Abstract: An image diagnosis supporting device includes a model reader that reads an image diagnostic model that outputs a diagnostic result for a diagnostic image that is an input medical image, a storage unit that stores facility data that is a plurality of medical images associated with diagnostic results held in a facility, and an adjuster that adjusts, based on the facility data, the image diagnostic model or the diagnostic image input to the image diagnostic model.

Abstract: An information processing system includes: a behavior history data feature extraction unit configured to extract a behavior history data feature that is a feature of the behavior history data acquired from the user; a measurement data feature extraction unit configured to extract a measurement data feature that is a feature of the measurement data acquired from the user; a feature conversion learning unit configured to learn a feature conversion model for deriving a feature of measurement data from the behavior history data using the behavior history data feature and the measurement data feature; and a treatment prediction learning unit configured to generate a prediction model for providing an appropriate treatment to a user using a first feature extracted from the measurement data, a second feature converted from the behavior history data, the treatment, and an effect of the treatment.

Abstract: A simulated moving-bed type chromatographic separation method separating a weakly adsorptive component, a strongly adsorptive component, and an intermediately adsorptive component, with eluents by using a circulation system in which a plurality of unit packed columns packed with an adsorbent are connected in series and in an endless form via pipes in which a feed solution supply port F, two or more eluent supply ports D corresponding to the eluents, an extraction port A of a fraction containing the weakly adsorptive component, an extraction port B of a fraction containing the intermediately adsorptive component, and an extraction port C of a fraction containing the strongly adsorptive component are provided in the pipes of the circulation system, and positions of the ports F, A, B, and C are set to have a specified relationship.

Abstract: Provided are a medical image processing apparatus and a medical image processing method capable of implementing specialized learning with higher accuracy in a case where the specialized learning is performed on a plurality of conventional features based on knowledge of a doctor. An image processing apparatus according to the present invention includes: an image group conversion unit that calculates a value of a predetermined feature (first feature) for each image constituting an input first image group, selects an image from the first image group on the basis of the value of the feature, and sets the image as an image of a second image group; and a feature extraction unit that extracts a new feature (second feature) by performing learning on the second image group generated by the image group conversion unit using a feature generation network.

Abstract: To obtain a predictive model that shows a diagnostic prediction result with higher accuracy and high medical validity. A medical imaging apparatus includes an imaging unit that collects an image signal of an inspection target, and an image processing unit that generates first image data from the image signal and performs image processing of the first image data. The image processing unit includes a feature quantity extraction unit that extracts a first feature quantity from the first image data, a feature quantity abstraction unit that abstracts the first feature quantity to extract a second feature quantity, a feature quantity conversion unit that converts the second feature quantity into a third feature quantity extracted by second image data, and an identification unit that uses the converted third feature quantity to calculate a predetermined parameter value.

Abstract: A simulated moving-bed type chromatographic separation method including separating a weakly adsorptive component, a strongly adsorptive component, and an intermediately adsorptive component that has adsorptive property intermediate between the two components, with respect to an adsorbent, with two or more kinds of eluents by using a circulation system in which a plurality of unit packed columns each packed with an adsorbent are connected in series and in an endless form via pipes, the weakly adsorptive component, the strongly adsorptive component, and the intermediately adsorptive component being contained in a feed solution, wherein a feed solution supply port, eluent suply ports and a plurality of extraction ports are provided on the pipes of the circulation system, and positions of the feed solution supply port and the plurality of extraction ports are set to have a specified relationship; and a chromatographic separation system suitable for implementing the chromatographic separation method.

Abstract: An information processing system includes: a processor that executes a program; and a storage device that stores the program, in which the storage device stores sensor data that is biological information of a user measured by a sensor and user data collected in association with the sensor data, and the processor acquires the sensor data, and imputes the sensor data using a causal relationship between the acquired sensor data and the user data.

Abstract: A computer system manages a first model calculating an output value, using time-series data including a value related to an intervention carried out on a person, a second model that calculates a feature by mapping an output value from the first model onto a feature space, and a third model that outputs a predicted value of an effect of an intervention, from the feature. The time-series data includes a time at which the intervention is carried out, factors indicating a state of the person, and a type and a degree of the intervention. The computer system calculates a predicted value of the continuous intervention corresponding to the time-series data, using the first, second, and third models. The second model maps an output value from the first model onto the feature space so that a difference in distribution of data strings used in machine learning reduces in the feature space.

Abstract: To acquire a higher-quality image with high-speed imaging in an MRI apparatus or the like to which compressed sensing is applied. Included are: an observation unit that does not observe, when any one of two points being point-symmetric with respect to the origin is observed, the other point in observation of a high frequency component of a K-space of the MRI apparatus; and a reconstruction unit that reconstructs an image from a component of the K-space observed by the observation unit. The reconstruction process of the reconstruction unit includes an image correction process based on an observation pattern of the observation unit.

Abstract: An image diagnostic device that obtains a prediction model indicating a higher accuracy diagnosis prediction result includes: an observation unit that collects an image of an examination object; and an image processing unit that generates first image data from the image, and performs image processing of the first image data. The image processing unit is provided with: a feature extraction unit that extracts a first feature from the first image data; a feature transformation unit that converts the first feature to a second feature to be extracted from second image data; and an identification unit that calculates a prescribed parameter value using the converted second feature. The feature extraction unit includes a prediction model learned using a plurality of combinations of the first image data and feature, and the feature transformation unit includes a feature transformation model learned using a plurality of combinations of the first and second features.

Abstract: An image diagnosis supporting device includes a model reader that reads an image diagnostic model that outputs a diagnostic result for a diagnostic image that is an input medical image, a storage unit that stores facility data that is a plurality of medical images associated with diagnostic results held in a facility, and an adjuster that adjusts, based on the facility data, the image diagnostic model or the diagnostic image input to the image diagnostic model.

Abstract: Image processing using a machine learning model is enabled, thereby accurately reducing noise to improve image quality. A medical image is acquired; and it is evaluated whether noise in the medical image exceeds a predetermined reference value. A noise reducer reduces the noise of the medical image that has been determined to include noise that exceeds the reference value. The noise of the medical image is reduced using a machine learning model constructed by collecting a plurality of learning data sets that include an image with noise as input data and an image without noise as output data. The machine learning model includes a plurality of layers that perform convolution on an image that is input, one layer of which includes a filter layer in which a plurality of linear or nonlinear filters are incorporated, and convolution coefficients of the plurality of linear or nonlinear filters are predetermined.

Abstract: A simulated moving-bed type chromatographic separation method separating a weakly adsorptive component, a strongly adsorptive component, and an intermediately adsorptive component, with eluents by using a circulation system in which a plurality of unit packed columns packed with an adsorbent are connected in series and in an endless form via pipes in which a feed solution supply port F, two or more eluent supply ports D corresponding to the eluents, an extraction port A of a fraction containing the weakly adsorptive component, an extraction port B of a fraction containing the intermediately adsorptive component, and an extraction port C of a fraction containing the strongly adsorptive component are provided in the pipes of the circulation system, and positions of the ports F, A, B, and C are set to have a specified relationship.

Abstract: A prediction method to predict a patient state with high accuracy by generating a fused feature quantity that can reflect a feature quantity of a large number of types of data includes an analysis step of extracting feature quantities by analyzing biometric information of a patient and medical care information of the patient other than the biometric information, a fusing step of generating a fused feature quantity by fusing the biometric information feature quantity and the medical care information feature quantity, a learning step of learning a relationship between the biometric information feature quantity and the medical care information feature quantity, a feature quantity mutation learning step of predicting the fused feature quantity by the feature quantity relationship learning from the input of only the biometric information, and a prediction step of predicting a patient state by using the predicted fused feature quantity obtained by the feature quantity mutation learning.

Abstract: To obtain a predictive model that shows a diagnostic prediction result with higher accuracy and high medical validity. A medical imaging apparatus includes an imaging unit that collects an image signal of an inspection target, and an image processing unit that generates first image data from the image signal and performs image processing of the first image data. The image processing unit includes a feature quantity extraction unit that extracts a first feature quantity from the first image data, a feature quantity abstraction unit that abstracts the first feature quantity to extract a second feature quantity, a feature quantity conversion unit that converts the second feature quantity into a third feature quantity extracted by second image data, and an identification unit that uses the converted third feature quantity to calculate a predetermined parameter value.

Abstract: Provided is a medical imaging device capable of obtaining a medical image with high image quality in a short time by using a novel image reconstruction technique in which DL is applied to medical image processing and by significantly reducing a total imaging time including an image reconstruction time. The medical imaging device classifies a medical image into any of a predetermined plurality of classes, selects an optimal one or a plurality of restorers from a plurality of restorers respectively corresponding to the plurality of classes according to classification results, and reconstructs the medical image using the selected restorers. The medical image is divided into, for example, a plurality of patches, and is reconstructed for each patch and integrated. The restorer can include a CNN.

Abstract: An image diagnostic device that obtains a prediction model indicating a higher accuracy diagnosis prediction result includes: an observation unit that collects an image of an examination object; and an image processing unit that generates first image data from the image, and performs image processing of the first image data. The image processing unit is provided with: a feature extraction unit that extracts a first feature from the first image data; a feature transformation unit that converts the first feature to a second feature to be extracted from second image data; and an identification unit that calculates a prescribed parameter value using the converted second feature. The feature extraction unit includes a prediction model learned using a plurality of combinations of the first image data and feature, and the feature transformation unit includes a feature transformation model learned using a plurality of combinations of the first and second features.

Abstract: Image processing using a machine learning model is enabled, thereby accurately reducing noise to improve image quality. A medical image is acquired; and it is evaluated whether noise in the medical image exceeds a predetermined reference value. A noise reducer reduces the noise of the medical image that has been determined to include noise that exceeds the reference value. The noise of the medical image is reduced using a machine learning model constructed by collecting a plurality of learning data sets that include an image with noise as input data and an image without noise as output data. The machine learning model includes a plurality of layers that perform convolution on an image that is input, one layer of which includes a filter layer in which a plurality of linear or nonlinear filters are incorporated, and convolution coefficients of the plurality of linear or nonlinear filters are predetermined.

Abstract: In a diagnostic imaging device, such as an MRI device, correction processing improves an image to be a high-quality image and an imaging time is shortened. In the diagnostic imaging device, a noise reduction unit 201 reduces a noise in observation data acquired with an observation unit 100 and converted into an image, and the image correction unit 202 corrects the noise reduced data by correction processing that uses visual characteristics of human. The image correction unit 202 separates the noise reduced data into a broad luminance component and a local variation component, and generates a correction level map using the broad luminance component. Correcting the noise reduced data using this correction level map and the local variation component acquires a high-quality image that is competent in the clinical field.

Abstract: A computer configured to perform image processing to detect an object from an image, comprising: an arithmetic device; and a storage device coupled to the arithmetic device, having a model information database to store a plurality of pieces of model information, model information defines a model to realize the image processing, and the arithmetic device being configured to: perform an identification process to detect the object from an evaluation image based on each of the plurality of pieces of model information in a case where the evaluation image is input; and integrate a plurality of output results each of which obtained by the identification process based on each of the plurality of pieces of model information, thereby outputting a detection result of the object.