- Tomorrow's Dose
- Posts
- Edition 2 - AI in Healthcare: Waze for Patient Care, Imaging Innovations & More
Edition 2 - AI in Healthcare: Waze for Patient Care, Imaging Innovations & More
Explore AI-driven patient scheduling, the role of children in medical imaging, and the next-gen SAM 2 model.
SAM 2: The next generation of Meta Segment Anything Model for videos and images
Mayo Clinic is the leader of pack in AI Readiness
Waze for healthcare developed
Why children and young people are ‘critical’ to AI in medical imaging
Featured follow of the week
Top posts of the week across social
Meet the editor
Want a featured article?
Specialty: All // Sub-Specialty: AI // Body Site: All
1. SAM 2: The next generation of Meta Segment Anything Model for videos and images:
Following up on the success of the Meta Segment Anything Model (SAM) for images, SAM 2 has been released, which is a unified model for real-time promptable object segmentation in images and videos. The code and model weights have been made open-source, with a permissive Apache 2.0 license. The SA-V dataset, which includes approximately 51,000 real-world videos and more than 600,000 masklets (spatio-temporal masks), has been shared. SAM 2 can segment any object in any video or image—even for objects and visual domains it has not seen previously, enabling a diverse range of use cases without custom adaptation.
Read Full Article
Paul’s Thoughts:
SAM 2 is potentially a real game-changer in the world of computer vision and there are many potential applications in the world of medicine. For instance, it could be used to monitor patient motion in radiation therapy (where the patient must lie still). Surface guided radiotherapy is very commonly applied for this purpose, but it requires dedicated equipment and software. Computer vision advances such as this could allow monitoring of the patient position using standard cameras, which could make it more accessible to more centres and raise the standard of care worldwide. It remains to be seen whether the speed of segmentation is sufficiently fast to allow for real-time beam gating, however. Additional applications could be to segment 4D imaging techniques such as CT and CBCT, allowing for tumour or marker tracking and beam adaptation.
Timescale: Early | 3 Years
Specialty: All // Sub-Specialty: AI // Body Site: All
2. Mayo Clinic is the leader of pack in AI Readiness:
CB Insights has assessed how prepared US health systems are to adopt and respond to evolving AI technologies, and has determined that Mayo Clinic is the leader in this regard. The Hospital AI Readiness Index was scored according to two key pillars: innovation and execution. Mayo demonstrated a strong innovative nature, with over 50 patents filed across areas such as cardiovascular health and oncology. Execution scores are based on data including AI-related business relationships, and Mayo teamed up with Techcyte to develop a platform that will help healthcare organisations harness AI their pathology practices.
Read Full Article
Paul’s Thoughts:
As AI embeds itself in the world of healthcare it is very logical that we will start to see more assessments of AI-readiness in healthcare, beyong the US. As well as demonstrating the innovative nature of the given centre, the metrics employed for ranking could be used as a guide for hospitals to direct their efforts.
Timescale: Acute | 1 Year
Specialty: Oncology // Sub-Specialty: Scheduling // Body Site: All
3. Waze for healthcare developed:
Gray Oncology Solutions, with roots from McGill and Polytechnique, has developed an AI-powered solution that optimises patient scheduling in the oncology pathway. Not only does the solution optimise patient scheduling, minimising gaps and reducing staff stress, it offers up-to-date information for patients.
Read Full Article
Paul’s Thoughts:
Going through cancer treatments is very stressful, which is exasperated by the waiting and 'not knowing'. Knowledge that your case is moving, in the background, is empowering for the patient. One of the grand aims of the portal being built is to allow patients to track medical procedures and know which professional is working on which part of their case, like tracking the progress of a parcel.
Timescale: Early | 2 Years
Specialty: Radiology // Sub-Specialty: Outreach // Body Site: All
4. Why children and young people are ‘critical’ to AI in medical imaging:
Researchers publicised a national online survey to UK schools, universities and charities partners. A total of 171 people responded to the survey, with ages ranging from 6 to 23 years, and from across all four UK nations. Most respondents agreed or strongly agreed they wanted to know the accuracy of an AI tool that was being used (122/171, 71.3%), that accuracy was more important than speed (113/171, 66.1%), and that AI should be used with human oversight (110/171, 64.3%). Many respondents (73/171, 42.7%) felt AI would be more accurate at finding problems on bone X-rays than humans, with almost all respondents who had sustained a missed fracture strongly agreeing with that sentiment (12/14, 85.7%).
Read Full Article
Paul’s Thoughts:
Paediatric patients’ voices are often overlooked in AI tool design and development, despite them being key stakeholders for their deployment in imaging, this study has found. It is “critical” that the views of children and young people on AI in modern healthcare and imaging are heard.
Timescale: Acute | 1 Year
A round-up of some of the best posts we found online this week.
Was this email forwarded to you?
Our weekly email brings you the latest health trends and insights, combining top news and opinions into a straightforward, digestible format.
 |  |  |
Want an article featured?
Have an insightful link or story about the future of medical health? Reach out below, and we may include it in a future release.
Reply