This paper analyzes the regulatory frameworks for artificial intelligence/machine learning AI/ML-enabled medical devices in the European Union (EU), the United States (US), and the Republic of Korea, with a focus on applications in spine surgery. The aim is to provide guidance for developers and researchers navigating regulatory pathways. A review of current literature, regulatory documents, and legislative frameworks was conducted. Key differences in regulatory bodies, risk classification, submission requirements, and approval pathways for AI/ML medical devices were examined in the EU, US, and Republic of Korea. The EU AI Act (2024) establishes a risk-based framework, requiring regulatory review based on device risk, with high-risk devices subject to stricter oversight. The US applies a more flexible approach, allowing multiple submission pathways and incorporating a focus on continuous learning. The Republic of Korea emphasizes possibilities of streamlined approval and with growing use of real-world data to support validation. Developers must ensure regulatory alignment early in the development process, focusing on key aspects like dataset quality, transparency, and continuous monitoring. Across all regions, the need for technical documentation, quality management systems, and bias mitigation are essential for approval. Developers are encouraged to adopt adaptable strategies to comply with evolving regulatory standards, ensuring models remain transparent, fair, and reliable. The EU’s comprehensive AI Act enforces stricter oversight, while the US and Korea offer more flexible pathways. Developers of spine surgery AI/ML devices must tailor development strategies to align with regional regulations, emphasizing transparent development, quality assurance, and postmarket monitoring to ensure approval success.
Citations
Citations to this article as recorded by
Artificial intelligence in spine surgery: a scoping review Anis Choucha, Morgane Evin, Matteo de Simone, Guillaume Dannhoff, Henry Dufour, Valentin Avinens, Kaissar Farah, Florian Saby, Stephane Fuentes Neurochirurgie.2026; 72(1): 101764. CrossRef
Applications of Raman Spectroscopy in Pandemic Virology: A Comprehensive Review Hulya Yilmaz, Anuradha Ramoji, Andreea Winterfeld, Hamideh Salehi, Aykut Ozkul, Jürgen Popp ACS Photonics.2026; 13(6): 1568. CrossRef
Application of artificial intelligence in diagnosis and treatment of spinal deformities Chunwang Jia, Haoming Sun, Zhenhao Chen, Yubao Hou, Jiyu Li, Xiaosheng Ma, Feizhou Lyu, Jianyuan Jiang, Yu Chen, Hongli Wang Spine Research.2026; 2(2): 110. CrossRef
Current Applications and Future Directions of Technologies Used in Adult Deformity Surgery for Personalized Alignment: A Narrative Review Janet Hsu, Taikhoom M. Dahodwala, Noel O. Akioyamen, Evan Mostafa, Rami Z. AbuQubo, Xiuyi Alexander Yang, Priya K. Singh, Daniel C. Berman, Rafael De la Garza Ramos, Yaroslav Gelfand, Saikiran G. Murthy, Jonathan D. Krystal, Ananth S. Eleswarapu, Mitchell Journal of Personalized Medicine.2025; 15(10): 480. CrossRef
Objective Virtual and augmented reality have enjoyed increased attention in spine surgery. Preoperative planning, pedicle screw placement, and surgical training are among the most studied use cases. Identifying osseous structures is a key aspect of navigating a 3-dimensional virtual reconstruction. To automate the otherwise time-consuming process of labeling vertebrae on each slice individually, we propose a fully automated pipeline that automates segmentation on computed tomography (CT) and which can form the basis for further virtual or augmented reality application and radiomic analysis.
Methods Based on a large public dataset of annotated vertebral CT scans, we first trained a YOLOv8m (You-Only-Look-Once algorithm, Version 8 and size medium) to detect each vertebra individually. On the then cropped images, a 2D-U-Net was developed and externally validated on 2 different public datasets.
Results Two hundred fourteen CT scans (cervical, thoracic, or lumbar spine) were used for model training, and 40 scans were used for external validation. Vertebra recognition achieved a mAP50 (mean average precision with Jaccard threshold of 0.5) of over 0.84, and the segmentation algorithm attained a mean Dice score of 0.75 ± 0.14 at internal, 0.77 ± 0.12 and 0.82 ± 0.14 at external validation, respectively.
Conclusion We propose a 2-stage approach consisting of single vertebra labeling by an object detection algorithm followed by semantic segmentation. In our externally validated pilot study, we demonstrate robust performance for our object detection network in identifying individual vertebrae, as well as for our segmentation model in precisely delineating the bony structures.
Artificial intelligence in spine surgery: a scoping review Anis Choucha, Morgane Evin, Matteo de Simone, Guillaume Dannhoff, Henry Dufour, Valentin Avinens, Kaissar Farah, Florian Saby, Stephane Fuentes Neurochirurgie.2026; 72(1): 101764. CrossRef
Deep Learning-Based Projection Angle Estimation for Lumbar Oblique Radiography: A Two-Stage Object Detection Approach Using Vertebral–Pedicle Ratio Analysis Riria Yamamoto, Kaori Tsutsumi, Takaaki Yoshimura, Hiroyuki Sugimori Applied Sciences.2026; 16(6): 2800. CrossRef
AI applications in lumbar and lumbosacral pedicle screw placement: a systematic review of limited evidence and future directions Pakpoom Thintharua, Ratchaphon Prabrai, Anuyut khamsiriwatchara, Rohan Sethi, Sorayouth Chumnanvej Neurosurgical Review.2026;[Epub] CrossRef
Vertebra-Level Completeness Analysis in Thoracolumbar Ultrasound Using a YOLO-Based Detection Framework Sumartini Dana, Chen Zhang, Yongping Zheng, Sai Ho Ling Sensors.2026; 26(7): 2101. CrossRef
Segmentation and 3D Visualization of Spinal Motion Segments from MSCT Images Using a 3D U‑Net Framework Antor Mahamudul Hashan, Khlebnikov Nikolai Alexandrovich, Denis Protasov Journal of Imaging Informatics in Medicine.2026;[Epub] CrossRef
Dual-cooperation of spatial and local cues enhances point-supervised spinal structure segmentation Pei Wang, Jiansong Fan, Xiang Pan, Wei Chu Applied Soft Computing.2026; 202: 115993. CrossRef
The Application of Artificial Intelligence in Spine Surgery: A Scoping Review Liangyu Shi, Hongfei Wang, Graham Ka-Hon Shea JAAOS: Global Research and Reviews.2025;[Epub] CrossRef
Can artificial intelligence in spine imaging affect current practice? Practical developments and their clinical status Yu-Cherng Chang, Cinthia Del Toro, Joseph P. Gjolaj, Thiago A. Braga, Ty K. Subhawong North American Spine Society Journal (NASSJ).2025; 23: 100621. CrossRef
Mask prompt-guided multi-stage network for vertebrae identification Zhikai Zhou, Ziyue Zhang, Mingying Li, Lei Song, Youyong Kong, Jean Louis Coatrieux, Huazhong Shu Biomedical Signal Processing and Control.2025; 110: 108091. CrossRef
Empowering the future of spinal surgery through digital and intelligent technologies Chenfei Gao, Tianyu Yao, Tenghui Zhang, Wenyu Zhang, Jianxi Wang, Fazhi Zang, Huajiang Chen Spine Research.2025; 1(1): 23. CrossRef
Deep learning for automatic vertebra analysis: A methodological survey of recent advances Zhuofan Xie, Zishan Lin, Enlong Sun, Fengyi Ding, Jie Qi, Shen Zhao Computerized Medical Imaging and Graphics.2025; 125: 102652. CrossRef
Artificial Intelligence in Surgery: A Systematic Review of Use and Validation Nitzan Kenig, Javier Monton Echeverria, Aina Muntaner Vives Journal of Clinical Medicine.2024; 13(23): 7108. CrossRef
Objective Computed tomography (CT) imaging is a cornerstone in the assessment of patients with spinal trauma and in the planning of spinal interventions. However, CT studies are associated with logistical problems, acquisition costs, and radiation exposure. In this proof-of-concept study, the feasibility of generating synthetic spinal CT images using biplanar radiographs was explored. This could expand the potential applications of x-ray machines pre-, post-, and even intraoperatively.
Methods A cohort of 209 patients who underwent spinal CT imaging from the VerSe2020 dataset was used to train the algorithm. The model was subsequently evaluated using an internal and external validation set containing 55 from the VerSe2020 dataset and a subset of 56 images from the CTSpine1K dataset, respectively. Digitally reconstructed radiographs served as input for training and evaluation of the 2-dimensional (2D)-to-3-dimentional (3D) generative adversarial model. Model performance was assessed using peak signal to noise ratio (PSNR), structural similarity index (SSIM), and cosine similarity (CS).
Results At external validation, the developed model achieved a PSNR of 21.139 ± 1.018 dB (mean ± standard deviation). The SSIM and CS amounted to 0.947 ± 0.010 and 0.671 ± 0.691, respectively.
Conclusion Generating an artificial 3D output from 2D imaging is challenging, especially for spinal imaging, where x-rays are known to deliver insufficient information frequently. Although the synthetic CT scans derived from our model do not perfectly match their ground truth CT, our proof-of-concept study warrants further exploration of the potential of this technology.
Citations
Citations to this article as recorded by
Artificial intelligence in spine surgery: a scoping review Anis Choucha, Morgane Evin, Matteo de Simone, Guillaume Dannhoff, Henry Dufour, Valentin Avinens, Kaissar Farah, Florian Saby, Stephane Fuentes Neurochirurgie.2026; 72(1): 101764. CrossRef
TomoRay cranial: synthesis of cranial CT imaging from biplanar radiographs using a generative adversarial network Olivier Zanier, Seungjun Ryu, Raffaele Da Mutten, Sven Theiler, Alessandro Carretta, Giorgio Palandri, Diego Mazzatenta, Luca Regli, Carlo Serra, Victor E. Staartjes European Radiology.2026; 36(6): 4873. CrossRef
Synthetic Imaging Methods: Ready for the Neurosurgical Operating Room? Victor E. Staartjes, Massimo Bottini, Olivier Zanier, Luca Regli, Carlo Serra World Neurosurgery.2026; 206: 124740. CrossRef
Enhancement and Segmentation of High Definition CT Images in Everything 6G Medical IoT Environment Jinlei Liu, Fuyao Yu, Rui Li, Xiaohong Lyu, Shilei Zheng IEEE Internet of Things Journal.2026; 13(5): 7862. CrossRef
Strategies for generating synthetic computed tomography-like imaging from radiographs: A scoping review Daniel De Wilde, Olivier Zanier, Raffaele Da Mutten, Michael Jin, Luca Regli, Carlo Serra, Victor E. Staartjes Medical Image Analysis.2025; 101: 103454. CrossRef
Cross-modality image-to-image translation from MR to synthetic 18F-FDOPA PET/MR fusion images using conditional GAN in brain cancer Youngbeom Seo, Heesung Yang, Eunjung Kong, Vivek Sanker, Atman Desai, Jungwon Lee, So Hee Park, You Seon Song, Ikchan Jeon Neuroradiology.2025; 67(10): 2727. CrossRef
Generation of synthetic tomographic images from biplanar X-ray: a narrative review of history, methods, and the state of the art Aron ALAKMEH, Olivier ZANIER, Massimo BOTTINI, Maria L. GANDIA-GONZALEZ, Gustav BURSTRÖM, Erik EDSTRÖM, Adrian ELMI TERANDER, Ethan SCHONFELD, Anand VEERAVAGU, Luca REGLI, Carlo SERRA, Victor E. STAARTJES Journal of Neurosurgical Sciences.2025;[Epub] CrossRef
From the Editor-in-Chief: Featured Articles in the March 2024 Issue Inbo Han Neurospine.2024; 21(1): 1. CrossRef
Automatic 3D reconstruction of vertebrae from orthogonal bi-planar radiographs Yuepeng Chen, Yue Gao, Xiangling Fu, Yingyin Chen, Ji Wu, Chenyi Guo, Xiaodong Li Scientific Reports.2024;[Epub] CrossRef
Enabling Technologies in the Management of Cervical Spine Trauma Arjun K. Menta, Antony A. Fuleihan, Marvin Li, Tej D. Azad, Timothy F. Witham Clinical Spine Surgery.2024; 37(9): 459. CrossRef
First
Prev
