Radiographic assessment of acute vs chronic vertebral compression fractures

Surgical Stabilization of the Spine: A Clinical Review of Spinal Fractures, Spondylolisthesis, and Instrumentation Methods

The spine is a complex structure critical for stability, force transmission, and neural protection, with spinal fractures and spondylolisthesis posing significant challenges to its integrity and function. Spinal fractures arise from trauma, degenerative conditions, or osteoporosis, often affecting transitional zones like the thoracolumbar junction. Spondylolisthesis results from structural defects or degenerative changes, leading to vertebral displacement and potential neurological symptoms. Diagnostic and classification systems, such as AO Spine and TLICS, aid in evaluating instability and guiding treatment strategies. Advances in surgical techniques, including minimally invasive approaches, pedicle screws, interbody cages, and robotic-assisted systems, have improved precision and recovery while reducing morbidity. Vertebral augmentation techniques like vertebroplasty and kyphoplasty offer minimally invasive options for osteoporotic fractures. Despite these innovations, postoperative outcomes vary, with challenges such as persistent pain and hardware complications necessitating tailored interventions. Future directions emphasize predictive analytics and enhanced recovery strategies to optimize surgical outcomes and patient quality of life.

Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification

OBJECTIVE

This study evaluated the applicability of the classical method, height loss ratio (HLR), for identifying major acute compression fractures in clinical practice and compared its performance with deep learning (DL)-based VCF detection methods. Additionally, it examined whether combining the HLR with DL approaches could enhance performance, exploring the potential integration of classical and DL methodologies.

METHODS

End-to-End VCF Detection (EEVD), Two-Stage VCF Detection with Segmentation and Detection (TSVD_SD), and Two-Stage VCF Detection with Detection and Classification (TSVD_DC). The models were evaluated on a dataset of 589 patients, focusing on sensitivity, specificity, accuracy, and precision.

RESULTS

TSVD_SD outperformed all other methods, achieving the highest sensitivity (84.46%) and accuracy (95.05%), making it particularly effective for identifying true positives. The complementary use of DL methods with HLR further improved detection performance. For instance, combining HLR-negative cases with TSVD_SD increased sensitivity to 87.84%, reducing missed fractures, while combining HLR-positive cases with EEVD achieved the highest specificity (99.77%), minimizing false positives.

CONCLUSION

These findings demonstrated that DL-based approaches, particularly TSVD_SD, provided robust alternatives or complements to traditional methods, significantly enhancing diagnostic accuracy for acute VCFs in clinical practice.

Improved Detection Accuracy of Chronic Vertebral Compression Fractures by Integrating Height Loss Ratio and Deep Learning Approaches

OBJECTIVES

This study aims to assess the limitations of the height loss ratio (HLR) method and introduce a new approach that integrates a deep learning (DL) model to enhance vertebral compression fracture (VCF) detection performance.

METHODS

We conducted a retrospective study on 589 patients with chronic VCFs. We compared four different methods: HLR-only, DL-only, a combination of HLR and DL for positive VCF, and a combination of HLR and DL for negative VCF. The models were evaluated using dice similarity coefficient, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC).

RESULTS

The combined method (HLR + DL, positive) demonstrated the best performance with an AUROC of 0.968, sensitivity (94.95%), and specificity (90.59%). The HLR-only and the HLR + DL (negative) also showed strong discriminatory power, with AUROCs of 0.948 and 0.947, respectively. The DL-only model achieved the highest specificity (95.92%) but exhibited lower sensitivity (82.83%).

CONCLUSIONS

Our study highlights the limitations of the HLR method in detecting chronic VCFs and demonstrates the improved performance of combining HLR with DL models.

Radiological Diagnosis and Advances in Imaging of Vertebral Compression Fractures

Vertebral compression fractures (VCFs) affect 1.4 million patients every year, especially among the globally aging population, leading to increased morbidity and mortality. Often characterized with symptoms of sudden onset back pain, decreased vertebral height, progressive kyphosis, and limited mobility, VCFs can significantly impact a patient's quality of life and are a significant public health concern. Imaging modalities in radiology, including radiographs, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) studies and bone scans, play crucial and evolving roles in the diagnosis, assessment, and management of VCFs. An understanding of anatomy, and the extent to which each imaging modality serves to elucidate that anatomy, is crucial in understanding and providing guidance on fracture severity, classification, associated soft tissue injuries, underlying pathologies, and bone mineral density, ultimately guiding treatment decisions, monitoring treatment response, and predicting prognosis and long-term outcomes. This article thus explores the important role of radiology in illuminating the underlying anatomy and pathophysiology, classification, diagnosis, treatment, and management of patients with VCFs. Continued research and advancements in imaging technologies will further enhance our understanding of VCFs and pave the way for personalized and effective management strategies.

An overview of the performance of AI in fracture detection in lumbar and thoracic spine radiographs on a per vertebra basis

PURPOSE

Subtle spinal compression fractures can easily be missed. AI may help in interpreting these images. We propose to test the performance of an FDA-approved algorithm for fracture detection in radiographs on a per vertebra basis, assessing performance based on grade of compression, presence of foreign material, severity of degenerative changes, and acuity of the fracture.

METHODS

Thoracic and lumbar spine radiographs with inquiries for fracture were retrospectively collected and analyzed by the AI. The presence or absence of fracture was defined by the written report or cross-sectional imaging where available. Fractures were classified semi-quantitatively by the Genant classification, by acuity, by the presence of foreign material, and overall degree of degenerative change of the spine. The results of the AI were compared to the gold standard.

RESULTS

A total of 512 exams were included, depicting 4114 vertebra with 495 fractures. Overall sensitivity was 63.2% for the lumbar spine, significantly higher than the thoracic spine with 50.6%. Specificity was 96.7 and 98.3% respectively. Sensitivity increased with fracture grade, without a significant difference between grade 2 and 3 compression fractures (lumbar spine: grade 1, 52.5%; grade 2, 72.3%; grade 3, 75.8%; thoracic spine: grade 1, 42.4%; grade 2, 60.0%; grade 3, 60.0%). The presence of foreign material and a high degree of degenerative changes reduced sensitivity.

CONCLUSION

Overall performance of the AI on a per vertebra basis was degraded in clinically relevant scenarios such as for low-grade compression fractures.

A Deep Learning-Based Model for Classifying Osteoporotic Lumbar Vertebral Fractures on Radiographs: A Retrospective Model Development and Validation Study

Early diagnosis and initiation of treatment for fresh osteoporotic lumbar vertebral fractures (OLVF) are crucial. Magnetic resonance imaging (MRI) is generally performed to differentiate between fresh and old OLVF. However, MRIs can be intolerable for patients with severe back pain. Furthermore, it is difficult to perform in an emergency. MRI should therefore only be performed in appropriately selected patients with a high suspicion of fresh fractures. As radiography is the first-choice imaging examination for the diagnosis of OLVF, improving screening accuracy with radiographs will optimize the decision of whether an MRI is necessary. This study aimed to develop a method to automatically classify lumbar vertebrae (LV) conditions such as normal, old, or fresh OLVF using deep learning methods with radiography. A total of 3481 LV images for training, validation, and testing and 662 LV images for external validation were collected. Visual evaluation by two radiologists determined the ground truth of LV diagnoses. Three convolutional neural networks were ensembled. The accuracy, sensitivity, and specificity were 0.89, 0.83, and 0.92 in the test and 0.84, 0.76, and 0.89 in the external validation, respectively. The results suggest that the proposed method can contribute to the accurate automatic classification of LV conditions on radiography.