Data Show New AI Approach Enhances Osteoporosis Diagnosis, Monitoring

Medimaps Group is touting results showing its new spine segmentation (SpS) deep learning algorithm may be a reliable, time-efficient tool to enhance patient monitoring and osteoporosis diagnosis. The SpS algorithm has been designed to enhance bone measurement accuracy on dual energy X-ray absorptiometry (DXA) lumbar spine (LS) scans with potential application in X-ray based imaging systems. 
 
“Our main aim is to bring clinically-driven innovations to radiologists that increase efficiency by reducing technical errors, save time and augment productivity,” said Medimaps Group Co-Founder/CEO Prof. Didier Hans, head of the R&D Bone Diseases Center at Lausanne University Hospital in Switzerland. “Our data show, for the first time, the efficacy of an algorithm to assess lumbar spine segmentation on DXA scans to enable better screening for osteoporosis. Based on these results, we have moved this algorithm into further development stage, and look forward to submitting our next-generation product for regulatory approval later this year.”
 
The results¹ were obtained from a study using Medimaps Group’s SpS deep learning algorithm on thousands of scans from the OsteoLaus cohort and evaluated on an independent test set. Results showed a significant improvement for the measured bone mineral density (BMD), trabecular bone score (TBS) and surface compared to the machine default bone mask, and similar results as obtained from a human expert bone mask.
 
According to the International Osteoporosis Foundation (IOF), osteoporosis causes more than 8.9 million fractures globally every year, resulting in an osteoporosis fracture every three seconds. One in five men and one in three women will be affected by this disease in their lifetime. This suggests that approximately 500 million men and women worldwide may be affected by osteoporosis annually.²
 
“The volume of patients requiring scanning is steadily increasing in the radiology practice, therefore computerized tools such as the spine segmentation algorithm embedded into the TBS Osteo software represent a way forward to optimize the workflow while improving clinical patient management. This best-in class software has proven to be a precious aid in our clinical routine to detect more cases of osteoporosis, and to improve patients bone health prognostic reliably, ” said Prof. Giuseppe Guglielmi, Foggia University School of Medicine and Dimiccoli Teaching Hospital in Barletta, Italy, and former president of the European Society of Musculoskeletal Radiology (ESSR).
 
TBS Osteo is a software product used by radiologists to monitor bone health. The software calculates TBS, an index of the bone microarchitecture and a BMD-independent bone fracture risk predictor. The use of TBS is proven to help identify approximately 30%³ more patients at risk of fracture compared to BMD alone, without additional examination time nor radiation.
 
Medimaps Group’s imaging software TBS Osteo has received regulatory approval and benefits from reimbursement in the United States and certain European countries. It is commercially available in 60 markets worldwide.
 
Medimaps Group’s medical imaging software applications, based on patented multi-purpose technology with artificial intelligence capabilities, provide healthcare solutions that fit seamlessly into workflows. TBS iNsight (Osteo) has been used for years in clinical practice worldwide in osteoporosis. It has become the new gold standard for bone texture assessment in routine clinical practice. TBS has gained international recognition with more than 900 peer-reviewed scientific publications and is included in many guidelines and used by more than 30,000 physicians worldwide including leading healthcare institutions. 
 
References
¹ Gatineau G. et al, Evaluation of a deep learning spine segmentation (SpS) algorithm for accurate and reproducible monitoring of lumbar spine DXA scans, Poster #C-24875, ECR 2023.
² Facts & Statistics: epidemiology of osteoporosis and fragility fractures, IOF, https://www.osteoporosis.foundation/facts-statistics/epidemiology-of-osteoporosis-and-fragility-fractures, last accessed, February 22, 2023
³ Hans D, Goertzen AL, Krieg MA, Leslie WD. Bone microarchitecture assessed by TBS predicts osteoporotic fractures independent of bone density: the Manitoba study. J Bone Miner Res. 2011 Nov;26(11):2762-9. doi: 10.1002/jbmr.499. PMID: 21887701.