This study aimed to elucidate the efficacy and safety of mesenchymal stromal cell (MSC) therapy for chronic discogenic low back pain (LBP). A systematic literature search was conducted on PubMed/Medline, Scopus, Cochrane, and ClinicalTrials.gov following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analysis) guidelines. Eligible studies included published and ongoing clinical trials assessing intradiscal MSC injections in patients with chronic discogenic LBP unresponsive to conservative treatment. Risk-of-bias (RoB) assessment was performed through MINORS (Methodological Index for Non-randomized Studies) and RoB 2 tools. Within- and between-group differences were expressed as means and 95% confidence intervals. Effect sizes were calculated through Cohen d and g. Data from 10 published clinical studies (n=736; 470 in treatment and 266 in control groups) revealed a mean age of 41.5 years and an average follow-up of 21.6 (range, 6–72) months. Various MSC sources were employed, including autologous and allogeneic bone marrow-derived MSCs and adipose-derived MSCs, with doses ranging from 6×10⁶ to over 50×10⁶ cells/disc. Visual analogue scale, Oswestry Disability Index, and quality-of-life questionnaires indicated modest improvements in pain, disability, and functional status. Additionally, magnetic resonance imaging assessments occasionally demonstrated increased disc hydration and stabilization or improvement of Pfirrmann grade. Data from 8 ongoing trials (n=498 participants; 276 treatment, 222 control) with follow-up periods ranging 6–24 months further corroborate the feasibility and safety of MSC-based interventions. MSC therapy is a biologically-driven approach for managing chronic discogenic LBP. While preliminary data support its potential to alleviate pain and improve disc integrity, further high-quality, standardized trials are necessary to optimize treatment protocols and confirm long-term clinical benefits.
Objective To develop and evaluate a technique using convolutional neural networks (CNNs) for the computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. By leveraging deep learning techniques, the study might potentially lead to improved patient outcomes and clinical decision-making.
Methods This study obtained 500 lateral radiographic cervical spine x-ray images from standard open-source dataset repositories to develop a classification model using CNNs. All the images contained diagnostic information, including normal cervical radiographic images (n=250) and fracture images of the cervical spine fracture (n=250). The model would classify whether the patient had a cervical spine fracture or not. Seventy percent of the images were training data sets used for model training, and 30% were for testing. Konstanz Information Miner (KNIME)’s graphic user interface-based programming enabled class label annotation, data preprocessing, CNNs model training, and performance evaluation.
Results The performance evaluation of a model for detecting cervical spine fractures presents compelling results across various metrics. This model exhibits high sensitivity (recall) values of 0.886 for fractures and 0.957 for normal cases, indicating its proficiency in identifying true positives. Precision values of 0.954 for fractures and 0.893 for normal cases highlight the model’s ability to minimize false positives. With specificity values of 0.957 for fractures and 0.886 for normal cases, the model effectively identifies true negatives. The overall accuracy of 92.14% highlights its reliability in correctly classifying cases by the area under the receiver operating characteristic curve.
Conclusion We successfully used deep learning models for computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. This approach can assist the radiologist in screening, detecting, and diagnosing cervical spine fractures.
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
Contrastive Learning-Driven Representation and Feature Selection for Spinal Fracture Detection on CT Images Hasan Genç, Canan Koç, Esra Yüzgeç Özdemír, Fatíh Özyurt IEEE Access.2026; 14: 8047. CrossRef
Clinical Application of Deep Learning for Spine MRI Interpretation: A Multicenter Evaluation of Artificial-Intelligence-Assisted versus Manual Reading on Diagnostic Agreement with the Reference Standard Xing Cheng, Maoping Zhang, Zhenxiao Ren, Tang Tang, Xiaolin Meng, Zhong Huang, Hongwei Bran Li, Weiguo Li, Qiuchan Yan, Haixiong Chen, Jie Jia, Ce Wang, Cheng Li, Chunshan Yang, Guifeng Shi, Guohua Li, Kaixin Zeng, Wei Chen, Haoxuan Gao, Xiaobo Wang, Xin Research.2026;[Epub] CrossRef
A two-stage deep learning system for cervical spine fracture diagnosis: integrating 3D segmentation and 2.5D classification on CT images Renyi Lu, Yuying Feng, Ruozhou Wang, Ting Song European Spine Journal.2026;[Epub] CrossRef
Artificial Intelligence for Cervical Spine Fracture Detection: A Systematic Review of Diagnostic Performance and Clinical Potential Wongthawat Liawrungrueang, Watcharaporn Cholamjiak, Arunee Promsri, Khanathip Jitpakdee, Sompoom Sunpaweravong, Vit Kotheeranurak, Peem Sarasombath Global Spine Journal.2025; 15(4): 2547. CrossRef
Performance and clinical implications of machine learning models for detecting cervical ossification of the posterior longitudinal ligament: a systematic review Wongthawat Liawrungrueang, Sung Tan Cho, Watcharaporn Cholamjiak, Peem Sarasombath, Nattaphon Twinprai, Prin Twinprai, Inbo Han Asian Spine Journal.2025; 19(1): 148. CrossRef
Cervical vertebral body segmentation in X-ray and magnetic resonance imaging based on YOLO-UNet: Automatic segmentation approach and available tool Hongyan Wang, Jie Lu, Song Yang, Yin Xiao, Liangliang He, Zhi Dou, Wenxing Zhao, Liqiang Yang DIGITAL HEALTH.2025;[Epub] CrossRef
Artificial Intelligence (AI) Agents Versus Agentic AI: What’s the Effect in Spine Surgery? Wongthawat Liawrungrueang Neurospine.2025; 22(2): 473. CrossRef
Fully automated pedicle screw manufacturer identification in plain radiograph with deep learning methods Rattapoom Waranusast, Panomkhawn Riyamongkol, Santi Weerakul, Nattharut Chaibhuddanugul, Artit Laoruengthana, Akaworn Mahatthanatrakul European Spine Journal.2025; 34(9): 3940. 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
Artificial intelligence in orthopedic trauma: a comprehensive review Abdulhamit Misir Injury.2025; 56(8): 112570. CrossRef
Advancing Spine Fracture Detection: The Role of Artificial Intelligence in Clinical Practice Seonghoon Jeong, Byung-Jou Lee Korean Journal of Neurotrauma.2025; 21(3): 172. CrossRef
Intelligence Architectures and Machine Learning Applications in Contemporary Spine Care Rahul Kumar, Conor Dougherty, Kyle Sporn, Akshay Khanna, Puja Ravi, Pranay Prabhakar, Nasif Zaman Bioengineering.2025; 12(9): 967. CrossRef
A Multi-Context Squeeze-Excitation Framework with Explainable Attention for Cervical Spine Fracture Detection in CT Imaging M. Anitha, P. Tamije Selvy Iranian Journal of Science and Technology, Transactions of Electrical Engineering.2025;[Epub] CrossRef
The evolution of cervical spine trauma classification: a paradigm shift from morphological description to clinical decision-making Xihao Huang, Yihong Zhang, Haowei Xiao, Jinlong Chen, Yu Jiang Frontiers in Neurology.2025;[Epub] CrossRef
From the Editor-in-Chief: Featured Articles in the September 2024 Issue Inbo Han Neurospine.2024; 21(3): 743. CrossRef
Commentary on “Artificial Intelligence Detection of Cervical Spine Fractures Using Convolutional Neural Network Models” Yu-Cheng Yeh, Fon-Yih Tsuang Neurospine.2024; 21(3): 842. CrossRef
Objective We aimed to comprehensively compare surgical methods for osteoporotic vertebral compression fracture (OVCF) using systematic review and network meta-analysis to understand their effectiveness and outcomes, as current research provides limited overviews.
Methods We followed PRISMA (preferred reporting items for systematic reviews and meta-analyses) guidelines, preregistering our protocol with PROSPERO. We analyzed Englishpublished randomized controlled trials (RCTs) on adults with OVCFs that evaluated pain intensity or functionality using tools like visual analogue scale (VAS) or Oswestry Disability Index (ODI). Exclusions included non-RCTs, malignancy-related fractures, and certain interventions. Using the RoB 2 tool, we assessed bias and visualized results with Robvis. Our primary outcome was pain intensity, with secondary outcomes including disability, new fractures, and cement leakage. Results were synthesized using Stata/MP.
Results Thirty-four RCTs from 10 countries, totaling 4,384 patients, were analyzed. Shortterm VAS indicated kyphoplasty with facet joint injection (KIJ) as the top treatment at 87.7%, while unipedicular kyphoplasty (UKP) led to long-term at 74.9%. Short-term ODI favored vertebroplasty with facet joint injection (VIJ) at 98.4%, with kyphoplasty (KP) leading longterm at 66.0%. All surgical techniques were superior to conservative treatment. Vertebral augmentation devices reported the fewest new fractures and curved vertebroplasty had the least cement leakage. SUCRA (surface under the cumulative ranking) analyses suggested UKP and VIJ as top choices for postoperative pain relief, with VIJ excelling in postoperative disability improvement.
Conclusion Our analysis evaluates 12 OVCF interventions, underscoring KIJ for short-term pain relief and VIJ and UKP for long-term efficacy. Notably, VIJ stands out in disability outcomes, emphasizing the need for comprehensive OVCF management.
Citations
Citations to this article as recorded by
Diagnosis and treatment of osteoporotic vertebral fractures Martin Bibza, Michal Božík, Mário Malina, Boris Šteňo Clinical Osteology.2026; 31(1): 55. CrossRef
Predicting long-term clinical mortality of elderly patients with vertebral compression fractures Shuofan Wang, Kaiwen Peng, Kaili Peng, Zhichao Gao Frontiers in Medicine.2026;[Epub] CrossRef
Restoration of Sagittal Alignment and Pulmonary Function With Percutaneous Vertebral Body Augmentation for Painful Osteoporotic Vertebral Compression Fractures: A Systematic Review Hanne H Jørgensen, Mikkel Ø Andersen, Tove F Frandsen, Line A Wickstrøm, Benjamin Kostic, Leah Y Carreon Cureus.2025;[Epub] CrossRef
Prophylactic Antibiotics in Vertebroplasty and Kyphoplasty: A Nationwide Analysis of Infection Rates and Antibiotic Use in South Korea Youngjin Kim, Young-Hoon Kim, Sukil Kim, Jun-Seok Lee, Sang-Il Kim, Joonghyun Ahn, So-Young Han, Hyung-Youl Park Antibiotics.2025; 14(9): 901. CrossRef
Spinal Subdural Hematoma After Kyphoplasty in a Patient on Warfarin: A Case Report and Literature Review Ho-Young Jung, Jun-Seok Lee, Geon-U Kim, Hyung-Youl Park Journal of Advanced Spine Surgery.2025; 15(1): 38. CrossRef
SPINAL DISORDER DIAGNOSIS BASED ON DEEP LEARNING INTEGRATING BIOMECHANICAL DATA HUI-JUAN WAN, TENG-TENG ZHANG, JIN-XIN ZHENG, BING-BING WANG, YONG-JUN CHEN Journal of Mechanics in Medicine and Biology.2025;[Epub] CrossRef
Minimally Invasive Treatment Using Biportal Endoscopic Decompression with Vertebroplasty for Osteoporotic Vertebral Compression Fractures in Older Adult Patients Sang-Min Park, Sang-Soo Na, Ho-Joong Kim, Jin S. Yeom Clinics in Orthopedic Surgery.2025; 17(5): 836. CrossRef
Interleukin Concentrations in Bone Marrow Fluid and MRI Prognostic Findings in Osteoporotic Vertebral Fractures Yasuhiro Nakajima, Akinori Kageyama, Yasukazu Hijikata, Ayako Motomura, Takashi Tsujiuchi, Koji Osuka Cureus.2025;[Epub] CrossRef
Osteoporosis en columna vertebral Barón Zárate Kalfópulos, Irving Omar Estévez-García Investigación en Discapacidad.2025; 11(2): 41. CrossRef
A retrospective study identifying the primary source of hidden blood loss during vertebroplasty Yuanhao Wang, Ting Zhao, Cong Chen, Baoshan Xu Medicine.2025; 104(42): e45213. CrossRef
The Use of Polymethylmethacrylate Cement in Percutaneous Vertebroplasty Versus Conservative Management: How to Treat Osteoporotic Vertebral Compression Fractures Corrado Ciatti, Chiara Asti, Pietro Maniscalco, Michelangelo Rinaldi, Gianfranco Pirellas, Gianfilippo Caggiari, Francesco Pisanu, Angelino Sanna, Carlo Doria Medicina.2025; 61(11): 2004. CrossRef
Influence of thoracolumbar kyphotic Cobb angle on prognosis after PKP surgery Peng Yuan, Xiang Ge, Qiang Shi, Yifan Wu, Zhen Yu Scientific Reports.2025;[Epub] CrossRef
Commentary on “Deep Learning-Assisted Quantitative Measurement of Thoracolumbar Fracture Features on Lateral Radiographs” Chao-Hung Kuo Neurospine.2024; 21(1): 44. CrossRef
Clinical Oversight and Delayed Diagnosis of a Pathological Compression Fracture Causing Paraplegia Yin-Sheng Chen, Ping-Chuan Liu, Chih-Chang Chang, Tsung-Hsi Tu, Chao-Hung Kuo Cureus.2024;[Epub] CrossRef
Clinical significance of modified unilateral puncture percutaneous vertebroplasty guided by 3D- printed guides in the treatment of osteoporotic vertebral compression fractures: a retrospective study Tao Gao, Sheng-Yu Wan, Zhi-Yu Chen, Tao Li, Xu Lin, Hai-Gang Hu, Jian-Dong Tang, Chao Wu BMC Musculoskeletal Disorders.2024;[Epub] CrossRef
Validity and reliability of the osteoporotic fracture treatment score (OF score) and outcomes across various treatments in osteoporosis vertebral compression fracture patients Korawish Mekariya, Borriwat Santipas, Harit Khamnurak, Wilasinee Sirichativapee, Ekkapoj Korwutthikulrangsri, Monchai Ruangchainikom, Werasak Sutipornpalangkul Journal of Orthopaedic Surgery and Research.2024;[Epub] CrossRef
Objective Herein, we investigated whether mesenchymal stem cells (MSCs) transplantation combined with electroacupuncture (EA) treatment could decrease the proportion of proinflammatory microglia/macrophages and neurotoxic A1 reactive astrocytes and inhibit glial scar formation to enhance axonal regeneration after spinal cord injury (SCI).
Methods Adult rats were divided into 5 groups after complete transection of the spinal cord at the T10 level: a control group, a nonacupoint EA (NA-EA) group, an EA group, an MSC group, and an MSCs+EA group. Immunofluorescence labeling, quantitative real-time polymerase chain reaction, enzyme-linked immunosorbent assay, and Western blots were performed.
Results The results showed that MSCs+EA treatment reduced the proportion of proinflammatory M1 subtype microglia/macrophages, but increased the differentiation of anti-inflammatory M2 phenotype cells, thereby suppressing the mRNA and protein expression of proinflammatory cytokines (tumor necrosis factor-α and IL-1β) and increasing the expression of an anti-inflammatory cytokine (interleukin [IL]-10) on days 7 and 14 after SCI. The changes in expression correlated with the attenuated neurotoxic A1 reactive astrocytes and glial scar, which in turn facilitated the axonal regeneration of the injured spinal cord. In vitro, the proinflammatory cytokines increased the level of proliferation of astrocytes and increased the expression levels of C3, glial fibrillary acidic protein, and chondroitin sulfate proteoglycan. These effects were blocked by administering inhibitors of ErbB1 and signal transducer and activator of transcription 3 (STAT3) (AG1478 and AG490) and IL-10.
Conclusion These findings showed that MSCs+EA treatment synergistically regulated the microglia/macrophage subpopulation to reduce inflammation, the formation of neurotoxic A1 astrocytes, and glial scars. This was achieved by downregulating the ErbB1-STAT3 signal pathway, thereby providing a favorable microenvironment conducive to axonal regeneration after SCI.
Citations
Citations to this article as recorded by
The role of autophagy in spinal cord injury: Mechanisms, crosstalk, and therapeutic strategies Rui Wang, Zhen Niu, Runze Tian, Aini Chen, Huangmei Liao, Rui Kuang, Ying Feng, Guangyu Chin, Jiesheng Xie, Ping Zhu, Chi Teng Vong, Ge Li Neural Regeneration Research.2026; 21(6): 2110. CrossRef
Mesenchymal stem cells transplantation as a replacement stem cell for the treatment of neuropathic pain Wen-Jun Zhang, Xin Zhang, Ji-Peng Liu, Yong-Sheng Xu, Jun-Xiang Liao, Bing Zou, Liu-Xiang Fu International Journal of Surgery.2026; 112(3): 7906. CrossRef
Glial cell: Role of the pain modulation in acupuncture analgesia Mi YUAN, Lan YUAN, Wei CHEN, Yang-shuai SU, Meng-yan FAN, Xiang-hong JING, Wei HE, Xiao-yu WANG World Journal of Acupuncture - Moxibustion.2025; 35(2): 103. CrossRef
Biomaterials and cell-based therapy post spinal cord injury Sara Haratizadeh, Haitao Liu, Hengde Li, Mohsen Adeli, Angelo H. All Journal of Translational Medicine.2025;[Epub] CrossRef
Integrated single-cell and bulk RNA sequencing reveals the mechanisms of electroacupuncture in suppressing ferroptosis after spinal cord injury Jieqi Zhang, Yi Huang, Xihan Ying, Ruoqi Wang, Kai Zhang, Lei Wu, Dexiong Han, Ruijie Ma, Kelin He Clinical Traditional Medicine and Pharmacology.2025; 6(3): 200230. CrossRef
Therapeutic Transplantation of Human Central Nervous System Organoids for Neural Reconstruction Sung Jun Hong, Minsung Bock, Songzi Zhang, Seong Bae An, Inbo Han International Journal of Molecular Sciences.2024; 25(15): 8540. CrossRef
First
Prev
