Abstract: Provided are a linear structure extraction device, a method, a program, and a learned model which can detect a linear structure in an image. A linear structure extraction device according to an embodiment of the present disclosure includes a learning model that is learned to receive an input of the image and output, as a prediction result, one or more element points which constitute the linear structure from the image, in which the learning model includes a first processing module that receives the image and generates a feature map representing a feature amount of the image by convolution processing, and a second processing module that calculates a shift amount from a unit center point to the element point of the linear structure closest to the unit center point, for each unit obtained by dividing the feature map into a plurality of the units including regions having a predetermined size in a grid pattern.

Abstract: Provided are a learning method, a learning device, a generative model, and a program that generate an image including high resolution information without adjusting a parameter and largely correcting a network architecture even in a case in which there is a variation of the parts of an image to be input. Only a first image is input to a generator of a generative adversarial network that generates a virtual second image having a relatively high resolution by using the first image having a relatively low resolution, and a second image for learning or the virtual second image and part information of the second image for learning or the virtual second image are input to a discriminator that identifies the second image for learning and the virtual second image.

Abstract: A machine learning method and an apparatus, a program, a learned model, and a discrimination apparatus capable of controlling a calculation amount by learning a new task without changing output performance for an existing task in a learned network are provided.

Abstract: An information processing apparatus includes one or more processors, and one or more storage devices that store a program including an image generation model trained to generate, from a first image, a second image that imitates an image obtained by an imaging protocol different from an imaging protocol of the first image. The image generation model is a model trained, through machine learning using training data in which a training image captured by a first imaging protocol is associated with a correct answer clinical parameter calculated from a corresponding image captured by a second imaging protocol different from the first imaging protocol for the same subject as the training image using a modality of the same type as a modality used to capture the training image, such that a clinical parameter calculated from a generation image output by the image generation model approaches the correct answer clinical parameter.

Abstract: A processor sequentially acquires a plurality of radiation images of a subject having a body cavity into which an ultrasonic endoscope to which an ultrasonic imaging device is attached and to which a radiation impermeable marker is attached is inserted, sequentially acquires a plurality of two-dimensional ultrasound images corresponding to the plurality of radiation images, which are acquired by the ultrasonic imaging device, recognizes a position and a posture of the ultrasonic endoscope in the body cavity based on the marker included in each of the plurality of radiation images, and derives a three-dimensional ultrasound image from the plurality of two-dimensional ultrasound images based on the position and the posture of the ultrasonic endoscope recognized with respect to the plurality of radiation images.

Abstract: A processor is configured to: divide a target image into a plurality of first regions through a first division; divide the target image into a plurality of second regions through a second division different from the first division; derive a feature vector that represents at least a feature of each of the second regions for each of the first regions; derive a determination result for a target object included in the target image based on the feature vector; specify, among elements of the feature vector, an influential element that affects the determination result; and specify an influential region that affects the determination result in the target image based on the influential element.

Abstract: A processor is configured to acquire an original image and a mask image in which masks are applied to one or more regions respectively representing one or more objects including a target object in the original image, derive a pseudo mask image by processing the mask in the mask image, and derive a pseudo image that has a region based on a mask included in the pseudo mask image and has the same representation format as the original image, based on the original image and the pseudo mask image.

Abstract: An all-solid battery is formed by laminating a first current collector, a positive-electrode layer, a solid electrolyte layer, a negative-electrode layer, and a second current collector in this order. The positive-electrode fine particle layer contains positive-electrode active material fine particles having a particle diameter smaller than that of the positive-electrode active material and is formed on a side surface of the positive-electrode layer. The negative-electrode fine particle layer contains negative-electrode active material fine particles having a particle diameter smaller than that of the negative-electrode active material and is formed on a side surface of the negative-electrode layer.

Abstract: Provided herein is a solid-state battery having high volume energy density, as well as a method of manufacture of such a solid-state battery. A solid-state battery 100 is a laminate including a first collector layer 1, a positive electrode layer 2, a solid electrolyte layer 5, a negative electrode layer 4, and a second collector layer 3, in this order from the top. The solid-state battery 100 satisfies ?>90°, ?>90°, and ?>?, where ? is the angle formed in the positive electrode layer 2 by a side surface 2A of the positive electrode layer 2 and the top surface of the solid electrolyte layer 5 underlying the positive electrode layer 2, and ? is the angle formed in the negative electrode layer 4 by a side surface 4A of the negative electrode layer 4 and the top surface of the second collector layer 3 underlying the negative electrode layer 4.

Abstract: An all-solid-state battery has a structure in which a positive electrode current collector, a positive electrode layer containing a positive electrode active material and a solid electrolyte, a solid electrolyte layer containing a solid electrolyte, a negative electrode layer containing a negative electrode active material and a solid electrolyte, and a negative electrode current collector are stacked in this order. The solid electrolyte layer has a repeating structure in which a low porosity portion and a high porosity portion having a higher porosity than a porosity of the low porosity portion are repeated in an in-plane direction.

Abstract: A learning support device 18 includes an acquisition unit 26, a registration unit 27, a storage device 28, a learning unit 29, and a controller 31. The acquisition unit 26 acquires an image of a region of interest and a name of the region of interest by analyzing an interpretation report 23. The registration unit 27 registers training data consisting of the image of the region of interest and the name of the region of interest acquired by the acquisition unit 26 in the storage device 28. The learning unit 29 performs learning for generating a discrimination model 34, which outputs the image of the region of interest and the name of the region of interest with respect to an input of an inspection image 22 of the interpretation report 23, using a plurality of pieces of training data 33 registered in the storage device 28.

Abstract: An image generation device derives, for a subject including a specific structure, a subject model representing the subject by deriving each feature amount of the target image having the at least one representation format and combining the feature amounts based on the target image. A latent variable derivation unit derives a latent variable obtained by dimensionally compressing a feature of the subject model according to the target information based on the target information and the subject model. A virtual image derivation unit outputs a virtual image having the representation format represented by the target information based on the target information, the subject model, and the latent variable.

Abstract: A prediction apparatus includes a learning section that performs machine learning in which, with respect to a combination of different types of captured images obtained by imaging the same subject, one captured image is set to an input and another captured image is set to an output to generate a prediction model; and a controller that performs a control for inputting a first image to the prediction model as an input captured image and outputting a predicted second image that is a captured image having a type different from that of the input captured image.

Abstract: An extraction model is constituted of an encoder that extracts a feature amount of a first image of a first representation format to derive a feature map of the first image, a first decoder that derives a second virtual image of a second representation format different from the representation format of the first image on the basis of the feature map, a first discriminator that discriminates a representation format of an input image and whether the input image is a real image or a virtual image, and outputs a first discrimination result, a second decoder that extracts a region of interest of the first image on the basis of the feature map, and a second discriminator that discriminates whether an extraction result of the region of interest by the second decoder is an extraction result of a first image with ground-truth mask or an extraction result of a first image without ground-truth mask, and outputs a second discrimination result.

Abstract: Provided are a linear structure extraction device, a method, a program, and a learned model which can detect a linear structure in an image. A linear structure extraction device according to an embodiment of the present disclosure includes a learning model that is learned to receive an input of the image and output, as a prediction result, one or more element points which constitute the linear structure from the image, in which the learning model includes a first processing module that receives the image and generates a feature map representing a feature amount of the image by convolution processing, and a second processing module that calculates a shift amount from a unit center point to the element point of the linear structure closest to the unit center point, for each unit obtained by dividing the feature map into a plurality of the units including regions having a predetermined size in a grid pattern.

Abstract: A region specification apparatus specifies a region of an object which is included in an input image and which includes a plurality of subclass objects having different properties. The region specification apparatus includes a first discriminator that specifies an object candidate included in the input image. The first discriminator has a component configured to predict at least one of movement or transformation of a plurality of anchors according to the property of the subclass object and specify an object candidate region surrounding the object candidate.

Abstract: Provided are a learning method and a learning system of a generative model, a program, a learned model, and a super resolution image generating device that can handle input data of any size and can suppress the amount of calculation at the time of image generation. A learning method according to an embodiment of the present disclosure is a learning method for performing machine learning of a generative model that estimates, from a first image, a second image including higher resolution image information than the first image, the method comprising using a generative adversarial network including a generator which is the generative model and a discriminator which is an identification model that identifies whether provided data is data of a correct image for learning or data derived from an output from the generator and implementing a self-attention mechanism only in a network of the discriminator among the generator and the discriminator.

Abstract: Provided are a learning method, a learning device, a generative model, and a program that generate an image including high resolution information without adjusting a parameter and largely correcting a network architecture even in a case in which there is a variation of the parts of an image to be input. Only a first image is input to a generator of a generative adversarial network that generates a virtual second image having a relatively high resolution by using the first image having a relatively low resolution, and a second image for learning or the virtual second image and part information of the second image for learning or the virtual second image are input to a discriminator that identifies the second image for learning and the virtual second image.

Abstract: A region specification apparatus, a region specification method, and a region specification program efficiently specify any object included in an input image. A convolutional neural network of an object specification unit generates a convolutional feature map from an input image (S0). A first discriminator selects an anchor based on a similarity in shape and size to a ground truth box including an object candidate from among a plurality of anchors having various shapes and various sizes. The first discriminator specifies an object candidate region in the input image based on the selected anchor.

Abstract: Provided are an image processing apparatus, an image processing method, and a program that can suppress an error in the segmentation of a medical image. An image processing apparatus includes: a segmentation unit (42) that applies deep learning to perform segmentation which classifies a medical image (200) into a specific class on the basis of a local feature of the medical image; and a global feature classification unit (46) that applies deep learning to classify the medical image into a global feature which is an overall feature of the medical image. The segmentation unit shares a weight of a first low-order layer which is a low-order layer with a second low-order layer which is a low-order layer in the global feature classification unit.