographers achieved either “good” or “fair” interobserver agreement rates with radiologists for emphysema and CAC findings, but the variety of other incidental pathologies was “too broad to reasonably expect radiographers to detect and interpret.”

The Takeaway
Although CADe-assisted radiographer studies might concern some radiologists, this seems like an important aspect of AI to understand given the workload demands that come with lung cancer screening programs, and the need to better understand how clinicians and AI can work together. 

Good thing for any concerned radiologists, this study shows that LDCT reporting is too complex and current CADe solutions are too limited for CADe-equipped radiographers to independently read LDCTs… “at least for the foreseeable future.”

RMI Sees Clearly and Decides Confidently

See how adopting ClearRead CT allowed Michigan’s Regional Medical Imaging’s radiologists to complete their chest CT reads faster and more accurately in this Riverain Technologies case study.

Canon Across America

Canon Medical is making its way through the US on its 2022 Mobile Tour, bringing its products and solutions directly to hospitals and providers in 50 US cities. Tune in to see when Canon is coming to you and watch highlights from its tour stops along the way.

The Wire

• COVID Recoveries: A new Radiology Journal study brought some good news for those recovering from COVID-19, finding that 93% of patients who were hospitalized with moderate COVID-19 pneumonia (n = 84) had no residual chest CT abnormalities after one year. The patients’ CTs showed significant improvements in ground-glass opacity prevenance (100% at baseline vs. 2% at 12mo), consolidations (71% at baseline vs. 0% at 6mo), and fibrotic-like abnormalities (50% at 3mo, 42% at 6mo, 2% at 12mo).

• RadNet’s AI Clearances: RadNet’s DeepHealth and Quantib subsidiaries scored FDA 510(k) clearances for updated versions of their flagship mammography and prostate MRI AI solutions. DeepHealth’s new Saige-DX solution (succeeds Saige-Q) automatically identifies suspicious lesions in mammograms and assigns suspicion levels to each finding and case, supporting detection and reducing unnecessary recalls. Quantib’s new Prostate 2.0 prostate cancer reporting solution (succeeds v1.3) adds automatic prostate zone segmentation (in addition to prostate gland segmentation) and localization of lesions on the PI-RADS sector map.

• Tumor Board Attendance Impact: A new Clinical Radiology study found that neuroradiologists’ participation in tumor board meetings directly impacts their diagnostic accuracy. The researchers analyzed 607 diagnostic errors from a tertiary academic center, finding a strong correlation between radiologists’ tumor board participation and their error rates (Spearman’s Rank correlation coefficient: –0.89, p=0.0002), while there was no correlation between radiologist experience and diagnostic accuracy.

• AI Funding Cools Down: Healthcare AI startups haven’t been immune to the recent plunge in health tech funding, with CB Insights reporting that the sector raised 32% less capital (still $2.5B) during the first quarter. The AI news comes right after Rock Health reported an 18% funding dropoff across all digital health companies in Q1 2022, breaking a streak of consecutive increases dating back to 2019. Despite last quarter’s slowdown, healthcare companies still led the AI sector in total funding and mega-rounds over $100M (7), but CB Insights predicts that we might see things continue to cool off before there’s a rebound.

• Clarius & Turtle’s Home Fertility Alliance: Clarius Mobile Health and Turtle Health unveiled their at-home virtual transvaginal ultrasonography solution, combining Clarius’ handheld ultrasound and transvaginal scanner with Turtle’s virtual gynecology clinic. Although the solution is under FDA review, their initial study showed that it provided follicle count information that’s comparable to in-clinic exams with greater patient satisfaction ratings. The alliance also continues an influx in home ultrasound activity, coming just a few days after GE Healthcare’s investment in home maternity/fertility ultrasound startup Pulsenmore and amid increased interest from a number of other ultrasound vendors.

• Home Dx Privacy: In other home care news, a Quest Diagnostics survey found many potential patients are concerned about how their at-home diagnostic data could be shared. Quest surveyed over 800 office workers, finding that 89% consider home health screenings an essential employment benefit, but 67% would not want their employer to know their results, and 55% are concerned about employer overreach in healthcare. This survey wasn’t specifically about imaging and few employers would likely support home imaging, but home imaging privacy concerns are likely similar.

• ProFound AI Risk Impact: A new study out of Sweden’s Karolinska Institutet highlighted iCAD’s ProFound AI Risk DBT solution’s ability to identify women with higher risks of developing breast cancer. The researchers used ProFound AI Risk to analyze DBT exams from 5,978 women (805 later diagnosed with cancer), achieving an 0.82 AUC (vs. traditional risk models’ 0.60 AUC). ProFound AI Risk marked 14% of the women as high risk, and those women represented 76% of all future stage II and III cancers and 59% of stage 0 cancers.

• Travel Labor Impact: Hospital labor expenses have risen by 37% from pre-pandemic levels, according to Kaufman Hall’s latest workforce dislocation report, and traveling clinician labor costs were a main driver. Contract labor accounted for 11% of total hospital labor expenses in 2022, versus 2% in 2019, while contract nurses’ median hourly wages climbed 106% since the beginning of the pandemic (from $64 to $132 per hour).

• iThera Targets DMD: iThera Medical is leading a €1.6m project to develop a machine learning-assisted optoacoustic imaging solution for pediatric Duchenne muscular dystrophy (DMD) monitoring. The solution will combine iThera’s Multispectral optoacoustic tomography (MSOT) technology, ML-based 3D image reconstruction, and a handheld probe, and would potentially allow clinicians to better detect/quantify DMD biomarkers.

• Mayo’s Pre-Imaging Chatbots: A new Mayo Clinic study showed that a text chatbot solution they deployed to screen for signs of COVID before patients’ outpatient imaging exams achieved decent participation (58.1% of 4,687 patients), high patient experience scores (avg 4.6 out of 5), and flagged roughly 4% of scheduled patients with COVID symptoms or pending tests. Unsurprisingly, English speaking patients were far more likely to respond to the texts (odds ratio: 2.71).

• Data Breach Case Dismissed: A federal judge dismissed the class action data breach case against Northeast Radiology PC and Alliance HealthCare Services, finding that the plaintiffs’ allegations that the PACS breach could cause patients future harm was too speculative. The early 2020 breach officially affected 29 patients, but the lawsuit alleged that the breach potentially exposed 1.2M patient’s medical records, putting them at risk of future misuse of their information.

Blackford’s AI Value Matrix

Working out your AI business case? Check out this helpful Blackford Analysis post detailing how to create your AI Value Matrix based on your organizational objectives and value indicators.

WellSpan Health’s AI Implementation

We’re excited to share the latest Imaging Wire Show, featuring Aidoc’s Elad Walach and WellSpan Health’s Edward Steiner, MD. 

We explore WellSpan’s path towards AI adoption, WellSpan and Aidoc’s evolving partnership, why some in radiology are slow to adopt AI, and how they can successfully bring AI into their practices. This is a must-watch episode whether you’re an AI insider or still figuring out your AI plan, so check it out.

The Resource Wire

• Clinicians are using the NAEOTOM Alpha to overcome limitations previously thought unavoidable in CT, with ultra-high spatial resolution without dose penalty and detailed spectral imaging without compromises. Get the facts about the technology and the benefits of photon-counting CT.

• When SyntheticMR validated its SyMRI MSK solution, they leveraged the CARPL platform to compare conventional knee and spine MRI image quality with SyntheticMR images. Check out their validation process and results here.

• Precision medicine startup BAMF Health just installed United Imaging’s uEXPLORER scanner, making it the first total-body PET/CT used for theranostics in the US. See how this combination will allow BAMF Health to deliver more effective and efficient theranostics treatments.

• Do your patients text more than they use CDs? Find out how Novarad’s CryptoChart simplifies image access, combining secure QR codes and text and email communications to help providers and patients ditch the disk.

• Learn how Windsong Radiology Group used Bayer’s MEDRAD Stellant FLEX CT injection system to drive efficiencies and standardization across its imaging centers.

• See how three hospitals are leveraging GE Healthcare’s AIR Recon DL to improve their cardiac MRI image quality, shorten scan times, and expand their cardiac imaging capabilities.

• Working on your enterprise imaging cloud strategy? Hear how two healthcare IT leaders are moving their enterprise imaging to the cloud and the lessons they learned along the way in this Change Healthcare podcast.

• See how Us2.ai cuts echocardiography’s manual work, subjectivity, and turnaround times to automate the fight against heart disease.

• Arterys’ Cardio AI solution recently added a new Atrial Volumes feature that allows cardiologists and radiologists to easily quantify volumes for both left and right atria in cardiac MRI images.

• See how Valley Radiology’s decision to make Intelerad IntelePACS its single reading environment helped the independent practice gain control of its growing volumes and rising case complexity, improve its efficiency and radiologist experience, and deliver better patient care.

• In this Nuance Q&A, Open System Imaging’s medical director and CTO discuss how adopting PowerScribe One improved the California radiology practice’s efficiency and productivity.

• See how Fujifilm Healthcare helped Arkansas Children’s Hospital imaging IT infrastructure evolve from departmental silos to an interoperable architecture that improved its radiology and IT teams’ day-to-day flexibility and future scalability.