Patient-matched surgical plans and instruments are intended to offer advantages such as improved precision, enhanced outcomes, increased efficiency, minimized risks, and reduced costs in many orthopedic procedures. Technologies such as 3D printing, robotics, and augmented or virtual reality have redefined surgical procedures, enabling highly precise and personalized interventions that address the unique requirements of individual patients. The integration of deep learning and artificial intelligence (AI) algorithms into patient data processing is enabling faster design and development of patient-matched implants and instrumentation. Advanced preoperative planning portals are consolidating previously isolated processes while improving visualization and communication among surgeons and engineers. The ability to automate and streamline personalization workflows can help translate virtual surgery into the OR, improve surgical outcomes,^1,2 and elevate the patient experience.

Historically, most orthopedic pre-surgical planning workflows rely on volumetric imaging data created by computed tomography (CT) or magnetic resonance imaging (MRI). CT imaging is the preferred modality for medical professionals seeking to diagnose and treat complex diseases as they can deliver detailed, cross-sectional images of hard tissues such as bone. While CT imaging is a valuable tool, it has several drawbacks related to patient radiation exposure, time, and cost. Recent innovations in machine learning technologies have now unlocked the ability to leverage patient X-ray images as input to pre-surgical planning workflows. This has several advantages such as efficient and cost-effective imaging data acquisition since X-ray machines are widely available, including in non-acute care clinics and offices and require less infrastructure and capital expense. Additionally, radiation exposure with X-ray imaging is typically a fraction of the radiation dose delivered with most CT protocols.

Once the patient images are obtained, advanced 3D imaging software extracts the relevant anatomical structures. With CT imaging and traditional segmentation software applications, this extraction process requires a significant amount of labor. In manual segmentation workflows, highly trained professionals identify and outline the anatomies of interest, typically on each slice of a volumetric data set and occasionally with the help of semi-automated algorithms. Now, FDA-cleared solutions are available that use AI to convert patient bi-planar X-ray images into detailed 3D representations of the patient. Advanced algorithms then go to work to generate preoperative surgical plans that can be reviewed by the clinical team, and then, once approved, output the anatomic models, patient-matched surgical instrumentation, and even patient-matched implant designs that help the clinical team translate the digital surgical plan into the operating room. The result is a truly personalized patient treatment delivered from a highly streamlined and efficient workflow.

It’s encouraging to see these technologies are already gaining traction. At the Orthopedic Summit (OSET) held in September 2024, Dr. Matt Barber showcased a system developed by Enhatch for United Orthopedic Corporation U2 Total Knee Arthroplasty that uses 2D X-rays to design patient-specific guides that are produced using 3D printing technology. Dr. Barber commented, “This allows pre-planned implant fit and alignment to be achieved with great accuracy.” He went on to explain that he was able to accomplish all five resections of the distal femur with a single guide. He added, “This is truly accurate, efficient surgery in a streamlined package. No CT scan or MRI, no peer-to-peer calls, or denial of coverage from insurance providers.”

While X-rays are considered the oldest form of medical imaging, they are demonstrating value in driving efficient, effective patient-specific surgical plans and guides. Through the use of deep learning and AI, it’s now possible to derive tremendous value from X-rays as the foundation of surgical planning. When combined with technologies such as AR/VR and 3D printing, it’s possible to achieve interventions that meet the unique needs of each patient. Indeed, X-rays are shining a light on the future of surgery, illuminating a path toward more personalized and effective care.

References

¹ Hirsch DL, Garfein ES, Christensen AM, Weimer KA, Saadeh PB, Levine JP: Use of computer-aided design and computer-aided manufacturing to product orthognathically ideal surgical outcomes: a paradigm shift in head and neck reconstruction. J Oral Maxillofac Surg 67:2115-2122, 2009.

² McCormick S, Drew S: Virtual model surgery for efficient planning and surgical performance. J Oral Maxillofac Surg 69:638-644, 2011. 

Ben Johnson’s career spans more than two decades focused on the development and commercialization of innovative medical devices. He joined 3D Systems in 2015 through the acquisition of Medical Modeling and has held progressive roles in operations, product development, regulatory, and marketing. Johnson currently serves as a leader in the Healthcare Solutions Group as the vice president of Portfolio & Regulatory.

Michael Phipps, co-founder and president of Enhatch, brings over 12 years of expertise in AI-driven medical device innovation, specializing in 3D printing, machine learning, and product design. Leading in the development of advanced preoperative planning and implant optimization technologies, he is committed to revolutionizing patient care.