Brucella spondylitis, an infectious spinal disease caused by the invasion of Brucella bacteria into the body. Its diagnosis relies mainly on laboratory and imaging tests. Due to the limited diagnostic ability of X-ray and CT for Brucella spondylitis, MRI has become the main diagnostic tool. In recent years, functional magnetic resonance technology has demonstrated great advantages in the diagnosis and therapeutic evaluation of brucellosis spondylitis, which can provide pathophysiologic information about the disease and is also a noninvasive and noninvasive diagnostic tool with a broader application prospect. Radiomics, an emerging approach, has also shown better diagnostic efficacy for this disease.
The investigators will incorporate 100 confirmed cases of Brucella spondylitis (BS) patients diagnosed at Affiliated Hospital of Inner Mongolia Medical University. The patients receive routine scan with a Siemens Skyra 3.0T MRI scanner and the investigators collect clinical data and blood test results from the patients.The investigators segment the affected vertebral bodies by ITK-SNAP software on STIR images to create three-dimensional regions of interest. Then use Onekey software to extract radiomics features from the affected vertebral bodies. Employed t-tests and Lasso regression to select radiomics features. Then separately use radiomics features and combining it with clinical information to build random vector machine(SVM) and random forest(RF) models . All the models are constructed in the training set and their performance are evaluated on the validation set.
Study Type
OBSERVATIONAL
Enrollment
100
Affiliated Hospital of Inner Mongolia Medical University
Hohhot, Inner Mongolia, China
RECRUITINGThe useful value of radiomics of MRI in BS clinical diagnosis.
The investigators will validate the results. The validation and external test cohorts will be used to evaluate the performance of the prediction models. The micro-avg and macro-avg precision, true positive (TP), true negative (TN), false positive (FP), false negative (FN), accuracy, sensitivity, specificity, and F1 score of different models will be calculated. Receiver operating characteristic (ROC) curves is going to be used to assess the sensitivity and specificity of the models, and the area under the ROC curve (AUC) was used to describe the discriminative power of the models. The investigators think radiomics of MRI can provide a reliable basis for early damage in brucellosis spondylitis and provides evidence for early clinical intervention.
Time frame: December 2024
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.