Abstract: A stator includes a cylindrical stator core having a plurality of slots, and a plurality of coils having segment conductors inserted through the plurality of slots and extending in axial direction, a coolant flow channel through which coolant flows is formed between outer circumferential surface of the segment conductor and inner circumferential surface of the slot, the outer circumferential surface of the segment conductor includes first flat surface facing radial direction, second flat surface facing circumferential direction, and a corner portion curved surface connecting the first flat surface and the second flat surface, the corner portion curved surface includes first curved surface continuous with the first flat surface and second curved surface continuous with the second flat surface, and when seen in cross-sectional view perpendicular to the axial direction, radius of curvature of the first curved surface is greater than radius of curvature of the second curved surface.

Abstract: In a case where the operation program is started, a CPU of the mini-batch learning apparatus functions as a calculation unit, a specifying unit, and an update unit. The calculation unit calculates an area ratio of each of a plurality of classes in mini-batch data. The specifying unit specifies a rare class of which the area ratio is lower than a setting value. The update unit sets an update level of the machine learning model in a case where the rare class is specified by the specifying unit to be lower than an update level of the machine learning model in a case where the rare class is not specified by the specifying unit.

Abstract: Examples herein include methods, systems, and computer program products for utilizing neural networks in ultrasound systems. The methods include processor(s) of a computing device obtaining an image that depicts cells. The processor(s) applies one or more nuclei detection algorithms to detect nuclear aspects in the image. The processor(s) generates a nuclear segmentation map. The processor(s) utilizes the nuclear segmentation map to identify one or more regions of interest in the image. The processor(s) generates a classification result by automatically determining a cell type for each cell in a region of interest of the regions of interest.

Abstract: Provided are a cell image evaluation device, method, and program which are capable of more accurate and high reliable evaluation even though a captured image of each part to be observed within a container deteriorates. The cell image evaluation device includes an image evaluation unit that evaluates a state of a cell included in a captured image obtained by capturing an inside of the container that contains the cell based on the captured image, and a deterioration determination unit that determines whether or not the captured image deteriorates. The image evaluation unit changes an evaluation method of the captured image according to a determination result of the deterioration determination unit.

Abstract: A learning apparatus learns a machine learning model for performing semantic segmentation of determining a plurality of classes in an input image in units of pixels by extracting, for each layer, features which are included in the input image and have different frequency bands of spatial frequencies. A learning data analysis unit analyzes the frequency bands included in an annotation image of learning data. A learning method determination unit determines a learning method using the learning data based on an analysis result of the frequency bands by the learning data analysis unit. A learning unit learns the machine learning model via the determined learning method using the learning data.

Abstract: A cell culture evaluation device includes at least one processor. The processor is configured to acquire a cell image obtained by imaging a cell that is being cultured, to input the cell image to an image machine learning model and output an image feature amount set composed of a plurality of types of image feature amounts related to the cell image from the image machine learning model; and to input the image feature amount set to a data machine learning model and output an expression level set composed of expression levels of a plurality of types of ribonucleic acids of the cell from the data machine learning model.

Abstract: A dynamoelectric machine includes: a winding; a stator core including a slot in which the winding is installed; a cover part that covers the stator core; and a crossing part that is a space formed between the cover part and the stator core, wherein, in the crossing part, an end portion of the winding in an axial direction is exposed, and a filling member is disposed between a side surface of the winding in a radial direction and an inner side surface of the cover part in the radial direction.

Abstract: A rotating electric machine includes a rotor and a stator. The rotor includes: a rotor core having a refrigerant flow path; and an end surface plate arranged at least on one side of the rotor core. The refrigerant flow path includes: a first refrigerant flow path; and a second refrigerant flow path which is disposed further on a radial inner side than the first refrigerant flow pat. The stator includes: a stator core; and a coil end portion protruding from at least one side of the stator core. The end surface plate includes: a root side refrigerant supply portion which communicates with the first refrigerant flow path and supplies the refrigerant to a root region of the coil end portion; and a distal side refrigerant supply portion which communicates with the second refrigerant flow path and supplies the refrigerant to a distal region of the coil end portion.

Abstract: There is provided an image processing apparatus including: a display control unit that performs a control for displaying a learning input image which is input, as learning data, to a segmentation model for performing semantic segmentation, which determines a plurality of classes in an image in units of pixels; a reception unit that receives, for each of a plurality of estimated regions which are estimated as different classes in the learning input image, an input of a marker having a size smaller than a size of the estimated region; a calculation unit that calculates feature quantities for each of a plurality of partitions in the learning input image; a classification unit that classifies a plurality of the feature quantities for each of the plurality of partitions into clusters for at least the number of the estimated regions; and a generation unit that generates an annotation candidate image in which a classification result of the clusters is reflected in the learning input image so as to be identified.

Abstract: An image processing apparatus includes an extraction unit that extracts, from among a plurality of designated regions in which labels of classes are designated, complicated regions which are regions of at least a part of the designated regions and are regions having relatively complicated contours, in an annotation image given as learning data to a machine learning model for performing semantic segmentation in which a plurality of the classes in an image are discriminated on a per-pixel basis, and a setting unit that sets additional labels for the complicated regions separately from original labels originally designated for the annotation image.

Abstract: There is provided a mini-batch learning apparatus that learns a machine learning model for performing semantic segmentation, which determines a plurality of classes in an image in units of pixels, by inputting mini-batch data to the machine learning model, the apparatus including a calculation unit, a specifying unit, and a generation unit. The calculation unit calculates, from a learning input image and an annotation image which are sources of the mini-batch data, a first area ratio of each of the plurality of classes with respect to an entire area of the annotation image. The specifying unit specifies a rare class of which the first area ratio is lower than a first setting value. The generation unit generates the mini-batch data from the learning input image and the annotation image. The generation unit generates the mini-batch data in which a second area ratio of the rare class is equal to or higher than a second setting value higher than the first area ratio calculated by the calculation unit.

Abstract: An object of an image processing apparatus, a method, and a non-transitory computer readable recording medium storing a program is to enable acquisition of a composite image in which an effect of a meniscus formed on a liquid surface of a liquid in a container is reduced. A plurality of captured images acquired by setting a part of adjacent observation regions to overlap with each other and imaging a container a plurality of times while changing a position of the observation region are acquired. An overlapping region selection unit 51 selects the captured image having a highest contrast in the overlapping region with at least one adjacent captured image in each captured image Gi as an image of the overlapping region. A composite image generation unit 52 generates a composite image Gs by linking the plurality of captured images in which the images of the overlapping regions are selected.

Abstract: In a case where the operation program is started, a CPU of the mini-batch learning apparatus functions as a calculation unit, a specifying unit, and an evaluation unit. The calculation unit calculates an area ratio of each of a plurality of classes in mini-batch data. The specifying unit specifies, as a correction target class, a rare class of which the area ratio is lower than a setting value. The evaluation unit evaluates the class determination accuracy of the machine learning model by using a loss function. As correction processing, the evaluation unit sets a weight for a loss value of the rare class to be larger than a weight for a loss value of a class other than the rare class.

Abstract: In a case where the operation program is started, a CPU of the mini-batch learning apparatus functions as a calculation unit, a specifying unit, and an update unit. The calculation unit calculates an area ratio of each of a plurality of classes in mini-batch data. The specifying unit specifies a rare class of which the area ratio is lower than a setting value. The update unit sets an update level of the machine learning model in a case where the rare class is specified by the specifying unit to be lower than an update level of the machine learning model in a case where the rare class is not specified by the specifying unit.

Abstract: A learning apparatus learns a machine learning model for performing semantic segmentation of determining a plurality of classes in an input image in units of pixels by extracting, for each layer, features which are included in the input image and have different frequency bands of spatial frequencies. A learning data analysis unit analyzes the frequency bands included in an annotation image of learning data. A learning method determination unit determines a learning method using the learning data based on an analysis result of the frequency bands by the learning data analysis unit. A learning unit learns the machine learning model via the determined learning method using the learning data.

Abstract: An evaluator 21 that evaluates states of cells included in each region of interest of a cell image, and a predictor 22 that performs, in advance, machine learning of a relationship between evaluation results for a specific region of interest within a first cell image obtained by imaging cells before a staining process and regions around the specific region of interest and staining states of cells of the specific region of interest within a second cell image obtained by imaging the same imaging targets as the cells of the first cell image after the staining process are provided. The predictor 22 predicts staining states of cells of a specific region of interest based on evaluation results for the specific region of interest and regions around the specific region of interest among the evaluation results for the third cell image of the cells before the staining process.

Abstract: Provided are a cell image evaluation device, method, and program which are capable of performing more accurate and high reliable evaluation even though a captured image of each part to be observed within a container is an image of which contrast is low due to influence of meniscus. The cell image evaluation device includes a region determination unit that determines whether a captured image obtained by capturing an inside of a container that contains a cell is an image obtained by capturing a meniscus region within the container or an image obtained by capturing a non-meniscus region within the container and an image evaluation unit that evaluates a state of the cell included in the captured image. The image evaluation unit evaluates the image of the meniscus region and the image of the non-meniscus region by different evaluation methods.

Abstract: An observation device includes a stage, an imaging optical system that includes an objective lens, a detection section that includes displacement sensors that detect a vertical position of a cultivation container, an imaging optical system controller that controls the imaging optical system driving section to move the objective lens in an optical axis direction on the basis of the vertical position of the cultivation container, and a horizontal driving section that moves the stage in a main scanning direction and a sub-scanning direction and reciprocates the stage in the main scanning direction, in which the detection section detects the vertical position of the cultivation container at a forward position in a movement direction of the observation region with reference to the position of the observation region of the imaging optical system with respect to the cultivation container.

Abstract: Provided is an information processing apparatus including an acquiring unit that acquires cell information indicating a state of a cell from production of a pluripotent stem cell to differentiation of the pluripotent stem cell into a specific differentiated cell by differentiation induction, and process history information indicating a history of a processing process for obtaining the differentiated cell, and a deriving unit that derives differentiation potency information indicating differentiation potency of the pluripotent stem cell based on the cell information and the process history information which are acquired by the acquiring unit.

Abstract: An image processing device (100) includes a non-discharge correction processing unit (114) that performs an image correction process for correcting an image defect caused by a non-discharge nozzle in an inkjet head and includes, as different files, a first halftone processing program file (152) that performs first halftone processing for a normal portion, which is an image region other than a non-discharge correction portion to be subjected to non-discharge correction and a non-discharge portion, and a second halftone processing program file (154) that performs second halftone processing for the non-discharge correction portion. The image processing device executes the first halftone processing program file (152) for the normal portion in an input image (102) and executes the second halftone processing program file (154) for the non-discharge correction portion, thereby obtaining a non-discharge-corrected halftone image (104).