Researchers at Florida Atlantic University’s College of Engineering and Computer Science, in collaboration with the Marcus Neuroscience Institute at Boca Raton Regional Hospital, part of Baptist Health, have developed a new artificial intelligence-based method to model the lumbar spine. This innovation could improve how doctors diagnose and treat lower back pain.
Lower back pain is a common problem in the United States, with nearly 30 percent of adults experiencing it within any three-month period. It is one of the leading causes of disability globally and often results in chronic discomfort and missed work.
The research team created a fully automated pipeline for finite element analysis tailored to lumbar spine modeling. By combining deep learning tools such as nnUNet and MONAI with biomechanical simulators like GIBBON and FEBio, they reduced the time needed to prepare lumbar spine models by almost 98 percent—from more than 24 hours to just over half an hour—without sacrificing accuracy.
According to Maohua Lin, Ph.D., corresponding author and research assistant professor at FAU’s Department of Biomedical Engineering: “What sets our approach apart is its ability to automatically convert standard medical images like CT or MRI scans into highly accurate, patient-specific spine models. Traditional manual methods require complex geometry processing, meshing and finite element simulation setup, making them not only time-intensive but also highly dependent on the operator’s expertise. Our automated pipeline significantly reduces the time required, cutting what once took several hours or even days down to just minutes.”
The new system can quickly create virtual spines that respond realistically during simulations involving bending or stretching. This allows for rapid patient-specific simulations that support preoperative planning, spinal implant optimization, and early detection of degenerative conditions.
Frank D. Vrionis, M.D., chief of neurosurgery at Marcus Neuroscience Institute and corresponding author on the study said: “Beyond advancing research, automated lumbar spine modeling plays a critical role in preoperative planning. This technology quickly generates patient-specific models to predict mechanical complications, optimize implant design and reduce surgical risks. By removing manual steps, it also improves speed and consistency, helping clinicians make more informed decisions.”
The researchers used advanced AI methods to identify key spinal components from medical scans before building detailed 3D models including bones, cartilage and ligaments. They then ran computer simulations showing how stress builds up during movement.
This study expands on previous work published by the group in journals such as Artificial Intelligence Review and North American Spine Society Journal on AI-driven biomechanical modeling techniques.
Stella Batalama, Ph.D., dean of FAU’s College of Engineering and Computer Science commented: “This groundbreaking work exemplifies the game-changing power of uniting engineering and medicine to address complex health care challenges. FAU and Baptist Health researchers are not only pushing the boundaries of innovation, they are also delivering real-world solutions that can improve patient outcomes and redefine spine care.”
Funding for this research came from Boca Raton Regional Hospital (Baptist Health), Helene and Stephen Weicholz Foundation; National Science Foundation; pilot grants from FAU’s College of Engineering & Computer Science; FAU Stiles-Nicholson Brain Institute; FAU Center for Smart Health; as well as the FAU Sensing Institute.
