Abstract: A treatment system of embodiments includes an imaging system including one or more radiation sources and a plurality of detectors, a first acquirer, a second acquirer, a first deriver, a second deriver, and a calibrator. The radiation sources radiate radiation to an object in a plurality of different directions. The plurality of detectors detect the radiation at different positions. The first acquirer acquires images based on the radiation. The second acquirer acquires position information of a first imaging device in a three-dimensional space. The first deriver derives the position of the object in the images. The second deriver derives the position of a second imaging device in the three-dimensional space based on the position of the object in the images, the position of the first imaging device, and the like. The calibrator performs calibration of the imaging system based on a derivation result of the second deriver.

Abstract: According to an embodiment, a radiation therapy device includes an acquirer, a projection position calculator, an element projection image generator, and an element projection image synthesizer. The acquirer acquires a condition of X-ray imaging in a treatment stage and a three-dimensional image of a patient imaged before the treatment stage. The projection position calculator calculates a projection position when each of pixels included in the three-dimensional image is projected onto a two-dimensional X-ray fluoroscopic image generated in the X-ray imaging on the basis of the condition of the X-ray imaging. The element projection image generator generates an element projection image for each pixel when each of the pixels included in the three-dimensional image is projected onto the X-ray fluoroscopic image. The element projection image synthesizer performs a synthesis process for the element projection image for each pixel on the basis of the projection position to generate a reconstructed image.

Abstract: A medical image processing device includes a first image acquiring unit, a second image acquiring unit, a first likelihood distribution calculating unit, a trackability determining unit, and a tracking unit. The first image acquiring unit acquires first images which are transparent images of the patient. The second image acquiring unit acquires second images which are transparent images of the patient generated at a time different from that of the first images. The first likelihood distribution calculating unit calculates a first likelihood distribution indicating a distribution of likelihoods indicating a likeness to the object in the first images. The trackability determining unit determines whether the object is trackable on the basis of the first likelihood distribution. The tracking unit tracks the position of the object in the second images on the basis of the result of determination.

Abstract: A learning device includes a structure search unit that searches for a first learned model structure obtained by selecting search space information in accordance with a target constraint condition of target hardware for each of a plurality of convolution processing blocks included in a base model structure in a neural network model; a parameter search unit that searches for a learning parameter of the neural network model in accordance with the target constraint condition; and a pruning unit that deletes a unit of at least one of the plurality of convolution processing blocks in the first learned model structure based on the target constraint condition and generates a second learned model structure.

Abstract: A robot system according to an embodiment includes one or more processors. The processors acquire first input data predetermined as data affecting an operation of a robot. The processors calculate a calculation cost of inference processing using a machine learning model for inferring control data used for controlling the robot, on the basis of the first input data. The processors infer the control data by the machine learning model set according to the calculation cost. The processors control the robot using the inferred control data.

Abstract: According to an embodiment, a medical image processing device includes a first image acquirer, a second image acquirer, a direction acquirer, and a movement amount calculator. The first image acquirer acquires a three-dimensional first image obtained by photographing the inside of a body of a patient. The second image acquirer acquires a three-dimensional second image of the inside of the body of the patient imaged at a timing different from that of the first image. The direction acquirer acquires information about an irradiation direction of radiation to the patient in a treatment room. The movement amount calculator outputs a movement amount signal indicating the amount of movement of the second image to be moved to align the position of the patient shown in the second image with the position of the patient shown in the first image based on the path of the radiation set in the first image and the information about the irradiation direction.

Abstract: A learning device according to an embodiment includes one or more hardware processors configured to function as a generation unit, an inference unit, and a training unit. The generation unit generates input data with which an error between a value output from each of one or more target nodes and a preset aimed value is equal to or less than a preset value, the target nodes being in a target layer of a plurality of layers included in a first neural network. The inference unit causes the input data to propagate in a forward direction of the first neural network to generate output data. The training unit trains a second neural network differing from the first neural network by using training data including a set of the input data and the output data.

Abstract: According to one embodiment, a machine learning apparatus includes a processing circuit. The processing circuit trains a first learning: parameter of an extraction layer configured to extract feature data of the input data, based on a plurality of training data. The processing circuit trains a second learning parameter of a reconstruction layer configured to generate reconstructed data of the input data, based on a plurality of training feature data obtained by applying the trained extraction layer to the plurality of training data. The second learning parameter represents representative vectors as many as a dimension count of the feature data. The representative vectors as many as the dimension count are based on a weighted sum of the plurality of training data.

Abstract: According to one embodiment, a defect classification apparatus includes a processor. The processor acquires a first design image which is an image based on design data created by design software and relates to a first inspection target, and acquires a first real image which is captured by imaging the first inspection target produced based on the design data. The processor converts the first design image to a reference image represented by using a second real image captured by imaging a second inspection target without a defect. The processor calculates a reliability of the reference image. The processor detects a defect in the first inspection target by comparing the reference image and the first real image and classifies the defect, based on the reliability.

Abstract: A providing apparatus according to an embodiment of the present disclosure includes a memory and a hardware processor coupled to the memory. The hardware processor is configured to: store, in the memory, a first machine learning model capable of changing an amount of calculation of a model of a neural network; acquire device information; set, based on the device information, extraction conditions representing conditions for extracting second machine learning models from the first machine learning model; extract the second machine learning models from the first machine learning model based on the extraction conditions; and provide the second machine learning models to a device specified by the device information.

Abstract: There is provided a check valve capable of effectively suppressing the generation of chattering. The check valve includes: a housing including an inlet channel, a valve chest, and an outlet channel; a seat member provided around the inlet channel, the seat member including a seat portion; a valve element pressed against the seat portion to close the inlet channel; a biasing member configured to push the valve element toward a valve seat; a guide portion provided at the housing and configured to guide the valve element when the valve element moves in an axial direction; and a damper chamber communicating with the valve chest through a space between the valve element and the guide portion, the damper chamber being configured to attenuate axial moving force of the valve element. The biasing member is arranged in the valve chest.

Abstract: A defect inspection device includes at least one memory storing instructions and at least one processor.

Abstract: A medical image processing device of an embodiment includes a comparator and a position determination region determiner. The comparator compares a first image obtained by photographing a patient with a comparative image which is an image used in previous radiation treatment and in which a valid region used in position alignment in the radiation treatment is designated. The position determination region determiner determines a position determination region similar to the valid region included within the first image on the basis of a comparison result of the comparator.

Abstract: According to one embodiment, a learning apparatus includes a processing circuit. The processing circuit acquires first sequence data representing transition of inference performance according to a training progress of a first model trained in accordance with a first training parameter value concerning a specific training condition. The processing circuit performs iterative learning of a second model in accordance with a second training parameter value concerning the specific training condition and changes the second training parameter value based on the inference performance of the second model and the first sequence data in a training process of the second model.

Abstract: According to one embodiment, a learning apparatus includes a setting unit, a training unit, and a display. The setting unit sets one or more second training conditions based on a first training condition relating to a first trained model. The training unit trains one or more neural networks in accordance with the one or more second training conditions and generates one or more second trained models which execute a task identical to a task executed by the first trained model. The display displays a graph showing an inference performance and calculation cost of each of the one or more second trained models.

Abstract: According to one embodiment, a defect inspection apparatus includes a storage and a processor. The storage stores dictionary in which a first design image generated by software is associated with a first real image corresponding to the first design image. The processor acquires a second design image generated by the software. The processor searches for a similar first design image similar to the second design image. The processor generates a reference image that is a pseudo real image of a second inspection object, based on the second design data and free of defect, by using the first real image associated with the similar first design image. The first design image includes information of an image area wider than the first real image.

Abstract: According to one embodiment, a learning apparatus includes processing circuitry. The processing circuitry acquires a plurality of learning samples to be learned and a plurality of target labels associated with the respective learning samples, iteratively learns a learning model so that a learning error between output data corresponding to the learning sample and the target label is small with respect to the learning model to which the output data is output by inputting the learning sample, and displays a layout image in which at least some of the learning samples are arranged based on a learning progress regarding the iterative learning of the learning model and a plurality of the learning errors.

Abstract: A medical image processing device of an embodiment includes a first image acquirer, a second image acquirer, a generator, and a calculator. The first image acquirer acquires a first fluoroscopic image of a patient. The second image acquirer acquires a second fluoroscopic image according to radiation with which the patient is irradiated at a time point different from a time point of acquisition of the first fluoroscopic image from a photography device that detects radiation with a detector and performs an imaging process. The generator generates a reconstructed image obtained by reproducing the second fluoroscopic image from the first fluoroscopic image virtually arranged in a three-dimensional space on the basis of an installation position of the detector in the three-dimensional space. The calculator obtains a suitable position on the first fluoroscopic image in the three-dimensional space on the basis of a degree of similarity between the second fluoroscopic image and the reconstructed image.

Abstract: An object positioning apparatus comprising: a radiographic image input interface configured to acquire a radiographic image that is generated by causing a fluoroscopic imaging apparatus to image an object and includes a first region and a second region, the first region depicting an index region for positioning of the object, the second region depicting a non-index region other than the index region; and a positioning processor configured to perform the positioning of the object by performing matching processing between a previously generated reference image and the first region that is specified from the radiographic image based on three-dimensional model information of the non-index region.

Abstract: A machine learning model compression system according to an embodiment includes one or more hardware processors configured to: select a layer of a trained machine learning model in order from an output side to an input side of the trained machine learning model; calculate, in units of an input channel, a first evaluation value evaluating a plurality of weights included in the selected layer; sort, in ascending order or descending order, the first evaluation values each calculated in units of the input channel; select a given number of the first evaluation values in ascending order of the first evaluation values; and delete the input channels used for calculation of the selected first evaluation values.