Abstract: Not only is annotating medical images tedious and time consuming, but it also demands costly, specialty-oriented expertise, which is not easily accessible. To address this challenge, a new self-supervised framework is introduced: TransVW (transferable visual words), exploiting the prowess of transfer learning with convolutional neural networks and the unsupervised nature of visual word extraction with bags of visual words, resulting in an annotation-efficient solution to medical image analysis. TransVW was evaluated using NIH ChestX-ray14 to demonstrate its annotation efficiency. When compared with training from scratch and ImageNet-based transfer learning, TransVW reduces the annotation efforts by 75% and 12%, respectively, in addition to significantly accelerating the convergence speed. More importantly, TransVW sets new records: achieving the best average AUC on all 14 diseases, the best individual AUC scores on 10 diseases, and the second best individual AUC scores on 3 diseases.

Abstract: Described herein are means for implementing medical image segmentation using interactive refinement, in which the trained deep models are then utilized for the processing of medical imaging.

Abstract: Described herein are means for generating source models for transfer learning to application specific models used in the processing of medical imaging.

Abstract: Methods, systems, and media for segmenting images are provided. In some embodiments, the method comprises: generating an aggregate U-Net comprised of a plurality of U-Nets, wherein each U-Net in the plurality of U-Nets has a different depth, wherein each U-Net is comprised of a plurality of nodes Xi,j, wherein i indicates a down-sampling layer the U-Net, and wherein j indicates a convolution layer of the U-Net; training the aggregate U-Net by: for each training sample in a group of training samples, calculating, for each node in the plurality of nodes Xi,j, a feature map xi,j, wherein xi,j is based on a convolution operation performed on a down-sampling of an output from Xi?1,j when j=0, and wherein xi,j is based on a convolution operation performed on an up-sampling operation of an output from Xi+1,j?1 when j>0; and predicting a segmentation of a test image using the trained aggregate U-Net.

Abstract: Described herein are means for implementing contrastive learning via reconstruction within 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 specially 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 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: A ceiling fan has a motor and multiple fan blades. The motor has a stator assembly and a rotor assembly. The stator frame has a frame, a stator core, and multiple coils. The frame has multiple branch containers and multiple protrusions on the branch containers. The stator core is securely mounted in the frame. The coils are wound on the branch containers and protrusions. Therefore, the coils may be an ellipse and thus the magnetic flux therein is larger, which converts electric energy torques to drive the rotor assembly in higher efficiency. Besides, the rotor has multiple magnetic components and each magnetic component has a magnetic pole. An amount of the magnetic poles is larger than that of the branch containers. The motor can provide a higher torque even at a lower rotating speed.

Abstract: Described herein are means for implementing fixed-point image-to-image translation using improved Generative Adversarial Networks (GANs). For instance, an exemplary system is specially configured for implementing a new framework, called a Fixed-Point GAN, which improves upon prior known methodologies by enhancing the quality of the images generated through global, local, and identity transformation. The Fixed-Point GAN as introduced and described herein, improves many applications dependant on image-to-image translation, including those in the field of medical image processing for the purposes of desease detection and localization. Other related embodiments are disclosed.

Abstract: A method for control of a soft generic routing encapsulation (GRE) tunnel based on client activity includes: receiving a data packet from a first external; storing an identifier associated with the first external device in a client table and a corresponding timestamp associated with receipt of the data packet; creating a soft GRE tunnel between a local interface of the computing device and a remote gateway; updating the client table, wherein updating the client table includes adding a new identifier and corresponding timestamp associated with additional external devices upon receipt of respective data packets, and updating the timestamp corresponding to the respective identifier upon receipt of an additional packet from an additional external device; and halting a GRE health-check process associated with the soft GRE tunnel once a predetermined period of time has elapsed since the timestamp corresponding to each identifier stored in the client table.

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: Described herein are means for the generation of semantic genesis models through self-supervised learning in the absence of manual labeling, in which the trained semantic genesis models are then utilized for the processing of medical imaging.

Abstract: Methods, systems, and media for discriminating and generating translated images are provided. In some embodiments, the method comprises: identifying a set of training images, wherein each image is associated with at least one domain from a plurality of domains; training a generator network to generate: i) a first fake image that is associated with a first domain; and ii) a second fake image that is associated with a second domain; training a discriminator network, using as inputs to the discriminator network: i) an image from the set of training images; ii) the first fake image; and iii) the second fake image; and using the generator network to generate, for an image not included in the set of training images at least one of: i) a third fake image that is associated with the first domain; and ii) a fourth fake image that is associated with the second domain.

Abstract: Disclosed are provided systems, methods, and apparatuses for implementing a multi-resolution neural network for use with imaging intensive applications including medical imaging. For example, a system having means to execute a neural network model formed from a plurality of layer blocks including an encoder layer block which precedes a plurality of decoder layer blocks includes: means for associating a resolution value with each of the plurality of layer blocks; means for processing via the encoder layer block a respective layer block input including a down-sampled layer block output processing, via decoder layer blocks, a respective layer block input including an up-sampled layer block output and a layer block output of a previous layer block associated with a prior resolution value of a layer block which precedes the respective decoder layer block; and generating the respective layer block output by summing or concatenating the processed layer block inputs.

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 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: Detecting a pulmonary embolism (PE) in an image dataset of a blood vessel involves obtaining a volume of interest (VOI) in the blood vessel, generating a plurality of PE candidates within the VOI, generating a set of voxels for each PE candidate, estimating for each PE candidate an orientation of the blood vessel that contains the PE candidate, given the set of voxels for the PE candidate, and generating a visualization of the blood vessel that contains the PE candidate using the estimated orientation of the blood vessel that contains the PE candidate.

Abstract: Not only is annotating medical images tedious and time consuming, but it also demands costly, specialty-oriented expertise, which is not easily accessible. To address this challenge, a new self-supervised framework is introduced: TransVW (transferable visual words), exploiting the prowess of transfer learning with convolutional neural networks and the unsupervised nature of visual word extraction with bags of visual words, resulting in an annotation-efficient solution to medical image analysis. TransVW was evaluated using NIH ChestX-ray14 to demonstrate its annotation efficiency. When compared with training from scratch and ImageNet-based transfer learning, TransVW reduces the annotation efforts by 75% and 12%, respectively, in addition to significantly accelerating the convergence speed. More importantly, TransVW sets new records: achieving the best average AUC on all 14 diseases, the best individual AUC scores on 10 diseases, and the second best individual AUC scores on 3 diseases.

Abstract: A method for control of a soft generic routing encapsulation (GRE) tunnel based on client activity includes: receiving a data packet from a first external; storing an identifier associated with the first external device in a client table and a corresponding timestamp associated with receipt of the data packet; creating a soft GRE tunnel between a local interface of the computing device and a remote gateway; updating the client table, wherein updating the client table includes adding a new identifier and corresponding timestamp associated with additional external devices upon receipt of respective data packets, and updating the time stamp corresponding to the respective identifier upon receipt of an additional packet from an additional external device; and halting a GRE health-check process associated with the soft GRE tunnel once a predetermined period of time has elapsed since the timestamp corresponding to each identifier stored in the client table.

Abstract: Methods, systems, and media for selecting candidates for annotation for use in training classifiers are provided. In some embodiments, the method comprises: identifying, for a trained Convolutional Neural Network (CNN), a group of candidate training samples, wherein each candidate training sample includes a plurality of patches; for each patch of the plurality of patches, determining a plurality of probabilities, each probability being a probability that the patch corresponds to a label of a plurality of labels; identifying a subset of the patches in the plurality of patches; for each patch in the subset of the patches, calculating a metric that indicates a variance of the probabilities assigned to each patch; selecting a subset of the candidate training samples based on the metric; labeling candidate training samples in the subset of the candidate training samples by querying an external source; and re-training the CNN using the labeled candidate training samples.

Abstract: Mechanisms for simultaneously monitoring colonoscopic video quality and detecting polyps in colonoscopy are provided. In some embodiments, the mechanisms can include a quality monitoring system that uses a first trained classifier to monitor image frames from a colonoscopic video to determine which image frames are informative frames and which image frames are non-informative frames. The informative image frames can be passed to an automatic polyp detection system that uses a second trained classifier to localize and identify whether a polyp or any other suitable object is present in one or more of the informative image frames.

Abstract: Methods, systems, and media for segmenting images are provided. In some embodiments, the method comprises: generating an aggregate U-Net comprised of a plurality of U-Nets, wherein each U-Net in the plurality of U-Nets has a different depth, wherein each U-Net is comprised of a plurality of nodes Xi,j, wherein i indicates a down-sampling layer the U-Net, and wherein j indicates a convolution layer of the U-Net; training the aggregate U-Net by: for each training sample in a group of training samples, calculating, for each node in the plurality of nodes Xi,j, a feature map xi,j, wherein xi,j is based on a convolution operation performed on a down-sampling of an output from Xi?1,j when j=0, and wherein xi,j is based on a convolution operation performed on an up-sampling operation of an output from Xi+1,j?1 when j>0; and predicting a segmentation of a test image using the trained aggregate U-Net.