Enhancement of Hip X-ray with Convolutional Autoencoder for Increasing Prediction Accuracy of Bone Mineral Density.

It is very important to keep track of decreases in the bone mineral density (BMD) of elderly people since it can be correlated with the risk of incidence of major osteoporotic fractures leading to fatal injuries. Even though dual-energy X-ray absorptiometry (DXA) is the one of the most precise measuring techniques used to quantify BMD, most patients have restricted access to this machine due to high cost of DXA equipment, which is also rarely distributed to local clinics. Meanwhile, the conventional X-rays, which are commonly used for visualizing conditions and injuries due to their low cost, combine the absorption of both soft and bone tissues, consequently limiting its ability to measure BMD. Therefore, we have proposed a specialized automated smart system to quantitatively predict BMD based on a conventional X-ray image only by reducing the soft tissue effect supported by the implementation of a convolutional autoencoder, which is trained using proposed synthesized data to generate grayscale values of bone tissue alone. From the enhanced image, multiple features are calculated from the hip X-ray to predict the BMD values. The performance of the proposed method has been validated through comparison with the DXA value, which shows high consistency with correlation coefficient of 0.81 and mean absolute error of 0.069 g/cm2.

Prediction of Hole Expansion Ratio for Advanced High-Strength Steel with Image Feature Analysis of Sheared Edge.

The punching process of AHSS induces edge cracks in successive process, limiting the application of AHSS for vehicle bodies. Controlling and predicting edge quality is substantially difficult due to the large variation in edge quality, die wear induced by high strength, and the complex effect of phase distribution. To overcome this challenge, a quality prediction model that considers the variation of the entire edge should be developed. In this study, the image of the entire edge was analyzed to provide a comprehensive evaluation of its quality. Statistical features were extracted from the edge images to represent the edge quality of DP780, DP980, and MART1500 steels. Combined with punching monitoring signals, a prediction model for hole expansion ratio was developed under punch conditions of varying clearance, punch angle, and punch edge radius. It was found that the features of grayscale variation are affected by the punching conditions and are related to the double burnish and uneven burr, which degrades the edge quality. Prediction of HER was possible based on only edge image and monitoring signals, with the same performance as the prediction based solely on punching parameters and material properties. The prediction performance improved when using all the features.