2D–3D reconstruction of distal forearm bone from actual X-ray images of the wrist using convolutional neural networks

The purpose of the study was to develop a deep learning network for estimating and constructing highly accurate 3D bone models directly from actual X-ray images and to verify its accuracy. The data used were 173 computed tomography (CT) images and 105 actual X-ray images of a healthy wrist joint. To compensate for the small size of the dataset, digitally reconstructed radiography (DRR) images generated from CT were used as training data instead of actual X-ray images. The DRR-like images were generated from actual X-ray images in the test and adapted to the network, and high-accuracy estimation of a 3D bone model from a small data set was possible. The 3D shape of the radius and ulna were estimated from actual X-ray images with accuracies of 1.05 ± 0.36 and 1.45 ± 0.41 mm, respectively.

Accuracy estimation of the absolute phase recovery in interferometric synthesized aperture radars data processing.

The problem of accuracy estimation of the absolute phase recovery in interferometric synthesized aperture radars (InSAR) data processing is considered. A method for accuracy estimation based on the calculation of the standard deviation of the reference phases and the absolute phases measured by the interferometric system in the radar image coordinate system "azimuth – slant range" is developed. The method includes converting the coordinates of the reference topographic height marks from the geographical coordinate system to the radar image coordinate system and then calculating of the transformation parameters between the reference heights and the measured absolute phases using the least squares method. The latter allows one to evaluate the performing effectiveness of individual stages of interferometric processing (multilooking, phase noise suppression, phase unwrapping) and experimentally determine the most effective processing algorithms that provide the best accuracy of the phase recovery and their optimal parameters. The method is tested using the ALOS PALSAR radar images obtained under various imaging conditions.