Memorial Sloan Kettering’s Anton Becker, MD, PhD on imaging’s need for an IT overhaul.

Imaging Wire Sponsors

annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  Canon Medical  •  CARPL.ai  •  Change Healthcare  •  Enlitic  •  GE Healthcare  •  Hyperfine  •  Intelerad  •  Novarad  •  Riverain Technologies  •  Siemens Healthineers  •  United Imaging  •  Us2.ai

Informatics

Imaging IT’s Infrastructure Problem

A heated Twitter conversation revealed widespread discontent with imaging’s outdated and fragmented IT infrastructure, suggesting that it’s draining radiologist productivity and standing in the way of AI adoption.

This tweet by Memorial Sloan Kettering’s Anton Becker, MD, PhD got things started: “95% of radiology departments would do well to direct 100% of their AI efforts and budget towards upgrade and maintenance of PACS, RIS and dictation software for the next 5 years… Our field is plagued by legacy software.” 

And here’s what the ensuing replies and retweets revealed:

• PACS Productivity – Nearly everyone agreed that their overall imaging IT setup was insufficient, with one rad estimating that a “supercharged PACS” would improve his productivity by 30%, and another noting that workflow customization would “at least double” her speed and accuracy.

• Imaging IT Revolution – Some called upon the “legacy” PACS, RIS, and voice recognition vendors to make more “revolutionary changes,” rather than settling for tweaks to current setups. Others proposed government intervention.

• IT Isn’t Flashy – One thing that might be holding some imaging IT overhauls back is “it’s not as flashy to boast” about high-quality infrastructure, and “the people who have authority to allocate resources are more motivated by flash than function.”

• Holistic IT – Eventually the conversation led to several well received proposals that we “eliminate the idea of PACS as a category and start thinking more holistically about radiology IT.” In other words, this might be more of a “fragmentation problem” than a PACS/RIS/voice functionality problem (or an AI budget problem). 

The Takeaway

Even if RadTwitter tends to skew towards academic radiologists and often focuses on what’s going wrong, this conversation indicates widespread dissatisfaction with current imaging IT setups, and suggests that radiologist productivity (and perhaps accuracy and burnout) would improve significantly if imaging IT worked as they’d like it to work. 

It’s debatable whether this imaging IT problem is actually due to an unnecessary focus on AI (very little of the conversation actually focused on AI), but it does seem reasonable that rad teams with solid infrastructure would be more likely to embrace AI.

Lessons from the Informatics Trenches

During 25 years in the imaging informatics trenches you see a lot of patched together solutions to data governance problems. See how these work-arounds helped shape Enlitic product leader Rocky Lien’s vision for what can be accomplished using Curie|ENDEX.

Canon Across America

Check out this Imaging Wire Show featuring Canon Medical Systems’ David Hashimoto, exploring how Canon is connecting with imaging teams and working to address their needs.

The Wire

• Guerbet & Bracco’s GBCA Clearance: Guerbet and Bracco Imaging announced the FDA clearance of their co-developed MRI agent, Gadopiclenol, which they will commercialize separately under Guerbet’s Elucirem and Bracco’s VUEWAY brands. Gadopiclenol reportedly has the highest relaxivity of any GBCA and requires half the gadolinium dose. Guerbet will manufacture Gadopiclenol’s active ingredient and vials for Bracco for up to seven years, when Bracco will begin manufacturing the GBCA on its own.

• CTAC AI CAC Scoring: JACC highlighted an AI model that can quickly (< 6 sec per scan) and accurately produce cardiovascular risk scores using PET/CT attenuation correction (CTAC) scans. The researchers trained the model using 9,543 ECG-gated CTs and tested it with ungated CTACs from 4,331 patients with major adverse cardiac events (MACE). Each CTAC-based CAC score level (0, 1-100, 101-400, and >400) was associated with increased risk of MACE within 4.3-years (HR up to 3.2), while CTAC CAC’s negative predictive values were similar to the manual CT-based CAC scores (83% & 85%).

• Envision Downgraded: Relying on leveraged finance and surprise billing was a slippery slope, and it seems to have caused Envision Healthcare to slide down to Moody’s lowest junk-level rating (C). Moody’s now ranks Envision among companies that are “typically in default, with little prospect for recovery of principal and interest.” If you’re wondering how Envision got here and what its private equity owners might do about it, we detailed those topics in April.

• AI-Assisted CTPA Peer Review: A new JACR study found that AI can improve the CTPA peer review process by reducing the radiologist labor associated with identifying missed lesions. Using 2,573 CTPA exams, an AI-based peer review system flagged 136 potentially missed liver lesions, including 13 that proved to be suspicious. This process significantly reduced the ratio of CTs that radiologists would have reviewed to spot each missed lesion (10:1 vs. 66:1).

• 2021 Burnout Levels: A study of 2.4k physicians in Mayo Clinic Proceedings revealed the unfortunate yet not too surprising information that 63% of physicians experienced burnout at least once in 2021 (up from 38% in 2020). Last year saw a 39% rise in emotional exhaustion scores and a 35% decrease in work-life balance satisfaction, although the moderate 6% increase in depression scores caused the authors to conclude that “the increase in physician distress in this interval was primarily due to increased work-related distress.”

• Breast Density Changes and BCa Risks: Women who show increases in breast density in subsequent screening mammograms could have a greater future risk of breast cancer. Among 2.2M South Korean women (22.4k w/ breast cancer), premenopausal and postmenopausal women with fatty breasts at their baseline mammogram who showed increased density by their third biennial screening also had increased future risk of breast cancer (fatty-to-dense HRs: 1.45 & 1.50). 

• Brain MRI DL Noise Reduction: New research out of Japan showed that deep learning-based reconstruction (dDLR) can improve 1.5T brain MRI image quality to the level of 3T MR images. The researchers performed 1.5T and 3T brain MRIs on 11 volunteers and enhanced the 1.5T scans using dDLR, finding that dDLR-1.5T images had significantly higher perceived image quality, signal-to-noise ratios, and contrast-to-noise ratios than the standard 1.5T MRIs, while being equivalent or even superior to the 3T images.

• Judge Greenlights UnitedHealth’s Change Acquisition: The big are getting bigger after a federal judge denied the DOJ’s attempt to block UnitedHealth Group’s $13B acquisition of Change Healthcare. UHG will be required to divest Change’s ClaimsXten service line (TPG Capital will acquire it for $2B), while Change’s imaging-related businesses remain included in the deal. If you’re interested in this story and didn’t catch our full writeup in Digital Health Wire, you’re missing out.

• CT Radiation’s Breast Cancer Risk: An Applied Radiation and Isotopes study showed that radiation exposure from chest and abdomen CTs might increase young women’s breast cancer risks. Analysis of 28 young women scanned at three Saudi Arabia hospitals found that their chest and abdomen CTs’ average effective radiation doses were far lower (7.9 & 6.6 mSv) than their average breast radiation exposure from the same exams (10.2 & 10.1 mSv), suggesting that exam protocols should be updated.

• Aidoc & Epic App Orchard: Aidoc announced that its aiOS AI platform is now available in the Epic App Orchard. Better integration with Epic is always a good thing, but this platform-to-platform integration also serves as an interesting reminder of hospitals’ diverse imaging setups, requiring AI integration beyond the PACS.

• Supercharged Cancer Moonshot: Although the US federal government’s Cancer Moonshot largely remains unchanged from its launch in February, President Biden revealed actions to “supercharge” the initiative. Updates and additions to the Cancer Moonshot include: (1) the official formation of a federal Cancer Cabinet, (2) plans to have the private sector share more cancer research data, (3) the launch of Trials.Cancer.gov, and (4) the signing of an executive order ensuring that biotechnologies invented in the US are manufactured domestically.

Annalise CXR In Action

annalise.ai’s Annalise CXR solution detects up to 124 findings in a single chest X-ray. See how it detects such a wide range of abnormalities using these demo studies…  or upload your own CXR images.

Hyperfine Images Intelligently

Hyperfine’s Swoop Portable MR Imaging System might look like hardware, but its deep learning-based image reconstruction pipeline is what makes the MRI’s point-of-care performance possible. See how Hyperfine’s reconstruction technology improves image quality, while allowing advanced gridding and denoising.

The Resource Wire

• Are you sure your imaging archive is safe and recoverable? See how Intelerad’s Cloud DR disaster recovery solution mitigates the many risks facing your archive by securely storing copies of every image.

• 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.

• Check out this patient case study showing how the Arterys Chest I MSK AI allowed radiologists at CSE in Paris to identify a fracture that was missed in three previous interpretations.

• Ready to Update Your PACS? This Novarad blog outlines the product, vendor, future-proofing, and support considerations to help make sure you select the right system.

• Find out what built for the modern world means — and why it matters — in this Aunt Minnie profile on United Imaging’s more modern approach to vertical integration, leadership, and culture.

• Is your organization ready to move enterprise imaging to the cloud? Check out this Change Healthcare and ACHE webinar detailing cloud-native imaging’s benefits, best practices, and ROI.

• This Riverain Technologies case study details how the University of Colorado Hospital enhanced its chest X-ray workflow with ClearRead Bone Suppress.

• See how Einstein Healthcare Network reduced its syringe expenses, enhanced its syringe loading, and improved its contrast documentation when it upgraded to Bayer Radiology’s MEDRAD Stellant FLEX CT Injection System.

• It’s no secret that radiologists are increasingly burned out, but there are technology-based solutions to this problem. Check out this GE Healthcare report detailing how a workload optimization engine can boost radiologists productivity and reduce burnout.

• Check out this Imaging Wire Show featuring Us2.ai’s co-founders, James Hare and Carolyn Lam MBBS, PhD, detailing Us2.ai’s unique origins, impressive capabilities, and big goals to automate echocardiography reporting across the world.

• Learn why Texas’ Baylor Scott & White Medical Center and the UK’s Queen Elizabeth Hospital Birmingham decided to upgrade their SPECT-only cameras and first-generation SPECT/CTs to Siemens Healthineers’ Symbia Pro.specta SPECT/CT and how they’ve benefited since then.

• Check out this Blackford Analysis white paper detailing how children’s hospital imaging teams can leverage AI to improve modality throughput and imaging device availability.