Springbok Analytics Receives $1.7m Phase II SBIR Grant from the NIH to Advance its Rotator Cuff Muscle Analysis Technology

Springbok Analytics (www.springbokanalytics.com ), a life sciences muscle analytics company, announced today that it has received a $1.7 million Phase II Small Business Innovation Research (SBIR) grant from the National Institutes of Health (NIH) to develop a commercially viable machine learning algorithm to automatically detect shoulder muscle pathology.

Springbok is building AI technology to provide a more accurate and objective scoring system for evaluating rotator cuff muscles and better predict surgical outcomes

CHARLOTTESVILLE, Va., March 5, 2024 /PRNewswire/ - Springbok Analytics (www.springbokanalytics.com), a life sciences muscle analytics company, announced today that it has received a $1.7 million Phase II Small Business Innovation Research (SBIR) grant from the National Institutes of Health (NIH) to develop a commercially viable machine learning algorithm to automatically detect shoulder muscle pathology. Alongside its research partners from the University of Virginia, the San Antonio Orthopedic Group (TSAOG), and the University of Wisconsin, Springbok is building AI technology to provide a more accurate and objective scoring system for evaluating RC muscles and better predict surgical outcomes.

“Springbok has the potential to significantly enhance how we understand, manage, and treat RC tears and improve surgical outcomes. I’m excited about its technology and the role it can play in helping surgeons make better clinical decisions,” said Andrew J. Sheean, MD, Director of the Research for Accelerated Therapeutics and Orthopaedic Rehabilitation (REACTOR) Lab, San Antonio.

RC repairs are the second most common orthopedic soft tissue surgery in the US with over 400,000 performed annually, but they remain a challenging clinical problem with a high surgical failure rate. The Goutallier classification system, used to assess muscle atrophy and fatty replacement in RC tears, is the current standard for surgical evaluation, but is highly limited due to its qualitative nature and inability to predict surgical outcomes. Researchers have shown that quantitative 3D measures of atrophy and fatty replacement are better predictors of surgical outcomes, but these methods have not been clinically accessible because of the long processing time and reliance on specialized research MRI methods. Springbok’s technology overcomes these two challenges through the use of AI and innovative analysis methods, described in recent studies in Radiology: Artificial Intelligence and Scientific Reports.

“We are excited to commence Phase II after successfully developing and validating our deep-learning-based algorithm for automated quantification of rotator cuff muscle and fatty infiltration from clinical scans,” said Lara Riem, PhD and Springbok’s Director of AI and Data Science. “In creating an extensive digital database of both healthy and pathological rotator cuff clinical scans in Phase I, we developed a novel method to account for variability in scan coverage, which led to the establishment of key muscle metrics that can be derived precisely and automatically, at scale, from MR images.”

Leveraging its proprietary muscle analytics, Springbok’s AI technology produces an enhanced RC analysis from standard MRIs that are acquired within the clinical workflow. Its 3D volumetric measurement provides a more comprehensive and sensitive assessment of RC pathology, and the output is a simple, objective, and actionable report available to both providers and patients for an improved surgical decision-making process.

“To obtain a proper treatment plan and avoid poor surgical outcomes and possible retears, it is critical to better understand a patient’s rotator cuff musculature in 3D and objectively measure both muscle atrophy and fat infiltration,” said Silvia Blemker, PhD and Springbok’s Co-Founder and Chief Science Officer. “Phase I demonstrated implementation viability of our new analysis, proving it was both valuable and practical within the clinical setting. Our goal with this next phase is to continue product development in the pursuit of an automatic rotator cuff segmentation and analysis technology that can benefit millions of patients and improve upon the subjective scoring standard used today.”

Completing Phase II will enable Springbok to apply for FDA 510(k) market clearance, with the aim to significantly improve the accuracy of shoulder pathology assessments, the diagnosis and treatment of shoulder injuries, and the outcomes of costly orthopedic procedures, potentially even eliminating unnecessary surgeries. “Our ultimate goal at Springbok Analytics is to become the standard for how we understand human musculature and improve clinical diagnosis, injury management and human performance through innovative, AI-based technologies,” concluded Blemker.

About Springbok Analytics:

Springbok is a life sciences muscle analytics company that drives better health and performance outcomes.

Its technology analyzes MRI data and creates personalized 3D visualizations of muscle health, enhancing the assessment, treatment monitoring, research and diagnostic value of advanced imaging. Springbok’s rapid imaging sequence and AI-based analysis reveals a complete view of musculoskeletal health, precisely quantified individual muscle volume and quality, fat infiltration, left-right asymmetries, as well as scar tissue, edema, and tendon morphology.

To learn more about how Springbok is creating a better view of health, please visit www.springbokanalytics.com.

Cision View original content:https://www.prnewswire.com/news-releases/springbok-analytics-receives-1-7m-phase-ii-sbir-grant-from-the-nih-to-advance-its-rotator-cuff-muscle-analysis-technology-302078954.html

SOURCE Springbok Analytics

MORE ON THIS TOPIC