Abstract: An example method may include generating, by a computing device, a graph based on segmentation data representing a branched anatomical structure, the graph representing a plurality of possible paths to a branch of the branched anatomical structure, the plurality of possible paths comprising a plurality of additional branches. The method may further include applying, by the computing device, a graph analysis algorithm to the graph, wherein the applying the graph analysis algorithm includes generating, for a possible path of the plurality of possible paths to the branch, a path probability value based on link affinity values of pairs of the additional branches on the possible path to the branch. The method may further include classifying, by the computing device and based on the applying the graph analysis algorithm, a branch of the branched anatomical structure.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: An example method may include determining, by a computing system and based on a set of seeds determined from data representative of a labeled first tubular structure and a labeled second tubular structure in a model of at least a portion of an anatomical structure, a partitioning of the model into segments. The method may further include outputting, by the computing system, data representative of the segments.

Abstract: A high-temperature-resistant and oxidation-resistant light-weight heat-insulation foam material and a preparation method thereof. The foam material is one of a SiBCN foam material, a SiHfBCN foam material, a SiBCN/C composite foam material and a SiHfBCN/C composite foam material. The foam material is prepared from a precursor solution through processes of template impregnation, curing, drying and cracking; wherein the precursor solution is a SiBCN precursor solution or a SiHfBCN precursor solution, and the template is a polyurethane foam or an organic carbon-modified polyurethane foam. The SiBCN foam material, SiHfBCN foam material, SiBCN/C composite foam material or SiHfBCN/C composite foam material obtained by the present application has the advantages of high temperature resistance, a low thermal conductivity, oxidation resistance, a low density and a high strength.

Abstract: An exemplary system accesses a three-dimensional (3D) model of an anatomical structure, applies a first detection process to the 3D model to detect a single-layer anatomical feature in the anatomical structure, applies a second detection process, different from the first detection process, to the 3D model to detect a non-single-layer anatomical feature in the anatomical structure, and provides a representation of the anatomical structure based on the 3D model, the detected single-layer anatomical structure, and the detected non-single-layer anatomical structure. In some implementations, the representation of the anatomical structure and a representation of a potential path to be traversed by a medical instrument in the anatomical structure are displayed.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: An exemplary processing system accesses a three-dimensional (3D) model of an anatomical structure of a patient and applies a detection process to the 3D model to detect a single-layer anatomical feature in the anatomical structure. The detection process includes generating, from the 3D model, a probability map of candidate points for the single-layer anatomical feature, and generating, based on the probability map of candidate points, a single-layer mesh representing the single-layer anatomical feature.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting at least one of a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The weighting that at least one of the plurality of volumetric units includes applying a weight based on a foreground structure classification. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: Provided are a porous silicone resin and a light-weight flexible flame-retardant composite material, belonging to the technical field of nano-porous materials. The porous silicon resin is prepared from a porous silicon resin precursor solution by means of curing and drying processes. The porous silicone resin precursor solution includes a flame retardant, a surfactant, a siloxane monomer, a catalyst, an auxiliary agent and a solvent. The porous silicone resin precursor solution is obtained by firstly dissolving the flame retardant and the surfactant in the solvent, and then adding the siloxane monomer, the catalyst and the auxiliary agent and mixing them uniformly. The porous silicone resin and the light-weight flexible flame-retardant composite material prepared therefrom have the excellent properties of high porosity, high flame retardancy, high elasticity and high strain.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: An exemplary processing system accesses a three-dimensional (3D) model of an anatomical structure of a patient and applies a detection process to the 3D model to detect a single-layer anatomical feature in the anatomical structure. The detection process includes generating, from the 3D model, a probability map of candidate points for the single-layer anatomical feature, and generating, based on the probability map of candidate points, a single-layer mesh representing the single-layer anatomical feature.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.

Abstract: A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.