Fracture POCUS | Prostate PET | Cardiac US for CV19

“That’s a very high bar for an imaging study.”

Emory’s David M. Schuster, MD, who’s study found that using PET for prostate cancer planning leads to better outcomes than conventional imaging.

Know anyone who made outstanding contributions to radiology practice and outcomes this year? Nominate them for an Imaging Wire Award.

Imaging Wire Sponsors

  • Arterys – Transforming medical imaging by reducing the tedium of interpretation and empowering physicians with our web-based AI platform.
  • Bayer Radiology – Providing a portfolio of radiology products, solutions, and services that enable radiologists to get the clear answers they need.
  • 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.
  • 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.

The Imaging Wire

POCUS for Pediatric Fractures

Point-of-care ultrasound can achieve “excellent” performance diagnosing pediatric fractures in the ED, and can even match the accuracy of X-ray exams. However, POCUS’ potential role in fracture diagnosis may rely on emergency departments expanding their POCUS training. Here are some details:

  • The Study – An Italian research team measured POCUS’ diagnostic performance on 554 children with suspected fractures (43% w/ fractures), using the kids’ X-rays as the study’s baseline. They also measured accuracy based on each emergency physician’s experience / skill with point-of-care ultrasound.
  • The Results – The high-skilled physicians’ POCUS exams were far more accurate than their low-skilled colleagues, achieving much higher sensitivity (91.67% vs. 71.5%), specificity (88.89% vs. 82.91%), positive predictive values (89.19% vs. 75.90%), and negative predictive values (91.43% vs. 79.44%). They also diagnosed fractures with far greater agreement levels (Cohen κ coefficient: 0.81 vs. 0.54).
  • The Takeaway – It’s tempting to make this a “POCUS rivals X-ray” story, especially since one particularly-experienced ED physician achieved 100% sensitivity and specificity. However, like many ultrasound studies, the main takeaway is that most emergency physicians will require more training and experience (or new fracture assessment AI tools) in order for POCUS to consistently approach X-rays’ accuracy. If we can get there, POCUS’ other advantages (no radiation, faster turnaround, painless, detects soft tissue injuries) could make it a valuable part of fracture workflows in busy EDs.

Cardiac Ultrasound and COVID Mortality

A new study out of Milan and NYC found extremely high myocardial injury rates among hospitalized COVID-19 patients, while highlighting cardiac ultrasound’s role in identifying the patients with the highest mortality risks.

  • The Study – The study reviewed data from 305 patients (190 w/ myocardial injury) who underwent transthoracic echocardiographic (cardiac ultrasound) and electrocardiographic exams, comparing outcomes based on the presence of myocardial injury and ultrasound abnormalities.
  • The Results – The study revealed that 63.2% of the patients with myocardial injury also had abnormalities in their cardiac ultrasound exams, while only 25% of patients without myocardial injury had cardiac US abnormalities. The patients that had both myocardial injury and cardiac US abnormalities had far greater mortality rates (31.7%) than the patients with myocardial injury but no US abnormalities (18.6%) or patients without myocardial injury (5.2%).
  • The Takeaway – Cardiac ultrasound could play a valuable role in COVID-19 assessments and treatment planning by helping identify the extremely high-risk COVID-19 patients (those w/ myocardial injury + cardiac US abnormalities).

The Wire

  • Google & Mayo’s AI RT Initiative: Google Health and Mayo Clinic announced an initiative to enhance radiation therapy planning using AI, teaming Mayo’s RT experts (e.g. radiation oncologists, medical physicists, dosimetrists) with Google’s imaging AI experts. Mayo and Google will initially develop an algorithm to automate contouring of healthy tissue and organs from tumors, and develop adaptive dosage and treatment plans for patients with head and neck cancers. This is Mayo and Google’s first research collaboration since announcing their alliance to “transform healthcare” just over a year ago.
  • PET for Recurrent Prostate Cancer Planning: PET imaging improves prostate cancer radiation treatment outcomes by helping “pinpoint the location of the prostate cancer recurrence” during planning. That’s from a new study that used 18F PET imaging and conventional imaging (MRI, CT, bone scans) to guide radiation treatments for 165 patients with recurrent prostate cancer, finding that more 18F PET imaging patients were disease free after three years (75.5% vs. 63%) and four years (75.5% vs. 51%). PET has an established role in prostate cancer management but this is the first study showing how PET-based planning is associated with improved outcomes with recurrent cancers.
  • The Lax Radiologist: A new ACR bulletin detailed a recent malpractice case where the time a radiologist spent reading each CT image was used as evidence to suggest that the radiologist might have rushed through that patients’ scan. The ACR warned that because there’s no current reading speed standards, a case involving speed/keystroke appropriateness could come down to “expert” testimony, encouraging radiologists to educate jurors on how (and how fast) scans are read if they ever find themselves defending “lax radiologist” allegations.
  • No Fasting for CE-CTs: Having patients fast before contrast-enhanced CT exams doesn’t reduce acute adverse reactions (AARs) and might actually lead to more nausea. That’s from a new study that reviewed AARs before and after a Japanese hospital stopped requiring patients to skip a meal prior to their CE-CTs. The review found no significant changes in AARs (1.6% vs. 1.4%), vomiting (0.12% vs. 0.16%), or severe allergic reactions (0.06% vs. 0.05%), while nausea rates fell significantly after the change (0.31% to 0.18%).
  • AI Criteria: A UCSF team outlined the criteria that radiology departments should consider when deciding whether to add an imaging AI tool to their workflow. Here’s their very practical checklist: 1) Define the problem that AI might solve; 2) Decide how to evaluate AI performance (before & after implementation); 3) Involve the local IT team; 4) Determine plans to validate or fine tune local data; 5) Confirm if the system will require monitoring; 6) Calculate / analyze TCO and ROI; 7) Clarify how the AI might impact quality, safety, and healthcare disparities.
  • Thyroid Ultrasound’s CAD Benefits: A new study out of China found that an ultrasound CAD system could identify people with thyroid cancer with “outstanding” sensitivity and could be particularly valuable for less-experienced radiologists. The study reviewed ultrasound scans from 494 patients (565 thyroid nodules), finding that the US CAD system’s sensitivity matched a senior radiologist (90.51% vs. 88.47%), its AUC was on par with a junior radiologist (0.748 vs. 0.739), but its 49.63% specificity was well below each of the radiologists (75.56%, 85.93%, 90.37%). The good news is, the CAD system improved the junior radiologist’s sensitivity (72.20% to 89.93%) and AUC (0.739 to 0.816), while not significantly decreasing specificity (75.56% to 73.33%).
  • Siemens YSIO X.pree’s FDA Approval: Siemens Healthineers announced the FDA approval of its efficiency / automation-focused YSIO X.pree “intelligent X-ray system.” The YSIO X.pree is highlighted by its new myExam Companion intelligent UI (guides the acquisition process), its new myExam 3D Camera (supports patient positioning and collimation), and its smart image processing engine.
  • RadNet’s AZ Expansion: RadNet expanded to Arizona following its acquisition of AZ Tech MRI & Radiology (8 Phoenix locations) and a new outpatient joint venture with Dignity Health/CommonSpirit Health. Through the joint venture, RadNet plans to develop a wider network of Arizona outpatient imaging centers, following the company’s strategy of building-out “geographic concentration and densely clustered facilities.”
  • AB-MR Evidence Mounts: Abbreviated breast MRI’s (AB-MRI) positive 2020 continued with a new UPenn study that found the rapid breast MRI scan might be an effective supplemental screening option for women with dense breasts. The study performed AB-MRI exams on 475 asymptomatic women with dense breasts and negative/benign DBT findings, that resulted in 42 biopsy recommendations (39 biopsies completed) and 13 follow up recommendations. The biopsies revealed 12 malignancies and the follow ups led to an additional invasive cancer diagnosis (27.4 per 1k CDR), none of which were identified through the patients’ DBT exams.
  • iPhone Stroke App: Penn State and Houston Methodist Hospital researchers developed a smartphone app that can identify signs of stroke within four minutes by measuring a person’s facial movements and listening to their speech. They developed the tool using iPhone videos from 80 Houston Methodist patients with stroke symptoms, achieving 79% accuracy when tested against the same dataset, which they suggest is similar to triage in the ED.
  • Project Thumb: Volpara Health announced its new “Project Thumb” initiative, enhancing breast imaging centers’ follow-up letters with thumbnail images of women’s own mammograms and their Volpara density grades. Volpara announced its new Project Thumb initiative with Henry Mayo’s Sheila R. Veloz Breast Center and will offer this capability to other centers in an effort to make patient letters more personalized and understandable.
  • Imbio on Siemens syngo.via Platform: Siemens Healthineers will make Imbio’s AI algorithms globally available as OpenApps on Siemens’ syngo.via platform. Imbio’s chest CT analysis tools join a growing list of solutions available as syngo.via OpenApps (Circle, PIE Medical Imaging, Mint, SyntheticMR, Materialise, mediCAD).
  • Physicians Under Threat: A new AMA survey (n = 3,500 physicians in mid-July) suggests that the “viability of physician practices remains under threat” as the COVID-19 emergency brought a 32% average drop in practice revenue. In-person patient visits fell dramatically (81% of practices had fewer in-person visits in July vs. February), while almost 7 out of 10 physicians reported fewer total visits (in-person + telehealth) despite the surge in virtual appointments.

The Resource Wire

– This is sponsored content.

  • This GE Healthcare post details how its Edison Developer Program creates a development and distribution ecosystem for independent software vendors and developers.
  • Wondering what to look for in your next CT? This Hitachi blog goes beyond slice count, detailing the top three features that your next CT has to have. Here’s a hint: they will help you care for your >30% patients who are overweight.
  • The advancements of AI and 4D flow can shorten exam and segmentation times, speed up diagnosis and make clinical care more data-driven, intelligent, and patient-focused. Learn more in Arterys’ Transforming Cardiac MR whitepaper.
  • Did you tune into the Siemens Healthineers MRI Summer Webinar Series? If not, you still have the chance. The series featured 5 leading MRI experts that discussed hot topics within the magnetic resonance imaging world. Register for access to watch the webinar recordings at your own convenience.
  • This Nuance case study details how PowerShare Image Sharing helped Navicent Health cut its mammography reporting time by 38%.

You might also like

You might also like..

Select All

You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team

You're all set!