Abstract: In one embodiment, an image processing system includes a memory and processing circuitry. The memory is configured to store a predetermined program. The processing circuitry is configured, by executing the predetermined program, to perform processing on an input image by exploiting a neural network having an input layer, an output layer, and an intermediate layer provided between the input layer and the output layer, the input image being inputted to the input layer, and adjust an internal parameter based on data related to the input image, while performing the processing on the input image after training of the neural network, the internal parameter being at least one internal parameter of at least one node included in the intermediate layer, and the input parameter having been calculated by the training of the neural network.

Abstract: According to one embodiment, the ultrasonic probe includes a transducer group, an acoustic transmission layer, and a protective material. The transducer group has a plurality of transducers transmitting ultrasonic waves. The acoustic transmission layer transmits the ultrasonic waves transmitted by the transducer group. The protective material protects the transducer group and the acoustic transmission layer. A width of the transducer group in an elevation direction and an opening width of the protective material at the position corresponding to the body contact surface of the acoustic transmission layer are almost identical. The transducer group is provided at a predetermined distance from the body contact surface of the acoustic transmission layer.

Abstract: A microfluidic device according to an embodiment includes a microchannel and an inflow part. The microchannel is configured to separate particles contained in a fluid at least in a first direction according to the size of the particles by the action of lift force, and separate the particles in a second direction by the action of flow in a channel cross-section. The inflow part is provided on the upstream from an area where the lift force acts in the microchannel and allows the fluid to flow into the area where the lift force acts. A length of a channel cross-section of the inflow part in the first direction is formed to be smaller than a length of a channel cross-section of the area where the lift force acts in the first direction.

Abstract: An optical measurement method comprises a holding step, a measurement step, and a first application step. In the holding step, a specimen solution containing a specimen and the magnetic particles is held in a specific magnetic field state, in which a magnetic field not lower than a first magnetic field for moving magnetic particles closer to a substrate is not applied, on the substrate or in a storage container different from the substrate. In the measurement step, an elapsed time from a start reference time of the specific magnetic field state is measured. In the first application step, after the elapsed time reaches a predetermined time, the first magnetic field is applied, for a first application time, by a magnet, to the specimen solution introduced to the substrate.

Abstract: A medical information processing device of an embodiment includes processing circuitry. The processing circuitry acquires a first attribute factor group which is a plurality of attribute factors relating to a disease of a target patient and which is a plurality of attribute factors at a first timing. The processing circuitry estimates a second attribute factor group which is a plurality of attribute factors at a second timing after the first timing on the basis of the first attribute factor group. The processing circuitry outputs information including the first attribute factor group and the second attribute factor group via an output interface.

Abstract: A magnetic resonance imaging apparatus according to the present embodiment comprises processing circuitry configured to set a region of interest for a locator image, automatically set an imaging condition based on the region of interest, and cause a sequence control circuitry to perform imaging based on the imaging condition, the sequence control circuitry performing the imaging.

Abstract: A medical image diagnosis apparatus according to one or more embodiments includes an air mattress, an air supplier, and processing circuitry. The air mattress is configured to be placed on a bed. The air mattress includes a plurality of air cells partitioning an inside of the air mattress into a plurality of regions to seal air supplied to the air cells. The air supplier supplies air to the air cells of the air mattress. The processing circuitry is configured to control the supply of air to the air cells of the air mattress so that a top surface of the air mattress may partially protrude upward from a flat state of the air mattress.

Abstract: An ultrasound diagnostic apparatus according to an embodiment includes image processing circuitry. The image processing circuitry acquires, based on a result of ultrasound scanning performed on a subject, blood flow information including a value that indicates a blood flow at each position within the subject and tissue property information including a value that indicates tissue properties at each position within the subject. The image processing circuitry generates a first image in which a difference in value in the blood flow information is represented by at least a difference in hue and a second image in which a difference in value in the tissue property information is represented by a difference other than the difference in hue. The image processing circuitry generates a combined image by combining the first image and the second image.

Abstract: A method is provided for count loss correction based on detector dead time in a radiation diagnosis apparatus. The method includes acquiring scan data from a scan of a patient performed using the radiation diagnosis apparatus; determining, from the acquired scan data, a first count rate occurring in a first energy window spanning a first energy range; determining, from the acquired scan data, a second count rate occurring in a second window spanning a second energy range, the second energy range being different from the first energy range; calculating a particular count loss correction factor based on the determined first count rate and the determined second count rate; and reconstructing an image based on the acquired scan data and the calculated particular count loss correction factor.

Abstract: A method and a system for providing calibration for a photon counting detector forward model for material decomposition. The flux independent weighted bin response function is estimated using the expectation maximization method, and then used to estimate the pileup correction terms at each tube voltage setting for each detector pixel.

Abstract: A medical information processing apparatus according to an embodiment includes a processing circuitry. The processing circuitry is configured: to distribute, to an information processing apparatus provided at each of a plurality of medical institutions, a program for causing a machine learning process to be executed by using medical data held at the medical institution having the information processing apparatus; to receive, from each of the information processing apparatuses, a change amount in a parameter related to the machine learning process, regarding a change caused in conjunction with the execution of the machine learning process; to adjust a value of the parameter on the basis of the received change amount; and to transmit the adjusted parameter to each of the information processing apparatuses to cause the machine learning process to be executed on the basis of the parameter.

Abstract: A medical information anonymizing system includes a processing circuitry. The processing circuitry acquires medical information generated in a format based on a communication standard for a medical image and including a medical image and supplementary information. The processing circuitry adds the anonymization reference information indicating an anonymizing method for anonymizing the medical information to the supplementary information in the medical information. The processing circuitry configured to receive the medical information in which the anonymization reference information is added to the supplementary information and, based on the anonymization reference information added to the medical information, anonymize at least one of the medical image and the supplementary information included in the medical information.

Abstract: A photon counting detector (PCD) apparatus includes a PCD array including a plurality of micro-pixels positioned in at least one of a channel direction and a row direction; and processing circuitry configured to: receive signals from each of the plurality of micro-pixels; configure the PCD array to include (a) a first micro-pixel area including a first group of plural micro-pixels of the plurality of micro-pixels and (b) a second micro-pixel area including a second group of plural micro-pixels of the plurality of micro-pixels, such that a portion of the first and second groups of plural micro-pixels overlap between the first and second groups; bin the signals from the first group of plural micro-pixels into a first virtual bin value; and bin the signals from the second group of plural micro-pixels into a second virtual bin value.

Abstract: A correction X-ray detector according to an embodiment includes a plurality of detector elements configured to detect an X-ray, and processing circuitry. The processing circuitry is configured to acquire a plurality of output values respectively corresponding to the plurality of the plurality of detector elements. The processing circuitry is further configured to determine the detector elements to be used in generating correction data based on the plurality of output values.

Abstract: A method of grouping detection events in an imaging apparatus is described herein. The detection events can include primary detection events and secondary scattered events, which are frequently discarded due to the secondary scattered events, thus reducing sensitivity of the dataset for eventual image reconstruction. The method includes cell modules cascaded with identical parametrized cells, in a pipeline fashion, having the last cell in the chain circle back to the first cell. A rotating data pointer indicates the location of the first entry in the cell pipeline. The described method enables the grouping of multiple samples of detector data in real time with no loss of information, based on a time and location of the detected event. The method can be implemented in an FPGA as a hardware-based real time process.

Abstract: According to one embodiment, a medical diagnostic apparatus includes processing circuitry and display circuitry. The processing circuitry estimates a position of a structure in a subject based on data obtained by scanning with respect to the subject and analyzes tissue characterization in the subject. The display circuitry displays an analysis result of the tissue characterization obtained by the processing circuitry with respect to a plurality of positions in the subject except for the estimated structure position.

Abstract: In one embodiment, a receiving coil includes a plurality of coil elements, wherein: at least one of the coil elements includes a loop coil and a modified dipole disposed inside the loop coil; and the modified dipole includes a main dipole configured to receive a radio-frequency “RF” signal and output a reception signal and a parasitic element that includes a split ring having a gap in part of a ring shape.

Abstract: A deep learning (DL) convolution neural network (CNN) reduces noise in positron emission tomography (PET) images, and is trained using a range of noise levels for the low-quality images having high noise in the training dataset to produce uniform high-quality images having low noise, independently of the noise level of the input image. The DL-CNN network can be implemented by slicing a three-dimensional (3D) PET image into 2D slices along transaxial, coronal, and sagittal planes, using three separate 2D CNN networks for each respective plane, and averaging the outputs from these three separate 2D CNN networks. Feature-oriented training can be implemented by segmenting each training image into lesion and background regions, and, in the loss function, applying greater weights to voxels in the lesion region. Other medical images (e.g. MRI and CT) can be used to enhance resolution of the PET images and provide partial volume corrections.

Abstract: A radiotherapy planning apparatus includes processing circuitry. The processing circuitry obtains a medical image relating to a patient. The processing circuitry obtains number of beams and beam directions of a plurality of radiation beams applied substantially simultaneously to an irradiation area of the patient. The processing circuitry generates a total dose rate distribution which is a spatial distribution of total values of predicted dose rates of the radiation beams to be applied to the patient, based on the medical image and the number and the direction of the radiation beams.

Abstract: A puncture support device includes a display unit, a puncture target setting unit, a puncturable region setting unit, a puncture route extraction unit, a safety degree calculation unit, and an insertion point candidate region display control unit. The puncture target setting unit is configured to set a puncture target in a acquired volume data. The puncturable region setting unit is configured to set a puncturable region on a body surface image. The puncture route extraction unit is configured to extract a puncture route from the set puncturable region on the body surface image to the puncture target. The safety degree calculation unit is configured to calculate a safety degree of the extracted puncture route. The insertion point candidate region display control unit is configured to divide the puncturable region into groups based on the calculated safety degree, and display the divided region on the display unit.