Abstract: The present disclosure provides a method, a device, and a computer program product using a self-supervised anatomical embedding (SAM) method.

Abstract: A method of harvesting lesion annotations includes conditioning a lesion proposal generator (LPG) based on a first two-dimensional (2D) image set to obtain a conditioned LPG, including adding lesion annotations to the first 2D image set to obtain a revised first 2D image set, forming a three-dimensional (3D) composite image according to the revised first 2D image set, reducing false-positive lesion annotations from the revised first 2D image set according to the 3D composite image to obtain a second-revised first 2D image set, and feeding the second-revised first 2D image set to the LPG to obtain the conditioned LPG, and applying the conditioned LPG to a second 2D image set different than the first 2D image set to harvest lesion annotations.

Abstract: An image processing method and apparatus, a device, and a non-transitory computer-readable storage medium are provided. In the method, a first feature map is obtained based on feature-encoding of an original image. A second feature map of the original image is obtained based on the first feature map. The second feature map includes noise information to be superimposed on the original image. A third feature map of the original image is obtained based on the first feature map. The third feature map includes different feature values. Each feature value represents a relative importance of an image feature at a position corresponding to the respective feature value. A noise image is generated based on the second feature map and the third feature map.

Abstract: A semiconductor package includes a die pad having a die attach surface, a first laterally separated and vertically offset from the die pad, a semiconductor die mounted on the die attach surface and comprising a first terminal on an upper surface of the semiconductor die, an interconnect clip that is electrically connected to the first terminal and to the first lead, and a heat spreader mounted on top of the interconnect clip. The interconnect clip includes a first planar section that interfaces with the upper surface of the semiconductor die and extends past an outer edge side of the die pad. The heat spreader covers an area of the first planar section that is larger than an area of the semiconductor die. The heat spreader laterally extends past a first outer edge side of the die pad that faces the first lead.

Abstract: A laser projection apparatus includes a laser source assembly, a display control circuit, a signal shaping circuit and a laser source driving circuit. The display control circuit is configured to output a first driving signal and a second driving signal. The signal shaping circuit is coupled to the laser source driving circuit, and is configured to shape the first driving signal based on a shaping signal to obtain a target driving signal. A frequency of the target driving signal is higher than a frequency of the first driving signal. The laser source driving circuit is coupled to the laser source assembly, and is configured to receive the second driving signal and the target driving signal, and drive the laser source assembly to be turned on or turned off in response to the second driving signal and the target driving signal.

Abstract: A distributed database system, a data disaster backup exercise method and a non-transitory computer-readable storage medium are disclosed. The distributed database system may include a local computer room (110) and an offsite computer room (120), where the local computer room (110) includes a local management node (111) and a local database cluster (112), the offsite computer room (120) includes an offsite management node (121), an offsite exercise database cluster (123) and an offsite synchronization database cluster (122); where the local database cluster (112) and the offsite synchronization database cluster (122) are both connected with the local management node (111); the offsite exercise database cluster (123) is configured for: establishing a first connection with the offsite management node (121); and receiving a test service sent by a service layer.

Abstract: The present disclosure provides a computer-implemented method, a device, and a storage medium. The method includes inputting an image into an attention-enhanced high-resolution network (AHRNet) to extract feature maps for generating a first feature map; generating a first probability map which is concatenated with the first feature map to form a concatenated first feature map, and updating the AHRNet using the first segmentation loss; generating a second feature map, and scaling the second feature map to form a third feature map; generating a second probability map which is concatenated with the third feature map to form a concatenated third feature map, and updating the AHRNet using the second segmentation loss; generating a fourth feature map, and scaling the fourth feature map to form a fifth feature map; updating the AHRNet using the third segmentation loss and the regional level set loss; and outputting the third probability map.

Abstract: A semiconductor package includes a die pad, a semiconductor die mounted on the die pad and comprising a first terminal facing away from the die pad and a second terminal facing and electrically connected to the die pad, an interconnect clip electrically connected to the first terminal, an encapsulant body of electrically insulating material that encapsulates the semiconductor die and the interconnect clip, and a first opening in the encapsulant body that exposes a surface of the interconnect clip, the encapsulant body comprises a lower surface, an upper surface opposite from the lower surface, and a first outer edge side extending between the lower surface and the upper surface, and the first opening is laterally offset from the first outer edge side.

Abstract: The present disclosure provides a method, a device, and a storage medium for prior-guided dual-path network (PDNet). The method includes inputting an image into a split-attention network to extract a feature map at each scale and compressing the feature map to form a compressed feature map of each scale, by an image encoder, inputting the compressed feature map and a three-channel image into a prior encoder to generate an attention enhanced feature map of each scale, and outputting the attention enhanced feature map to a decoder; concatenating, by the decoder, an attention enhanced feature map at a current scale, in combination with up-sampled feature maps and/or down-sampled feature maps from other scales, to form a concatenated feature map of the current scale; and attaching a deconvolutional layer to a highest-level scale SA to segment a lesion and predict a RECIST diameter based on concatenated feature maps.

Abstract: Systems and methods are described for managing charging and discharging of battery packs. In one or more aspects, a system and method are provided to minimize overcharging of battery cells of specific battery chemistries while still enabling fast charging cycles. In other aspects, a buck converter may be used to reduce a voltage of power used to charge the cells. In further aspects, a fast overcurrent protection circuit is described to address situations involving internal short circuits of a battery cell or battery pack. In yet further aspects, a bypass circuit is provided in series-connected battery packs to improve the charging of undercharged battery packs while also increasing the efficiency of the overall charging process. In other aspects, a circuit is provided that permits a controller to determine a configuration of battery packs.

Abstract: A semiconductor module includes: a dual-gauge leadframe having thicker and thinner parts, part of the thinner part forming a high voltage lead; a semiconductor die attached to the thicker part; and a molding compound (MC) encapsulating the die. The thicker leadframe part is disposed at a bottom side of the MC. A side face of the MC has a stepped region between the high voltage lead and thicker leadframe part. A first generally vertical part of the stepped region extends from the high voltage lead to the generally horizontal part, a generally horizontal part of the stepped region extends to the second generally vertical part, and a second generally vertical part of the stepped region extends to the bottom side of the MC. A linear dimension of the generally horizontal part as measured from the first generally vertical part to the second generally vertical part is at least 4.5 mm.

Abstract: The present disclosure provides a computer-implemented method, a device, and a computer program product for deep lesion tracker. The method includes inputting a search image into a first three-dimensional DenseFPN (feature pyramid network) of an image encoder and inputting a template image into a second three-dimensional DenseFPN of the image encoder to extract image features; encoding anatomy signals of the search image and the template image as Gaussian heatmaps, and inputting the Gaussian heatmap of the template image into a first anatomy signal encoders (ASE) and inputting the Gaussian heatmap of the search image into a second ASE to extract anatomy features; inputting the image features and the anatomy features into a fast cross-correlation layer to generate correspondence maps, and computing a probability map according to the correspondence maps; and performing supervised learning or self-supervised learning to predict a lesion center in the search image.

Abstract: A method for performing a computer-aided diagnosis (CAD) for universal lesion detection includes: receiving a medical image; processing the medical image to predict lesion proposals and generating cropped feature maps corresponding to the lesion proposals; for each lesion proposal, applying a plurality of lesion detection classifiers to generate a plurality of lesion detection scores, the plurality of lesion detection classifiers including a whole-body classifier and one or more organ-specific classifiers; for each lesion proposal, applying an organ-gating classifier to generate a plurality of weighting coefficients corresponding to the plurality of lesion detection classifiers; and for each lesion proposal, performing weight gating on the plurality of lesion detection scores with the plurality of weighting coefficients to generate a comprehensive lesion detection score.

Abstract: Systems and methods are described for managing charging and discharging of battery packs. In one or more aspects, a system and method are provided to minimize overcharging of battery cells of specific battery chemistries while still enabling fast charging cycles. In other aspects, a buck converter may be used to reduce a voltage of power used to charge the cells. In further aspects, a fast overcurrent protection circuit is described to address situations involving internal short circuits of a battery cell or battery pack. In yet further aspects, a bypass circuit is provided in series-connected battery packs to improve the charging of undercharged battery packs while also increasing the efficiency of the overall charging process. In other aspects, a circuit is provided that permits a controller to determine a configuration of battery packs.

Abstract: The present disclosure provides a computer-implemented method, a device, and a computer program product for deep lesion tracker. The method includes inputting a search image into a first three-dimensional DenseFPN (feature pyramid network) of an image encoder and inputting a template image into a second three-dimensional DenseFPN of the image encoder to extract image features; encoding anatomy signals of the search image and the template image as Gaussian heatmaps, and inputting the Gaussian heatmap of the template image into a first anatomy signal encoders (ASE) and inputting the Gaussian heatmap of the search image into a second ASE to extract anatomy features; inputting the image features and the anatomy features into a fast cross-correlation layer to generate correspondence maps, and computing a probability map according to the correspondence maps; and performing supervised learning or self-supervised learning to predict a lesion center in the search image.

Abstract: The present disclosure provides a method, a device, and a computer program product using a self-supervised anatomical embedding (SAM) method.

Abstract: A package is disclosed. In one example, the package includes a first main face for mounting a heat sink and an opposing second main face for being mounted on a mounting base. The package comprises a carrier, an electronic component mounted at the carrier, and an encapsulant encapsulating at least part of the electronic component and at least part of the carrier. Electrically insulating material covers electrically conductive material of the carrier at said first main face. The encapsulant comprises at least one step at the first main face.

Abstract: A method, apparatus and device for synchronously playing audio are provided. The method includes: acquiring status information of a Bluetooth controller in the first audio playing device and Bluetooth time from the Bluetooth controller, and determining native Bluetooth time of the first audio playing device based on the status information and the Bluetooth time acquired from the Bluetooth controller; estimating, based on the native Bluetooth time of the first audio playing device and offset time of the native Bluetooth time of the first audio playing device relative to native Bluetooth time of a second audio playing device or native Bluetooth time of an audio providing device, absolute time of the second audio playing device or absolute time of the audio providing device; and playing an audio signal provided by the audio providing device synchronously with the second audio playing device based on the estimated absolute time.

Abstract: An interconnect clip includes a die attach pad that comp includes rises a die attach surface at an inner side of the interconnect clip, a heat dissipation pad that includes a heat dissipation surface at an outer side of the interconnect clip, and a lead contact pad that includes a lead contact surface at an inner side of the interconnect clip or at an outer side of the interconnect clip. The outer side of the interconnect clip in the lead contact pad faces and is spaced apart from the inner side of the interconnect clip in the heat dissipation pad, and the inner side of the interconnect clip in the lead contact pad faces and is spaced apart from the outer side of the interconnect clip in the die attach pad.

Abstract: Systems and methods for characterizing a region of interest (ROI) in a medical image are provided. An exemplary system may include a memory storing instructions and at least one processor communicatively coupled to the memory to execute the instructions which, when executed by the processor, may cause the processor to perform operations. The operations may include detecting one or more candidate ROIs from the medical image using a three-dimensional (3D) machine learning network. The operations may also include determining a key slice for each candidate ROI. The operations may further include selecting a primary ROI from the one or more candidate ROIs based on the respective key slices. In addition, the operations may include classifying the primary ROI into one of a plurality of categories using a texture-based classifier based on the key slice corresponding to the primary ROI.