Abstract: For uncertainty estimation for a machine-learned model prediction in medical imaging, a distribution in latent space is sampled to determine uncertainty in machine-learned model prediction. For example, a segmentation is output by a machine-learned model in response to input of multi-parametric data. A latent space generated by the machine-learned model is used to estimate the uncertainty of the segmentation, such as a segmentation of a prostate lesion. The model of Kohl, et al., may be used as the variational auto encoder generates a latent space representing the distribution of the training data, which latent space may be used to determine uncertainty.

Abstract: Systems and methods for determining whether input medical images are out-of-distribution of training images on which a machine learning based medical imaging analysis network is trained are provided. One or more input medical images of a patient are received. One or more reconstructed images of the one or more input medical images are generated using a machine learning based reconstruction network. It is determined whether the one or more input medical images are out-of-distribution from training images on which a machine learning based medical imaging analysis network is trained based on the one or more input medical images and the one or more reconstructed images. The determination of whether the one or more input medical images are out-of-distribution from the training images is output.

Abstract: A planetary transmission device with a small tooth number difference for implementing smart workload self-adaptation comprises a left planetary gear, a right planetary gear, a left-end disk, a right-end disk, a housing and a connection member. One end of the connection member axially run through the left planetary gear and the right planetary gear. End parts of both ends of the connection member are fixedly connected to the left-end disk and the right-end disk respectively. By means of a force closure mechanism, the transmission device can automatically and steplessly adjust a transmission ratio and an output rotation speed according to a change in load without depending on a measurement md control system, md has a simple structure and low costs.

Abstract: A planetary transmission device with a small tooth number difference for implementing smart workload self-adaptation comprises a left planetary gear (5), a right planetary gear (2), a left-end disk (4), a right-end disk (1), a housing (3) and a connection member (8). One end of the connection member (8) axially runs through the left planetary gear (5) and the right planetary gear (2). End parts of both ends of the connection member (8) are fixedly connected to the left-end disk (4) and the right-end disk (1) respectively. The left planetary gear (5) is engaged with both the tooth profile on the left-end disk (4) and the tooth profile on the housing (3). The right planetary gear (2) is engaged with the tooth profile on the right-end disk (1) and the tooth profile on the housing (3). The left planetary gear (5), the right planetary gear (2), the left-end disk (4), the right-end disk (1) and the housing (3) form a force closure mechanism.