2D/3D deformable registration for endoscopic camera images using self-supervised offline learning of intraoperative pneumothorax deformation.

Shape registration of patient-specific organ shapes to endoscopic camera images is expected to be a key to realizing image-guided surgery, and a variety of applications of machine learning methods have been considered. Because the number of training data available from clinical cases is limited, the use of synthetic images generated from a statistical deformation model has been attempted; however, the influence on estimation caused by the difference between synthetic images and real scenes is a problem. In this study, we propose a self-supervised offline learning framework for model-based registration using image features commonly obtained from synthetic images and real camera images. Because of the limited number of endoscopic images available for training, we use a synthetic image generated from the nonlinear deformation model that represents possible intraoperative pneumothorax deformations. In order to solve the difficulty in estimating deformed shapes and viewpoints from the common image features obtained from synthetic and real images, we attempted to improve the registration error by adding the shading and distance information that can be obtained as prior knowledge in the synthetic image. Shape registration with real camera images is performed by learning the task of predicting the differential model parameters between two synthetic images. The developed framework achieved registration accuracy with a mean absolute error of less than 10 mm and a mean distance of less than 5 mm in a thoracoscopic pulmonary cancer resection, confirming improved prediction accuracy compared with conventional methods.

Principal Vibration Modes of the La2O3-Ga2O3 Binary Glass Originated from Diverse Coordination Environments of Oxygen Atoms.

La2O3-Ga2O3 binary glass exhibits unusual optical properties owing to its high oxygen polarizability and low vibration energy. These optical properties include high refractive indices and a wide transmittance range. In this study, we performed classical molecular dynamics simulations on La2O3-Ga2O3 glass synthesized by an aerodynamic levitation technique. We have obtained structural models that reproduce experimental results, such as NMR, high-energy X-ray diffraction, and neutron diffraction. Based on our analysis, the structural features were clarified: 5-, 6-coordinated Ga, edge-sharing GaOx-GaOx polyhedral linkages, and oxygen triclusters. Additionally, the vibrational density of states was calculated by diagonalization of the dynamical matrix derived from the structural models and the results were compared with Raman scattering spectra. The mode analysis of the Raman spectra revealed that the principal bands at 650 cm-1 were mainly attributed to the stretching modes of the bridging and nonbridging oxygens. Meanwhile, the shoulder bands at the highest frequency of 750 cm-1 were mainly attributed to the stretching modes of the bridging oxygens and oxygen triclusters. The structural models obtained in this study well describe the characteristic local structures and vibrational properties of the La2O3-Ga2O3 glass.