The Use of Radiomics Data Obtained from ADC Map of Lumbar MRI and Machine Learning in Diagnosis of Osteoporosis

Abstract

Background: Osteoporosis is a systemic skeletal disorder marked by reduced bone density and microarchitecturaldeterioration, leading to increased fracture risk. While the dual-energy X-ray absorptiometry (DEXA) scan is the World HealthOrganization (WHO)-recommended diagnostic standard, its limitations necessitate alternative methods. Emerging magneticresonance imaging (MRI) techniques, radiomics, and machine learning promise to enhance osteoporosis diagnosis throughdetailed analysis of lumbar MRI apparent diffusion coefficient (ADC) maps, potentially revolutionizing early detection andtreatment strategies. Objectives: In this study, we are going to evaluate the performance of machine learning (ML) models using radiomics featuresof lumbar MRI ADC map for osteoporosis detection, and to identify significant features and their diagnostic thresholds. Specificperformance metrics such as accuracy, sensitivity, specificity, and Area Under the receiver operating characteristic (ROC) Curve(AUC) were assessed. Patients and Methods: This retrospective study employed a cross-sectional design, with a total of 140 cases, including 21 withosteoporosis. The study's inclusion criteria consisted of concurrent lumbar MRI and DEXA within a year, while exclusion criteriaincluded infectious or neoplastic lumbar lesions, fractures, instrumentation, significant osteodegenerative changes, caseswhere the first four lumbar vertebrae were not included in the imaging field, and absence of diffusion-weighted imaging.Manual segmentation of lumbar vertebrae from ADC maps was performed to create a comprehensive dataset, comprising 5,580radiomics features per case. Subsequently, the top five features selected by fast correlation-based filter (FCBF) were used to testthe performance of seven Machine Learning algorithms (k-Nearest neighbors, decision tree, random forest, logistic regression,support vector machine, naive bayes, and neural network). Statistical tests and ROC curve analysis were conducted to determinethe significance and thresholds of these features. Results: The study included 140 cases, with 132 females (94.3%) and 8 males (5.7%), and a mean age of 65.32 +/- 8.50 years. Themean BMI was 31.43 +/- 5.53 kg/m(2) for females and 26 +/- 3.59 kg/m(2) for males. In terms of demographic differences, no significantage difference was found between the osteoporotic and non-osteoporotic groups (P = 0.889). However, the osteoporotic grouphad significantly lower mean body weight (64.90 +/- 10.13 kg vs. 74.68 +/- 13.94 kg, P = 0.003) and BMI (27.40 +/- 4.38 kg/m(2) vs. 31.77 +/- 5.52 kg/m(2), P = 0.001) compared to the non-osteoporotic group. The median interval between DEXA and lumbar MRI was 1 month(range 0.1 - 11.87 months). The Neural Network model demonstrated the highest performance with an AUC of 0.616 and aclassification accuracy of 0.764 using all features. The Naive Bayes model, using the top five features selected by FCBF, showedthe highest performance with an AUC of 0.913, accuracy of 0.907, sensitivity of 0.667, and specificity of 0.95. All ML models'performance were elevated by feature selection. Independent t-tests and Mann-Whitney U tests identified 521 and 670 significantfeatures, respectively (P < 0.05). ROC analysis revealed 58 features with AUC values above 0.70. Conclusion: This study's findings suggest that ML models, particularly the Naive Bayes algorithm, can effectively use lumbarADC map radiomics to diagnose osteoporosis. These findings could enhance early detection and treatment strategies,potentially improving patient outcomes and reducing the burden of osteoporotic fractures. This study also establishedthreshold values for significant features.