Non-invasive Methodological Techniques to Determine Health of a Bone

Khare, Meghana R.; Havaldar, Raviraj

doi:10.1007/978-3-030-69921-5_34

Cited by 1 publication

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the guidelines of the National Osteoporosis Foundation, the indications for DEXA examination are: (a) women 65 years old and men 70 years and older, (b) postmenopausal women and men over 50 who have suffered bone fractures, and (c) adults who suffer from rheumatoid arthritis or use medications such as glucocorticoids and have low bone mass [2,3,11]. However, DEXA scans do not give any information regarding the bone microarchitecture and mechanical properties, which are also crucial factors in bone resistance to fracture [12,13]. To obtain these factors, other non-invasive methods such as conventional radiology, computed tomography, magnetic resonance imaging (MRI), and ultrasound have been investigated [14,15].…”

Section: Introductionmentioning

confidence: 99%

Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation

Najafi,

Yousefi Rezaii,

Danishvar

et al. 2023

Sensors

View full text Add to dashboard Cite

The aim of this study was to use geometric features and texture analysis to discriminate between healthy and unhealthy femurs and to identify the most influential features. We scanned proximal femoral bone (PFB) of 284 Iranian cases (21 to 83 years old) using different dual-energy X-ray absorptiometry (DEXA) scanners and magnetic resonance imaging (MRI) machines. Subjects were labeled as “healthy” (T-score > −0.9) and “unhealthy” based on the results of DEXA scans. Based on the geometry and texture of the PFB in MRI, 204 features were retrieved. We used support vector machine (SVM) with different kernels, decision tree, and logistic regression algorithms as classifiers and the Genetic algorithm (GA) to select the best set of features and to maximize accuracy. There were 185 participants classified as healthy and 99 as unhealthy. The SVM with radial basis function kernels had the best performance (89.08%) and the most influential features were geometrical ones. Even though our findings show the high performance of this model, further investigation with more subjects is suggested. To our knowledge, this is the first study that investigates qualitative classification of PFBs based on MRI with reference to DEXA scans using machine learning methods and the GA.

show abstract