This paper suggests a new technique for trabecular bone characterization using fractal analysis of X‐Ray and MRI texture images for osteoporosis diagnosis. Osteoporosis is a chronic disease characterized by a decrease in bone density that can lead to fracture and disability. In essence, the proposed fractal model makes use of the differential box‐counting method (DBCM) to estimate the fractal dimension (FD) after an appropriate image preprocessing stage that ensures a robust estimation process. In this study, we showed that within the frequency domain generated through discrete cosine transform (DCT), only a quarter of DCT coefficients are enough to characterize osteoporotic tissues. The algorithmic complexity of the developed approach is of the order of N8log2N8 where N stands for the size of the image, which, in turn, likely yields important gain in terms of medication cost. We report a successful separation of healthy and pathological cases in term of both P − value (using statistical Wilcoxon rank sum test) and margin difference. A comparative statistical analysis has been performed using a publicly available database that contains a set of MRI and X‐Ray texture images of both healthy and osteoporotic bone tissues. The statistical results demonstrated the feasibility and accepted performance level of our fractal model‐based diagnosis to discriminate healthy and unhealthy trabecular bone tissues. The developed approach has been implemented on a medical device prototype.
The present paper deals with breast tumors classification from ultrasound images. The proposed procedure consists of four steps, namely preprocessing, segmentation, feature extraction and classification. To improve the quality of ultrasound images, the preprocessing step consists of anisotropic filtering and histogram equalization that are performed on the original images. The segmentation is performed on the preprocessed images using the Level Set method that allows to extract the region of interest (ROI) and to reduce its size at the same time. Two feature extraction methods are used in this work namely, the local binary pattern (LBP) method and the histogram of oriented gradients (HOG) method. The two methods (LBP and HOG) are techniques of textures analysis and allow to characterize the ROI. The extracted feature sets constitute the inputs for three classifiers namely, support vector machines (SVM), k-nearest neighbors (KNN) and decision trees (DT). In this work, the best results are obtained by the concatenation of the two feature vectors namely LBP and HOG associated to the SVM classifier. This allows to achieve an accuracy of 96%, a sensitivity of 97% and a specificity of 94%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.