Abstract: An image segmentation method is disclosed. The method includes receiving a plurality of atlases and a subject image, each atlas including an atlas image showing a structure of interest and associated structure delineations, the subject image being acquired by an image acquisition device and showing the structure of interest. The method further includes calculating, by an image processor, mapped atlases by registering the respective atlases to the subject image, and determining, by the image processor, a first structure label map for the subject image based on the mapped atlases. The method also includes training, by the image processor, a structure classifier using a subset of the mapped atlases, and determining, by the image processor, a second structure label map for the subject image by applying the trained structure classifier to one or more subject image points in the subject image.

Abstract: The present invention relates to a reactive hot melt adhesive composition, a polyurethane prepolymer composition, and cured reaction product thereof having a high mechanical strength and an excellent bonding strength as well as a better reworkability. In particular, the present invention relates to a reactive hot melt adhesive composition comprising: 10% to 24% by weight of a polyisocyanate, 40% to 73% by weight of a first polyol having a number average molecular weight larger than 1,500 g/mol, 1% to 25% by weight of a (meth)acrylate polymer having a number average molecular weight of 20,000 to 80,000 g/mol, and 1% to 15% by weight of a diluent, in which the weight percentages are based on the total weight of all components of the composition.

Abstract: A first station generates indication information of any one of an operating channel, an operating band, or an operating channel and an operating band of a wake-up receiver in a second station. The first station sends the indication information, so that the wake-up receiver in the second station works on the indicated operating channel or the indicated operating band. The first station controls the operating channel or the operating band of the wake-up receiver in the second station by generating the indication information.

Abstract: A carburized La2O3 and Lu2O3 co-doped Mo filament cathode is made from lanthanum oxide (La2O3) and lutetium oxide (Lu2O3) doped molybdenum (Mo) powders, the lanthanum oxide (La2O3) and lutetium oxide (Lu2O3) doped molybdenum (Mo) powders contain La2O3, Lu2O3 and Mo with the total concentration of La2O3 and Lu2O3 being 2.0-5.0 wt. % and the rest being Mo.

Abstract: Techniques for enhancing image segmentation with the integration of deep learning are disclosed herein. An example method for atlas-based segmentation using deep learning includes: applying a deep learning model to a subject image to identify an anatomical feature, registering an atlas image to the subject image, using the deep learning segmentation data to improve a registration result, generating a mapped atlas, and identifying the feature in the subject image using the mapped atlas. Another example method for training and use of a trained machine learning classifier, in an atlas-based segmentation process using deep learning, includes: applying a deep learning model to an atlas image, training a machine learning model classifier using data from applying the deep learning model, estimating structure labels of areas of the subject image, and defining structure labels by combining the estimated structure labels with labels produced from atlas-based segmentation on the subject image.

Abstract: Embodiments of this application relate to the field of terminal technologies, and provide a volume adjustment method and a terminal, to adaptively adjust a volume during a voice conversation, and improve user experience. A specific solution is as follows: A terminal collects sound data during a voice conversation, where the sound data includes uplink voice data and background noise; and the terminal adjusts, when receiving downlink voice data, a volume of the downlink voice data based on the sound data. The embodiments of this application are used to adjust a volume.

Abstract: Embodiments of this application provide a relay indication method and an access point (AP). The method includes: sending, by an AP, relay indication information to at least one station (STA); and further, receiving, by the AP, a reply message sent by one or more of the at least one STA. In this way, relay communication in an IoT communications system is implemented.

Abstract: Embodiments of the disclosure may be directed to an image processing system configured to receive a medical image of a region of a subject's body taken at a first time and to receive a surface image of an exterior portion of the region of the subject's body taken at the first time. The image processing may also be configured to receive a medical image of the region of the subject's body taken at a second time and to register the medical image taken at the first time, the surface image taken at the first time, and the medical image taken at the second time.

Abstract: Systems and methods are provided for generating a pseudo-CT prediction model that can be used to generate pseudo-CT images. An exemplary system may include a processor configured to retrieve training data including at least one MR image and at least one CT image for each of a plurality of training subjects. For each training subject, the processor may extract a plurality of features from each image point of the at least one MR image, create a feature vector for each image point based on the extracted features, and extract a CT value from each image point of the at least one CT image. The processor may also generate the pseudo-CT prediction model based on the feature vectors and the CT values of the plurality of training subjects.

Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.

Abstract: Systems and methods are provided for generating a pseudo-CT prediction model that can be used to generate pseudo-CT images. An exemplary system may include a processor configured to retrieve training data including at least one MR image and at least one CT image for each of a plurality of training subjects. For each training subject, the processor may extract a plurality of features from each image point of the at least one MR image, create a feature vector for each image point based on the extracted features, and extract a CT value from each image point of the at least one CT image. The processor may also generate the pseudo-CT prediction model based on the feature vectors and the CT values of the plurality of training subjects.

Abstract: A preparation method for polypeptide nano-bubbles, comprising the following steps: constructing a recombinant plasmid, which includes a Flag tag, an adipose tissue-targeting polypeptide and the coding gene of nano-bubble marker membrane protein CD63; and transfecting the recombinant plasmid into cells which secrete nano-bubbles through lipidosome for culturing, collecting a cell culture solution, and extracting the polypeptide nano-bubbles by ultracentrifugation. The present invention further discloses the polypeptide nano-bubbles and application thereof in the preparation of drugs for treating obesity. The polypeptide nano-bubbles bring great convenience for targeted therapy of anti-obesity drugs. The polypeptide nano-bubbles have good biocompatibility and are capable of carrying different kinds of bioactive substances.

Abstract: The present invention discloses a strain S. cerevisiae M 2016785 producing high concentration of ?-phenylethanol and application thereof, and belongs to the technical field of industrial microorganisms. The strain S. cerevisiae M 2016785 producing high concentration of ?-phenylethanol according to the present invention was deposited in China Center for Type Culture Collection (CCTCC) on Dec. 26, 2016 with the accession number OF CCTCC NO: M 2016785. The strain of the present invention has the high ?-phenylethanol production capacity, and is applied in the fermentation of Huangjiu, the fermentation of cooking wine, the brewing of vinegar, the fermentation of soybean sauce and the fermentation of Baijiu, in which the content of ?-phenylethanol can reach 410 mg/L, 450 mg/L, 300 mg/L, 200 mg/L, 110 mg/L and 370 mg/L respectively, and effectively increases the concentration of the flavor substance such as 2-phenylethyl acetate.

Abstract: The present disclosure relates to systems, methods, and computer-readable storage media for segmenting medical image. Embodiments of the present disclosure may locate and track a moving, three-dimensional (3D) target in a patient undergoing image-guided radiation therapy. For example, an adaptive filter model for a region of interest in the patient may be received, wherein the adaptive filter model is based on the target to be tracked. An image acquisition device may obtain a two-dimensional (2D) slice of a region of interest in the patient. A processor may then apply the adaptive filter model to the 2D slice, wherein the adaptive filter model includes an offset value. The processor may also determine a location of the target in the 2D slice based on the adaptive filter model. The processor may also estimate a potential location of the target based on the offset value. The processor may then repeat one or more of the above steps to track the moving target during image-guided radiation therapy of the patient.

Abstract: This invention relates to pharmaceutical composition and methods of using RXR agonist and/or RAR agonist for the treatment or prevention of head and neck cancer.

Abstract: Embodiments disclose a method and system for segmenting medical images. In certain embodiments, the system comprises a database configured to store a plurality of medical images acquired by an image acquisition device. The plurality of images include at least one first medical image of an object, and a second medical image of the object, each first medical image associated with a first structure label map. The system further comprises a processor that is configured to register the at least one first medical image to the second medical image, determine a classifier model using the registered first medical image and the corresponding first structure label map, and determine a second structure label map associated with the second medical image using the classifier model.

Abstract: Embodiments of this application describe a communication method, a first station (STA), a second STA, and an access point (AP). The method includes: determining, by a first STA, a first basic service set (BSS) color; generating, by the first STA, a data frame when the first station STA and a second STA perform D2D transmission, where the data frame includes the first BSS color; and sending, by the first STA, the data frame to the second STA. The first BSS color is carried in the D2D data frame, so that when receiving the data frame, another receiving station in a BSS to which the first STA and the second STA belong can determine that the frame is a frame from a neighboring cell.

Abstract: Embodiments of this application provide an information transmission method, a network device, and a user equipment. The method provided in this application includes: sending, by a network device, a broadcast frame that includes first duration information and second duration information that are of A-BFT (Association Beamforming Training); receiving a frame sent by a first user equipment in a timeslot randomly selected from a first time range; and receiving a frame sent by a second user equipment in a timeslot randomly selected from a second time range. According to the embodiments of this application, beamforming training efficiency can be improved.

Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.

Abstract: Systems and methods are provided for generating a pseudo-CT prediction model using multi-channel MR images. An exemplary system may include a processor configured to retrieve training data including multiple MR images and at least one CT image for each of a plurality of training subjects. For each training subject, the processor may determine at least one tissue parameter map based on the multiple MR images and obtain CT values based on the at least one CT image. The processor may also generate the pseudo-CT prediction model based on the tissue parameter maps and the CT values of the plurality of training subjects.