Efficient and early detection of osteoporosis using trabecular region

Life time and its quality can be enhanced with early diagnosis of osteoporosis. Osteoporosis is a state of having brittle and fragile bone which arises due to vitamin deficiency, tissue loss, hormonal changes, etc. Diagnosis of osteoporosis is very important and mandatory in current scenario. Now a days Computer Aided Diagnostic (CAD) is used to detect osteoporosis more efficiently. This osteoporosis can be efficiently detected by calculating various features like Bone mineral density (BMD), statistical features from various trabecular region such as hip, toe, elbow, etc. Analysis of trabecular bounding on digital calcaneus radiographic (DCR) images will help in efficient identification of low BMD. Bone Mineral density measurement can be achieved by various segmentation methods such as K-means, Fuzzy segmentation etc. In this paper we proposed a Regression Artificial Neural Network (ANN) classifier-based computer-aided diagnosis (CAD) system for accurate osteoporotic risk detection using digital calcaneus radiographic images. The evaluation of diagnostic capability of the proposed method is to spot areas of Low Bone Mineral Density at the calcaneus region. The proposed system has achieved the highest classification accuracy of 90%, sensitivity, specificity and positive predictive value.