“If you think of the automobile industry, there’s a sea change from internal combustion to electric vehicles. CT is in a similar situation,”
Redlen Technologies CEO, Glenn Bindley, on CT’s upcoming photon-counting tech sea change.
Imaging Wire Sponsors
Arterys | Bayer Radiology | Blackford Analysis
Canon Medical Systems | Fujifilm Healthcare Americas
GE Healthcare | Novarad | Nuance
Riverain Technologies | Siemens Healthineers
United Imaging | Zebra Medical Vision
The Imaging Wire
Volpara’s Lung Cancer Push
Breast imaging AI leader Volpara Health took a big step into the lung cancer AI segment last week, launching partnerships with Riverain Technologies and RevealDx. Here are some details.
Volpara & Riverain – Volpara and Riverain announced plans to integrate Riverain ClearRead CT (AI-based lung nodule detection) and the Volpara Lung platform (lung cancer screening reporting, tracking, and risk assessment), giving Volpara a market-leading detection partner and extending the clinical value of both tools.
Volpara & RevealDx – Within days, Volpara announced a $250k strategic investment in AI-based lung nodule diagnosis startup RevealDx, that will allow Volpara to sell RevealDx’s RevealAI-Lung tool (CE-marked, FDA pending) in the US and make Volpara its exclusive distributor in Australia / New Zealand.
Not That Surprising – Volpara’s lung cancer screening expansion isn’t as surprising as some might think. Volpara first entered the lung cancer screening segment through its 2019 acquisition of MRS Systems, which likely targeted MRS’ breast cancer screening management software but also included its lung cancer screening platform (used w/ 8% of US LC screenings). Volpara also built its business around supporting population-scale cancer screening workflows and it has a long history of complementary partnerships within its breast imaging business.
The Takeaway – Lung cancer screening volumes are about to significantly increase in the US (and potentially globally), creating new bandwidth and workflow constraints, and driving demand for comprehensive solutions that support the entire screening and patient management pathway. With these alliances, Volpara, Riverain, and RevealDx are far better positioned to support that pathway.
Dual Source CT Making a Difference
Dynamic imaging on Dual Source CT can help you provide more confident, precise, and accurate answers. Download Siemens Healthineers’ clinical case collection to see powerful examples where functional imaging with DSCT is making a difference.
Validating ClearRead CT
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.
- A Federated Milestone: AI insiders are celebrating the latest evidence of federated learning’s ability to increase AI robustness and generalizability. The MGH-led study used federated learning to train an AI model (w/ 16k patients’ CXRs and vitals/data from 20 hospitals on 5 continents) to predict when COVID patients would require oxygen. The AI model was able to predict oxygen timing with a 0.92 AUC, representing a 16% improvement versus models trained/tested with the hospitals’ own internal data and a 38% generalizability improvement compared to models trained with one hospital’s internal data and tested against data from all hospitals.
- Cancel Culture: The US CMS revealed plans to repeal the Medicare Coverage of Innovative Technology (MCIT) program before it goes live in December, prompting pushback from medtech lobbyists. The MCIT program would have given “breakthrough” devices nationwide Medicare coverage at the same time as their FDA approval, but has faced consistent objections from the new CMS administration due to a range of concerns (e.g. lacking evidence requirements, unclear relevance to Medicare populations, CMS can’t rescind coverage).
- PCP Risk Communication Drives Screening: A new JAMA Open study (n = 188) found that providing women with their personal breast cancer risk scores during their annual primary care visits improves screening adherence, and could reduce breast cancer’s racial disparities. The population-based and PCP-driven approach drove a “nonsignificant increase” in overall mammography adherence (39% to 49%), but a significant increase among high-risk women (37% to 51%).
- ARA, an RP Company: It appears that the Alaska practice that Radiology Partners was rumored to be acquiring is Alaska Radiology Associates (ARA), previously the state’s largest independent rad practice. ARA has about 18 radiologists, a full suite of services (diagnostic, IR, telerad), and operates multiple imaging centers.
- Bone Tumor DL: A new Radiology Journal study detailed a deep learning model trained to locate, segment, and classify primary tumors on radiographs. Against an external test set (n = 111 patients), the model classified bone tumors as malignant or benign with 80.2% accuracy, better than radiology residents and comparable to MSK specialists (radres: 64.9% & 71.2%, MSKs: 82.9% & 83.8%). The model also relatively accurately placed bounding boxes around the tumors (82% of tumors) and segmented them (Dice score: 0.60).
- Prime Time Imaging: The BBC is about to bring medical imaging into UK living rooms, revealing plans to broadcast a new television show that takes participating patients and viewers “on an emotional journey deep inside the human body.” Tentatively entitled “Doctor, Can You See Me Now?,” the series uses medical imaging and augmented reality to allow patients to better understand their medical conditions and treatment choices.
- A SM+DBT & FFDM+DBT Disagreement: MD Anderson researchers revealed that SM+DBT and FFDM+DBT mammography exams recall different patients for breast calcifications, potentially influencing cancer detection performance. A review of 1,022 patients’ exams found that FFDM+DBT and SM+DBT had similar recall rates (7.8 vs. 6.8 per 1k) and cancer detection rates (7.8 vs. 6.8 per 1k). However, among the 19 patients recalled by only one of the methods, 13 were for calcifications (6 only via SM+DBT, 7 only via FFDM+DBT), suggesting that the exams show calcifications differently.
- Koios & GE’s ABUS Integration: Koios Medical announced that its Koios DS Breast decision software is now available on GE Healthcare’s Invenia 2.0 Automated Breast Ultrasound (ABUS) system. GE Healthcare already supports Koios DS Breast across its other ultrasound and PACS systems, and this is a logical addition given the Invenia ABUS’ specific focus on breast imaging and dense breast exams. It’s also another reminder of how focused GE Healthcare seems to be on adding AI across its ultrasound portfolio.
- Another Case for Centralized Screening: When lung cancer screening participants are managed within centralized programs, they are more likely to meet LCS eligibility criteria and return for future annual screenings. That’s from a new Chest Journal study (n = 1,117 patients) that found decentralized programs were responsible for 90% of the ineligible patients (190 of 211) and centralized programs had far higher future screening adherence rates (70% vs. 41% decentralized). This follows a similar JAMA study detailing centralized programs’ higher screening adherence rates (46% vs. 35%).
- Overnight Hikes: Radiology Twitter and the Aunt Minnie message boards lit up last week after “The largest provider of teleradiology services” (reportedly vRad) notified its clients that it plans to increase overnight telerad fees by 40%. Radiologist comments revealed a general lack of surprise given vRad/RP’s strong Telerad position and the tight labor market, while some suggested that this move will result in more practices and radiology departments bringing overnight reads in-house.
- Collateral Flow AI: University at Buffalo researchers developed an AI algorithm that can accurately and efficiently assess acute ischemic stroke (AIS) patients, helping determine their eligibility for reperfusion therapy. The algorithm analyzed blood vessels in AIS patients’ CTP scans to measure collateral flow filling, classifying dichotomized collateral scores (≥50% or <50% collateral filling) with 85% accuracy and classifying multiclass collateral scores (0% filling, 0%–50% filling, 50%–100% filling, or 100% filling) with 80% accuracy. A method like this could improve an important process that’s currently difficult and labor intensive.
- MRI Online & I-MED: MRI Online transitioned from a B2C radiology training company to a B2B company, launching a new partnership with heavyweight Australian radiology practice, I-MED Radiology Network (355 rads, 266 clinics). MRI Online will develop I-MED’s new Junior Consultant Pathway (1yr subspecialty training for new radiology hires) and make the MRI Online platform available to all radiologists in the I-MED network.
How to Ditch the Disk
CD burning issues? Check out this one-minute video showing how Novarad’s CryptoChart image sharing solution allows patients to easily access and share their medical images using personalized, highly secure QR codes (not CDs).
The Resource Wire
- Attainable Intelligence. Simply Masterful. See how United Imaging’s forthcoming uCT Atlas combines breakthrough technology and design to allow you to conduct your masterpiece.
- Some small imaging centers haven’t been getting a fair chance with AI – here’s how GE Healthcare plans to change that.
- Learn how the University of Oxford increased its vertebral compression fracture detection rate from 50% to 90% using Zebra Medical Vision’s bone health solution.
- It’s clear that structured reporting is a must for CVIS platforms, but they aren’t all created equal. This Fujifilm Healthcare article reveals what physicians and sonographers view as the “non-negotiable” CVIS structured reporting features.
- Check out this UCSD lung nodule detection study detailing how Arterys Lung AI drove a “clinically meaningful and statistically significant increase in sensitivity,” without changing reading time.
- See Ochsner Lafayette General’s Director of Radiology, Emily Broussard, describe their “seamless” transition to Nuance PowerScribe One and how its improved their reporting efficiency and quality.
- Adopting a platform strategy can simplify the deployment and management of imaging applications and AI algorithms, but there’s a lot to consider. In this eBook, Blackford Analysis and its clients detail how AI platforms can benefit clinical and IT teams, and share guidelines to consider when selecting a platform.
- With radiation dose management now largely considered best practice, this Bayer white paper details the top five benefits of adopting contrast dose management.
- This presentation from Dr. Brian Goldner, MD details UC Davis Sacramento’s experience with Canon’s Ultra High Resolution CT and how it can be applied to cardiothoracic interpretations.