Automatic assessment of femoral bone quality in specific regions of interest using texture features

The assessment of local bone quality for the surgical intervention after femoral neck fractures is a crucial task for the operating surgeon prior to the intervention. Unsatisfying results of surgical interventions like early loosening of implants may be one result of altered bone quality. Nowadays clinical diagnostic techniques to quantify local bone quality are limited and often highly observer dependent. Therefore, the development of tools, which reproducibly place regions of interest (ROIs) and asses the local bone quality, would be a significant improvement for surgical planning. In this paper the placement of regions of interest will be analyzed using method, which assesses the femur quality by using co-occurrence matrices to calculate texture features. For this purpose, the texture features of 15 CT-datasets of anatomical specimen of human femora are calculated within 11 different ROIs are analyzed. Performing statistical analysis the majority of all defined ROIs, especially in the area of the femoral neck, show a highly significant correlation between the calculated features and a specific biomechanical property of the proximal femur.