Abstract: A self-supervised machine learning method and system for learning visual representations in medical images. The system receives a plurality of medical images of similar anatomy, divides each of the plurality of medical images into its own sequence of non-overlapping patches, wherein a unique portion of each medical image appears in each patch in the sequence of non-overlapping patches. The system then randomizes the sequence of non-overlapping patches for each of the plurality of medical images, and randomly distorts the unique portion of each medical image that appears in each patch in the sequence of non-overlapping patches for each of the plurality of medical images. Thereafter, the system learns, via a vision transformer network, patch-wise high-level contextual features in the plurality of medical images, and simultaneously, learns, via the vision transformer network, fine-grained features embedded in the plurality of medical images.

Abstract: The system receives a plurality of medical images and integrates Self-Supervised machine Learning (SSL) instructions for performing a discriminative learning operation, a restorative learning operation, and an adversarial learning operation into a model for processing the received plurality of medical images. The model is configured with each of a discriminative encoder, a restorative decoder, and an adversarial encoder. Each of the discriminative encoder and the restorative decoder are configured to be skip connected, forming an encoder-decoder.

Abstract: The present disclosure discloses a protective case capable of being flipped to achieve supporting and capable of adjusting flipping and rotating angles, including a back plate, and a supporting component and a rotating mechanism which are mounted on the back plate. According to the present disclosure, in the horizontal rotating mechanism, horizontal rotation is achieved by mutual cooperation between only one annular rotating member and the rotating slot of the back plate, so that the protective case is simple in structure, easy to mount, and low in later maintenance rate; and furthermore, through the arrangement of a supporting positioning component, tangent planes that form angles are arranged on two shaft sleeves and the rotating shaft, so that the flippable supporting member can achieve mutually pressed rotation during flipping, and the flippable supporting member can be flipped and positioned in an angle.

Abstract: Described herein are means for generation of self-taught generic models, named Models Genesis, without requiring any manual labeling, in which the Models Genesis are then utilized for the processing of medical imaging. For instance, an exemplary system is specially configured for learning general-purpose image representations by recovering original sub-volumes of 3D input images from transformed 3D images. Such a system operates by cropping a sub-volume from each 3D input image; performing image transformations upon each of the sub-volumes cropped from the 3D input images to generate transformed sub-volumes; and training an encoder-decoder architecture with skip connections to learn a common image representation by restoring the original sub-volumes cropped from the 3D input images from the transformed sub-volumes generated via the image transformations.

Abstract: Described herein are means for training a deep model to learn contrastive representations embedded within part-whole semantics via a self-supervised learning framework, in which the trained deep models are then utilized for the processing of medical imaging. For instance, an exemplary system is specifically configured for performing a random cropping operation to crop a 3D cube from each of a plurality of medical images received at the system as input; performing a resize operation of the cropped 3D cubes; performing an image reconstruction operation of the resized and cropped 3D cubes to predict the resized whole image represented by the original medical images received; and generating a reconstructed image which is analyzed for reconstruction loss against the original image representing a known ground truth image to the reconstruction loss function. Other related embodiments are disclosed.

Abstract: An electronic device for processing real-time-streaming-protocol (RTSP) packets in a network to provide enhanced video-on-demand (VOD) services is provided. The electronic device includes a user interface, a non-transitory memory configured to store instructions including an application layer gateway (ALG) module and network service software, and a hardware processor. The hardware processor is configured to execute the instructions to store a list of mac-bridge clients that includes a MAC address and a MAC mask corresponding to each mac-bridge client, and determine whether at least one of the source and destination MAC address of a received RTSP packet is on the list. When at least one of the source and destination MAC address is on the list, the RTSP packet is processed using the network service software and a next RTSP packet is received; otherwise, the received RTSP packet is processed using the ALG module.

Abstract: Some aspects of the present publication relate to a cable modem, i.e. CM, comprising a memory unit, in which instructions are saved, and a processor. The processor is configured to execute the instructions saved in said memory unit so that said electronic device executes the following operations: Receiving special service flow configuration information; said special service flow configuration information comprises information, which is configured by users and used for enabling the establishment of special service flows with one or a plurality of client stations connected with the CM; and establishing said special service flows with the cable modem terminal system, i.e. the CMTS, using the dynamic service flow technology based on said special service flow configuration information; said special service flows are only used for the communication with said one or plurality of client stations.

Abstract: Described herein are systems, methods, and apparatuses for implementing self-supervised domain-adaptive pre-training via a transformer for use with medical image classification in the context of medical image analysis.

Abstract: Described herein are means for learning semantics-enriched representations via self-discovery, self-classification, and self-restoration in the context of medical imaging. Embodiments include the training of deep models to learn semantically enriched visual representation by self-discovery, self-classification, and self-restoration of the anatomy underneath medical images, resulting in a collection of semantics-enriched pre-trained models, called Semantic Genesis. Other related embodiments are disclosed.

Abstract: A Discriminative, Restorative, and Adversarial (DiRA) learning framework for self-supervised medical image analysis is described. For instance, a pre-trained DiRA framework may be applied to diagnosis and detection of new medical images which form no part of the training data. The exemplary DiRA framework includes means for receiving training data having medical images therein and applying discriminative learning, restorative learning, and adversarial learning via the DiRA framework by cropping patches from the medical images; inputting the cropped patches to the discriminative and restorative learning branches to generate discriminative latent features and synthesized images from each; and applying adversarial learning by executing an adversarial discriminator to perform a min-max function for distinguishing the synthesized restorative image from real medical images. The pre-trained model of the DiRA framework is then provided as output for use in generating predictions of disease within medical images.

Abstract: A self-supervised learning framework for empowering instance discrimination in medical imaging using Context-Aware instance Discrimination (CAiD), in which the trained deep models are then utilized for the processing of medical imaging. An exemplary system receives a plurality of medical images; trains a self-supervised learning framework to increasing instance discrimination for medical imaging using a Context-Aware instance Discrimination (CAiD) model using the received plurality of medical images; generates multiple cropped image samples and augments samples using image distortion; applies instance discrimination learning a mapping back to a corresponding original image; reconstructs the cropped image samples and applies an auxiliary context-aware learning loss operation; and generates as output, a pre-trained CAiD model based on the application of both (i) the instance discrimination learning and (ii) the auxiliary context-aware learning loss operation.

Abstract: An electronic device for processing real-time-streaming-protocol (RTSP) packets in a network to provide enhanced video-on-demand (VOD) services is provided. The electronic device includes a user interface, a non-transitory memory configured to store instructions including an application layer gateway (ALG) module and network service software, and a hardware processor. The hardware processor is configured to execute the instructions to store a list of mac-bridge clients that includes a MAC address and a MAC mask corresponding to each mac-bridge client, and determine whether at least one of the source and destination MAC address of a received RTSP packet is on the list. When at least one of the source and destination MAC address is on the list, the RTSP packet is processed using the network service software and a next RTSP packet is received; otherwise, the received RTSP packet is processed using the ALG module.

Abstract: Described herein are means for implementing systematic benchmarking analysis to improve transfer learning for medical image analysis.

Abstract: Described herein are means for systematically determining an optimal approach for the computer-aided diagnosis of a pulmonary embolism, in the context of processing medical imaging. According to a particular embodiment, there is a system specially configured for diagnosing a Pulmonary Embolism (PE) within new medical images which form no part of the dataset upon which the AI model was trained.

Abstract: Described herein are means for generating pre-trained models for nnU-Net through the use of improved transfer learning techniques, in which the pre-trained models are then utilized for the processing of medical imaging.

Abstract: The present disclosure relates to an access point, a method, a medium, and a computer program product for the access point.

Abstract: Described herein are means for implementing annotation-efficient deep learning models utilizing sparsely-annotated or annotation-free training, in which trained models are then utilized for the processing of medical imaging. An exemplary system includes at least a processor and a memory to execute instructions for learning anatomical embeddings by forcing embeddings learned from multiple modalities; initiating a training sequence of an AI model by learning dense anatomical embeddings from unlabeled date, then deriving application-specific models to diagnose diseases with a small number of examples; executing collaborative learning to generate pretrained multimodal models; training the AI model using zero-shot or few-shot learning; embedding physiological and anatomical knowledge; embedding known physical principles refining the AI model; and outputting a trained AI model for use in diagnosing diseases and abnormal conditions in medical imaging. Other related embodiments are disclosed.

Abstract: Embodiments described herein include systems for implementing annotation-efficient deep learning in computer-aided diagnosis.

Abstract: Described herein are means for the generation of Transferable Visual Word (TransVW) models through self-supervised learning in the absence of manual labeling, in which the trained TransVW models are then utilized for the processing of medical imaging.

Abstract: Described herein are systems, methods, and apparatuses for actively and continually fine-tuning convolutional neural networks to reduce annotation requirements, in which the trained networks are then utilized in the context of medical imaging. The success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, it is tedious, laborious, and time consuming to create large annotated datasets, and demands costly, specialty-oriented skills. A novel method to naturally integrate active learning and transfer learning (fine-tuning) into a single framework is presented to dramatically reduce annotation cost, starting with a pre-trained CNN to seek “worthy” samples for annotation and gradually enhances the (fine-tuned) CNN via continual fine-tuning.