Abstract: The present application discloses a method, device, and system for processing a medical image. The method includes obtaining, by one or more processors, a first medical image, wherein the first medical image includes a representation of a target organ, and processing, by the one or more processors, the first medical image based at least in part on a first machine learning model. A classification result associated with the first medical image and a first image of a target region in the first medical image are obtained based at least in part on the processing of the first medical image using the first machine learning model.

Abstract: A superconducting generator including an armature configured to be rotated via a shaft and a stationary field disposed concentric to and radially outward from the armature. The stationary field including a superconducting field winding and a vacuum vessel having an inner wall of one of a non-magnetic material or a paramagnetic material facing the armature, an opposed outer wall of a ferromagnetic material and a plurality of sidewalls coupling the inner wall and the opposed outer wall. The superconducting field winding is disposed in the vacuum vessel. A wind turbine and method are additionally disclosed. The wind turbine includes a rotor having a plurality of blades. The wind turbine further includes a shaft coupled to the rotor. Moreover, the wind turbine includes the superconducting generator coupled to the rotor via the shaft.

Abstract: A superconducting machine includes at least one superconducting coil and a coil support structure arranged with the at least one superconducting coil. The coil support structure includes at least one composite component affixed to the at least one superconducting coil and an interface component in frictional contact with the at least one composite component so as to reduce a likelihood of quench of the at least one superconducting coil.

Abstract: A superconducting magnet apparatus includes a plurality of superconducting magnet coil sections connected in series and housed within a cryogenically cooled, vacuum container. A power source generates a current. A first lead is electrically connected to the superconducting magnet coil sections. A second lead is enclosed entirely within the vacuum container. The second lead has a first section and a second section, and the first section is electrically connected to the power source. The second section is electrically connected to the first lead, and rigidly connected to a linear displacement device enclosed entirely within the vacuum container. The linear displacement device linearly displaces the second section relative to the first section, so that the first section contacts the second section thereby electrically connecting the first and second sections, or by creating a gap between the first section and second section thereby electrically disconnecting the first section from the second section.

Abstract: A superconducting magnet includes a cooling tank containing a cooling medium and at least one superconducting circuit configured for generating a magnetic field. The superconducting magnet further includes a power supply connected to the superconducting circuit(s) for energizing the superconducting circuit(s) and a superconducting switch electrically connected across ends of the superconducting circuit(s). The superconducting switch includes a superconducting winding and a thermal conduction member having a first end thermally coupled to the superconducting winding and a second end thermally coupled to the cooling medium within the cooling tank. The thermal conduction member includes, at least, a first layer and a second layer. The first layer is constructed of a metal material having a first thermal conductivity. The second layer supports the first layer and is constructed of a material having a second thermal conductivity that is lower than the first thermal conductivity.

Abstract: The present application discloses a method, device, and system for processing a medical image. The method includes obtaining, by one or more processors, a target image, segmenting, by the one or more processors, a target region image from the target image, wherein the target region image comprises a target object region in the target image, analyzing, by the one or more processors, the target region image based at least in part on a machine learning model, and obtaining by the one or more processors, a recognition result based at least in part on the analysis of the target region image.

Abstract: An image recognition method includes: obtaining an image; extracting a target image region corresponding to a target part from the image, wherein the target image region includes a target object; determining a location of the target object in the target image region (i) according to pixel values of pixels in the target image region and a location relationship between the pixels, or (ii) inputting the target image region to a trained segmentation model to obtain the location of the target object in the target image region; and displaying a recognition result of the image, wherein the recognition result indicates the location of the target object in the target image region.

Abstract: A superconducting machine includes at least one superconducting coil and a coil support structure arranged with the at least one superconducting coil. The coil support structure includes at least one composite component affixed to the at least one superconducting coil and an interface component in frictional contact with the at least one composite component so as to reduce a likelihood of quench of the at least one superconducting coil.

Abstract: A method for detecting a rib with a medical image, a device and a medium are provided. Feature coding is performed, by using a neural network model, on different rib regions in the medical image to obtain multiple feature vectors. According to a learned corresponding relationship between rib query items and the different rib regions, a feature vector for respective rib query item is determined. Parallel decoding is performed on the feature vector for respective rib query item to obtain a rib detection result corresponding to respective rib query item. The rib query items are endowed with semantic information in anatomy, such that respective rib query items may focus on features of different rib regions, and thus realizing controllable rib detection in instance-level. Any rib detection result includes a rib prediction classification and a prediction value of a pose parameter, in a three-dimensional space, of a rib detection box.

Abstract: The present disclosure relates to using an integrated cooling circuit to provide both forced-flow pre-cooling functionality and closed-loop thermosiphon cooling for persistent mode operation of a superconducting magnet. In one embodiment, the integrated cooling circuit shares a single set of cooling tubes for use with both the forced-flow pre-cooling circuit as well as the closed-loop operating-state cooling circuit.

Abstract: A system for minimizing MGI in a superconducting magnet system of an MRI system includes a thermal shield having bi-metal material. The thermal shield is configured to be disposed about a cold mass of the superconducting magnet system, wherein the bi-metal material is configured to minimize MGI.

Abstract: A system for minimizing MGI in a superconducting magnet system of an MRI system includes a thermal shield having bi-metal material. The thermal shield is configured to be disposed about a cold mass of the superconducting magnet system, wherein the bi-metal material is configured to minimize MGI.

Abstract: A quench protection system for a superconducting machine, such as a superconducting generator having a plurality of series-arranged superconducting coils, includes at least one switch heater electrically coupled to each of the superconducting coils. A quench protection switch is provided in series with the coils, wherein each switch heater is in thermal contact with the quench protection switch. A heater network is configured in parallel with the quench protection switch and is in thermal contact with each of the coils. A quench of any one of the coils triggers a quench of the quench protection switch, wherein the heater network then triggers a quench of all of the remaining coils.

Abstract: A superconducting generator including an armature configured to be rotated via a shaft and a stationary field disposed concentric to and radially outward from the armature. The stationary field including a superconducting field winding and a vacuum vessel having an inner wall of one of a non-magnetic material or a paramagnetic material facing the armature, an opposed outer wall of a ferromagnetic material and a plurality of sidewalls coupling the inner wall and the opposed outer wall. The superconducting field winding is disposed in the vacuum vessel. A wind turbine and method are additionally disclosed. The wind turbine includes a rotor having a plurality of blades. The wind turbine further includes a shaft coupled to the rotor. Moreover, the wind turbine includes the superconducting generator coupled to the rotor via the shaft.

Abstract: A current lead assembly for minimizing heat load to a conduction cooled superconducting magnet during a ramp operation is provided. The current lead assembly includes a vacuum chamber having a through hole to enable a first end of a current lead contact to remain outside the vacuum chamber and a second end of the current lead contact to penetrate within the vacuum chamber. A vacuum boundary wall is located between the vacuum chamber and the current lead contact. At least one superconducting magnet is arranged inside of the vacuum chamber and includes a magnet lead. A second end of the current lead contact is coupled to the magnet lead via an internal lead. A vacuum cap is removably disposed to sealingly encompass therein the first end of the current lead contact during a first state of operation. The first end of the current lead contact is arranged to contact a power supply during a second state of operation, wherein the contact occurs exterior the vacuum chamber.

Abstract: Provided are techniques that may include a disposable magnetic cell isolation holder having one or more passages that accommodate a magnetic retention material to facilitate magnetic cell isolation without adjustment of magnetic field parameters between isolation procedures using different magnetic particle sizes. When the magnetic cell isolation holder is coupled to a magnetic field generator, a first passage corresponding to a smaller particle size is positioned in a magnetic field where the magnetic field characteristics are different relative to a second passage, of a second holder or in the same holder, for use with another bead size.

Abstract: A magnetic resonance imaging device is described that includes multiple magnetic coils to generate a magnetic field. Additionally, the magnetic resonance imaging device may include one or more radial gaps within some or all of the magnetic coils (e.g., primary magnetic coils, bucking coils, and so forth) in which radial spacers may be located to help preserve the homogeneity of the magnetic isocenter of the primary magnetic coils during operation.

Abstract: A persistent current switch system is presented. One embodiment of the persistent current switch system includes a vacuum chamber having a winding unit and dual cooling paths. The dual cooling paths are configured to circulate a coolant flow. The dual cooling paths are defined by a first cooling path and a second cooling path. The first cooling path includes a solid thermal component disposed in direct contact with the winding unit and the second cooling path includes a cooling tube disposed in direct contact with the winding unit and configured to circulate a coolant therein. The dual cooling paths cool the temperature of the winding unit below the threshold temperature to transition the persistent current switch system from the first mode to the second mode. A method of for cooling a winding unit in a persistent current switch system and a switching system including dual cooling paths are also disclosed.

Abstract: An image recognition method includes: obtaining an image; extracting a target image region corresponding to a target part from the image, wherein the target image region includes a target object; determining a location of the target object in the target image region (i) according to pixel values of pixels in the target image region and a location relationship between the pixels, or (ii) inputting the target image region to a trained segmentation model to obtain the location of the target object in the target image region; and displaying a recognition result of the image, wherein the recognition result indicates the location of the target object in the target image region.

Abstract: The present application discloses a method, device, and system for processing a medical image. The method includes obtaining, by one or more processors, a target image, segmenting, by the one or more processors, a target region image from the target image, wherein the target region image comprises a target object region in the target image, analyzing, by the one or more processors, the target region image based at least in part on a machine learning model, and obtaining by the one or more processors, a recognition result based at least in part on the analysis of the target region image.