fbpx

Plain-Film Solution | Non-Rad AI | Tech MBSS

“if you can’t get ahold of radiology just start ordering random scans. we will call you so damn fast . . .

Twitter post from radiologist and excellent follow, Dr. Shadowgazer.



Imaging Wire Sponsors

  • Arterys – Reinventing imaging so you can practice better and faster.
  • Bayer Radiology – Providing a portfolio of radiology products, solutions, and services that enable radiologists to get the clear answers they need.
  • Canon Medical Systems – Delivering innovative imaging solutions and services through industry leading partnerships to improve the quality of life for all people.
  • GE Healthcare – Enabling clinicians to make faster, more informed decisions through intelligent devices, data analytics, applications and services.
  • Healthcare Administrative Partners – Empowering radiology groups through expert revenue cycle management, clinical analytics, practice support, and specialized coding.
  • Hitachi Healthcare Americas – Delivering best in class medical imaging technologies and value-based reporting.
  • Novarad – Transformational imaging technologies that empower hospitals and clinicians to deliver clinical, operational and fiscal excellence.
  • Nuance – AI and cloud-powered technology solutions to help radiologists stay focused, move quickly, and work smarter.
  • Riverain Technologies – Offering artificial intelligence tools dedicated to the early, efficient detection of lung disease.
  • Siemens Healthineers – Shaping the digital transformation of imaging to improve patient care.
  • United Imaging – Our mission, Equal Healthcare for All, pushes us beyond conventional boundaries to help clinicians expand modern, digital, intelligent care to more people within their communities.
  • Zebra Medical Vision – Transforming patient care with the power of AI.



The Imaging Wire


TCH’s Plain-Film Solution

The Texas Children’s Hospital (TCH) radiology department discovered that it had a “plain-film problem” after the hospital’s 2016-2018 expansions drove a 17% overall image volume increase and a 22% spike in daytime X-rays (vs. +12%-13% for US/CT/MR). Here’s how TCH later discovered its plain-film solution.

  • The Plain-Film Problem – TCH’s daytime X-ray surge was a poor fit for its highly subspecialized structure, leading to X-ray backlogs and regular “Hail Mary” efforts to “when the list felt out of control.”
  • Carrot-and-Stick Attempts – TCH tried various X-ray reading mandates and incentives (annual bonuses, public study counts, time-off penalties), but these attempts weren’t effective.
  • The Plain-Film Solution – After that experience, TCH decided to change how its interpretations are assigned. They developed a Nuance-based workflow distribution process that automatically distributed unread X-rays across radiologist worklists twice daily (up to 20 per worklist and shift), effectively “nudging” them to help the department avoid X-ray backlogs.
  • The Results – The new solution improved TCH’s X-ray turnaround times (avg: 43 to 41 minutes), reduced its X-ray interpretation variability per rotation (avg: -35%), and perhaps most importantly eliminated the “plain-film problem” from its monthly meeting agendas. It also earned the leader of this initiative, Marla B.K. Sammer, MD, The Imaging Wire’s 2020 Burnout Fighter Award.

The Wire

  • Non-Rad AI: We hear a lot about AI’s ability to augment radiologists, but a recent Qure.ai blog just reminded us that this is a very first world AI perspective. Qure.ai detailed how the integration of its qER stroke detection solution at a hospital in India’s Himalayan foothills shortened their stroke detection times by notifying the hospital’s non-radiologist staff of critical cases (including by mobile phone) much faster than their typical teleradiology turnaround times (1-2 minutes vs. 15-60 minutes).
  • Kidney Cancer’s Brain Cancer Link: Performing brain scans on patients with advanced kidney cancer could help identify asymptomatic brain cancers, which is a common area of disease progression among these patients but rarely evaluated before symptoms emerge. That’s from a new JNCCN-published study that reviewed data from 1,689 patients with kidney cancer who underwent baseline brain imaging at the start of a clinical trial and found that 72 (4.3%) had undetected brain metastases.
  • Exa Update: Konica Minolta updated its Exa PACS/RIS Platform, adding a number of new scheduling and billing-focused features, and making a handful of third-party integration and security updates. Most notable among the Exa updates is a new resource-based scheduling feature that allows imaging sites to schedule specific exams based on the availability of their appropriate radiologists and technologists.
  • AI Will Still Be Regulated: The HHS officially rejected a proposal that would have exempted a wide range of healthcare devices from FDA premarket approvals, including key imaging AI categories. The now-rejected proposal was part of a wave of anti-regulatory moves during Alex Azar’s final weeks atop the HHS that was followed by strong opposition from the major imaging societies (ACR, RSNA, SIIM).
  • Canon & RaySearch Expand: Canon Medical Systems USA and RaySearch Laboratories AB expanded their partnership, allowing RaySearch to distribute Canon’s Aquilion Large Bore CT and Celesteion PET/CT as part of their integrated radiation oncology systems. The companies first began working together 2+ years ago, combining Canon’s imaging systems with RaySearch’s RayStation treatment planning software, but the alliance didn’t allow RaySearch to independently offer the scanners before now.
  • The Case for Tech-Led MBSS: When Saskatoon’s Royal University Hospital started relying on technologists to perform modified barium swallow studies (MBSS) without radiologist supervision, their MBBS exams were safer and “non inferior,” but created new radiology reporting inefficiencies. That’s from a new study from this week’s ARRS 2021 meeting comparing the 6 months before and after MBBS’ policy change (n = 106 & 119), finding that it led to a drop in non-diagnostic images (6.5 vs. 4.5 per study) and didn’t affect other key metrics (e.g. fluoro time, number of images), but led to significantly longer report generation times (126 minutes vs. 942 minutes avg.).
  • Imageens’ €1.2M: French AI startup Imageens completed a €1.2M Seed round that it will use to fund the development and commercialization of its ArtFun+ AI product (measures arterial stiffness in MRIs) and its LABEL dataset preparation solution (automatically classifies and valorizes medical imaging data).
  • What’s Wrong With PACS: PACS is an important part of clinician workflows, but it’s also the source of considerable frustration, in part because many users aren’t comfortable with their PACS. That’s the main takeaway from a new Journal of Digital Imaging study that interviewed 35 hospital-based healthcare professionals (mainly in Ireland, most used PACS 6+ times / day). The majority of respondents only use basic PACS features, view the software as difficult (slow, too many clicks, too much searching), and believe they need more training.
  • CXR for COVID Outcomes: A new study presented at the ARRS 2021 meeting detailed a chest X-ray scoring system (0-24 points, based on severity/extent in CXRs) that can accurately predict COVID patient outcomes at the time of admission. The researchers applied the scoring system to 240 patients, finding that the CXR scores accurately predicted death, intubation, and the need for chronic renal replacement therapy (Odds Ratios: 1.17, 1.15, 1.14). They also found that radiologists with different experience levels were able to effectively produce the scores.
  • Radiologist Pay Still High, But Down: According to a new Medscape survey (n = 18k physicians), radiologists remained among the top-earning specialists in 2020 (-3% to $413k avg.), trailing only plastic surgeons ($526k), orthopedic surgeons ($511k), cardiologists ($459k), urologists ($427), and otolaryngologists ($417k). The fact that radiologist salaries only fell by 3% amid widespread COVID volume declines might surprise some, but most other specialties either posted flat or higher average incomes in 2020.
  • LDCT Cardiac Screening: A new Radiology: Cardiothoracic Imaging study detailed a low-dose CT-based deep learning model that’s able to accurately and quickly predict cardiovascular disease (CVD) mortality, suggesting that LDCT lung cancer screenings could also be used to screen for CVD. The model (trained w/ 4,451 screenings; tested w/ 1,113) analyzed six location-specific arterial calcium scores to accurately predict 5-year mortality in less than half a second (0.74 AUC). The LDCT-based model outperformed a CVD prediction model based on patient-reported data (e.g. smoking history & age; 0.69 AUC), while the two models combined to predict CVD mortality with even greater accuracy (0.76 AUC).
  • Transparency Enforcement: Now that it’s clear many hospitals aren’t complying with the U.S.’ new federal cost transparency rules (including rules for ~13 imaging exams), U.S. Congressional leaders are asking HHS to ramp up its compliance monitoring (e.g. audits) and enforcement (fines).
  • RamSoft & PatientPal: RamSoft will offer PatientPal’s front-desk automation software with its PowerServer RIS/PACS, allowing RamSoft’s imaging center clients to automate much of their patient coordination work after scheduling takes place (intake forms, appointment reminders, insurance verification, and payment calculation / collection).



The Resource Wire

– This is sponsored content.

  • The Saint Joseph Mercy Health System doubled its follow-up recommendation identification/tracking when it adopted Nuance PowerScribe Follow-up Manager, achieving ROI within the first year. Find out how in this Nuance case study.
  • Check out this Imaging Wire Q&A, where Arterys CEO John Axerio-Cilies, PhD discusses medical imaging’s AI and cloud evolution and how Arterys works with its Center of Excellence partners to make AI real.
  • This Hitachi blog details how a complete CVIS solution drives efficiencies and increases productivity.
  • It says a lot when a solution works so well for a radiology department that they decide to perform a study to quantify its benefits. In this Imaging Wire Q&A, University Hospital of Zurich’s Thomas Frauenfelder discusses his experience and study on Riverain Technologies ClearRead CT.
  • With a post-COVID surge in orthopedic surgery looming, this Zebra Med blog details how its 3D imaging orthopedic solution can help surgeons improve their preoperative efficiencies.
  • United Imaging took another step in its growth strategy last week, announcing its first U.S. channel partnerships with Radon Medical Imaging (mid-Atlantic), Imaging Solutions (mid & northern U.S.), and Medimax (Puerto Rico).
  • With the gap between AI interest and AI adoption becoming increasingly clear, this GE Healthcare post details how AI startups can bridge that gap.
  • CMS continues to modify the Quality Payment Program (QPP) and MIPS policies due to the COVID-19 public health emergency, but the changes and their timelines can be hard to manage. Check out this Healthcare Administrative Partners post detailing how radiology QPP and MIPS policies have changed and how radiology practices should react.