The Great Mimickers of Spinal Pathology

Farshad‐Amacker, Nadja A.; Sutter, Reto

doi:10.1055/s-0042-1748914

Cited by 1 publication

(4 citation statements)

References 84 publications

(113 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…X-rays and computed tomography (CT) are widely used diagnostic modalities for DSCs [ 5 ]. In this study, our objective was to develop a model for DSC detection and classification using spinal X-ray images.…”

Section: Discussionmentioning

confidence: 99%

“…The detection and characterization of these DSCs can be challenging due to the complexity of the spine's anatomy, presence of age-related deterioration, and subtlety of some DSCs in imaging studies [ 5 , 7 ]. This is particularly true in the presence of surgical implants, which can cause artifacts in images, making it difficult to identify and assess surrounding tissues [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

“…Degenerative spinal conditions (DSCs) encompass a broad spectrum of conditions that affect the structural elements of the spine that can significantly impact an individual's health and quality of life [1][2][3][4][5][6]. Globally, it has been estimated that nearly 30% of adults may suffer from a spinal disorder with even more individuals at risk of DSCs sometime in their lifetime.…”

Section: Introductionmentioning

confidence: 99%

“…[1]. From degenerative conditions, such as disc disease, foraminal stenosis, and osteophytes, to traumatic events leading to fractures and dislocations, the breadth of DSCs is expansive and their prevalence significant [5]. Treatment approaches to these conditions are as varied as their etiologies.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Utilizing Deep Learning for X-ray Imaging: Detecting and Classifying Degenerative Spinal Conditions

Ghauri¹,

Reddy²,

Tak³

et al. 2023

Cureus

View full text Add to dashboard Cite

Background Degenerative spinal conditions (DSCs) involve a diverse set of pathologies that significantly impact health and quality of life, affecting many individuals at least once during their lifetime. Treatment approaches are varied and complex, reflecting the intricacy of spinal anatomy and kinetics. Diagnosis and management pose challenges, with the accurate detection of lesions further complicated by age-related degeneration and surgical implants. Technological advancements, particularly in artificial intelligence (AI) and deep learning, have demonstrated the potential to enhance detection of spinal lesions. Despite challenges in dataset creation and integration into clinical settings, further research holds promise for improved patient outcomes. Methods This study aimed to develop a DSC detection and classification model using a Kaggle dataset of 967 spinal X-ray images at the Department of Neurosurgery of Arrowhead Regional Medical Center, Colton, California, USA. Our entire workflow, including data preprocessing, training, validation, and testing, was performed by utilizing an online-cloud based AI platform. The model's performance was evaluated based on its ability to accurately classify certain DSCs (osteophytes, spinal implants, and foraminal stenosis) and distinguish these from normal X-rays. Evaluation metrics, including accuracy, precision, recall, and confusion matrix, were calculated. Results The model achieved an average precision of 0.88, with precision and recall values of 87% and 83.3%, respectively, indicating its high accuracy in classifying DSCs and distinguishing these from normal cases. Sensitivity and specificity values were calculated as 94.12% and 96.68%, respectively. The overall accuracy of the model was calculated to be 89%. Conclusion These findings indicate the utility of deep learning algorithms in enhancing early DSC detection and screening. Our platform is a cost-effective tool that demonstrates robust performance given a heterogeneous dataset. However, additional validation studies are required to evaluate the model's generalizability across different populations and optimize its seamless integration into various types of clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%