Introduction To explore and evaluate the performance of MRI‐based brain tumor super‐resolution generative adversarial network (MRBT‐SR‐GAN) for improving the MRI image resolution in brain tumors. Methods A total of 237 patients from December 2018 and April 2020 with T2‐fluid attenuated inversion recovery (FLAIR) MR images (one image per patient) were included in the present research to form the super‐resolution MR dataset. The MRBT‐SR‐GAN was modified from the enhanced super‐resolution generative adversarial networks (ESRGAN) architecture, which could effectively recover high‐resolution MRI images while retaining the quality of the images. The T2‐FLAIR images from the brain tumor segmentation (BRATS) dataset were used to evaluate the performance of MRBT‐SR‐GAN contributed to the BRATS task. Results The super‐resolution T2‐FLAIR images yielded a 0.062 dice ratio improvement from 0.724 to 0.786 compared with the original low‐resolution T2‐FLAIR images, indicating the robustness of MRBT‐SR‐GAN in providing more substantial supervision for intensity consistency and texture recovery of the MRI images. The MRBT‐SR‐GAN was also modified and generalized to perform slice interpolation and other tasks. Conclusions MRBT‐SR‐GAN exhibited great potential in the early detection and accurate evaluation of the recurrence and prognosis of brain tumors, which could be employed in brain tumor surgery planning and navigation. In addition, this technique renders precise radiotherapy possible. The design paradigm of the MRBT‐SR‐GAN neural network may be applied for medical image super‐resolution in other diseases with different modalities as well.

The cartilage surface geometry of natural human hip joint is commonly regarded as sphere. It has been widely applied in computational simulation and hip joint prosthesis design. Some new geometry models have been developed and the sphere assumption has been questioned recently. The objective of this study was to analyze joint geometry effects on cartilage contact stress distribution and investigate contact patterns during a whole gait cycle. Hip surface was reconstructed from CT data of a healthy volunteer. Three finite element (FE) models of hip joint were developed from different cartilage geometries: natural geometry, sphere and rotational ellipsoid. Loads at ten instants of gait cycle were applied to these models based on published in-vivo data. FE predictions of peak contact pressure during gait of natural hip were compared with sphere and rotational ellipsoid replaced hip joint. Contact occurs mainly in upper anterior region of both acetabulum and femur distributing along sagittal plane of human body. It moves towards inferolateral aspect as the resultant joint reaction force changes during walking for natural hip. Peak pressures at the instant with maximum contact force were 7.48 MPa, 14.97 MPa and 13.12 MPa for models with natural hip surface, sphere replaced and rotational ellipsoid replaced surface respectively. During the whole gait cycle, contact pressure of natural hip ranked lowest in most of the instants, followed by rotational ellipsoid replaced and sphere replaced hip. The results indicate that rotational ellipsoid is more consistent with natural hip cartilage geometry than sphere during normal walking. This means rotational ellipsoid prosthesis could give a better description of physiological structure compared with standard sphere prosthesis. Therefore, rotational ellipsoid would be a better choice for prosthesis design.

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity issue in existing vision-and-language navigation datasets, we propose an effective paradigm for generating large-scale data for learning, which applies 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instructiontrajectory pairs using fully-accessible resources on the web. Importantly, we investigate the influence of each component in this paradigm on the agent's performance and study how to adequately apply the augmented data to pre-train and fine-tune an agent. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning. The long-lasting generalization gap between navigating in seen and unseen environments is also reduced to less than 1% (versus 8% in the previous best method). Moreover, our paradigm also facilitates different models to achieve new state-of-the-art navigation results on CVDN, REVERIE, and R2R in continuous environments.