Abstract: A medical image processing method, an X-ray diagnostic apparatus, and a method of generating a learned model includes receiving first X-ray image data, inputting the first X-ray image data to a trained model, outputting, from the trained model, an X-ray image having an image quality higher than an image quality of the first X-ray image data. The learned model was trained using contrastive learning using second X-ray image data as input data, third X-ray image data and fourth X-ray image data as label data, the third X-ray image data being negative label data having worse image quality than the second X-ray image data, and the fourth image data being positive label data having better image quality than the second X-ray image data.

Abstract: A control method for controlling data processing acquired from medical imaging modalities by using multiple data processors connected to multiple medical imaging modalities via a network. The method includes obtaining image information for imaging to be performed with an imaging modality from the multiple imaging modalities. The method also includes obtaining load information of the multiple data processors before the imaging is completed. Allocating, based on graph information generated based on the obtained load information, at least a part of the multiple data processors to processing of data acquired in imaging based on the imaging information. The control method may conclude by performing processing of the acquired data with the allocated data processing resource.

Abstract: Systems and methods are provided for generating training data for training a neural network. The neural network may be a machine learning model. The neural network may be a U-Net neural network. Training data for training a neural network may be generated by combining X-ray image data and non-X-ray image data. Training data for training a neural network may be generated by superimposing data having a characteristic related to a lesion onto X-ray image data. The superimposed data may be used to simulate calcification features in mammographic images. Processing circuitry is configured to perform noise reduction by inputting an input image of a breast into a trained machine-learning model to output an output image in which noise included in the input image is reduced in the output image while leaving a characteristic of a lesion included in the input image undeleted in the output image.

Abstract: A system and method is provided for controlling an acquisition system to obtain, based on a currently acquired set of projection data, a next set of projection data that is to be acquired using a set of learned imaging conditions. The set of learned imaging conditions are, at least in part, based on training data including projection data and dose information. In one embodiment, the initial dose and angle for obtaining the initial set of projection data are chosen at random. In another embodiment, the initial dose and angle for obtaining the initial set of projection data are chosen based on a test scan and a trained neural network for outputting the initial dose and angle using a loss function.

Abstract: A projection dataset from a cone beam computed tomography (CBCT) can be input into a first set of one or more neural networks trained for at least one of saturation correction, truncation correction, and scatter correction. Reconstruction can then be performed on the output projection dataset to produce an image dataset. Thereafter, this image dataset can be input into a second set of one or more neural networks trained for at least one of noise reduction and artefact reduction, thereby generating a higher quality CBCT image.

Abstract: A system and a method by which multiple regions or objects of interest can be indicated within an X-ray image, from which a user can select a primary region or object of interest and accordingly adjust the appropriate X-ray dose for obtaining a better quality image of the selected regions or objects of interest.

Abstract: A method of imaging includes obtaining a first image including projection data representing an intensity of X-rays detected by a plurality of detectors at a first X-ray exposure setting, the X-rays being emitted from an X-ray source; based on a detection result of a first object in the first image: determining a background region of interest (ROI) around the first object, the background ROI including background ROI pixels having a first intensity value corresponding to the intensity of the X-rays; and converting, for each pixel of the background ROI pixels, the first intensity values of the background ROI pixels to a normalized X-ray attenuation factor; and determining a second X-ray exposure setting for use in obtaining a second image based on the background ROI pixels converted to the normalized X-ray attenuation factor.

Abstract: An apparatus for magnetic resonance imaging includes processing circuitry to obtain a set of sequence instructions for performing a magnetic resonance scan; partition the obtained set of sequence instructions into a plurality of kernels by determining partition time points defining boundaries of the plurality of kernels, wherein the partition time points are not equally spaced in time; convert a first kernel of the plurality of kernels into a first hardware instruction set; transmit the first hardware instruction set to a hardware board controller for execution; and reconstruct a magnetic resonance image from received data, including data obtained by executing the first kernel.

Abstract: An X-ray diagnostic apparatus according to an embodiment includes processing circuitry configured to improve quality of fourth data corresponding to a fourth number of views that is smaller than a first number of views by inputting the fourth data to a learned model generated by performing machine learning with second data corresponding to a second number of views as input learning data, and third data corresponding to a third number of views that is larger than the second number of views as output learning data, the second data and the third data being acquired based on first data corresponding to the first number of views. The fourth data is data acquired by tomosynthesis imaging.

Abstract: A control method for controlling data processing acquired from medical imaging modalities by using multiple data processors connected to multiple medical imaging modalities via a network. The method includes obtaining image information for imaging to be performed with an imaging modality from the multiple imaging modalities. The method also includes obtaining load information of the multiple data processors before the imaging is completed. Allocating, based on graph information generated based on the obtained load information, at least a part of the multiple data processors to processing of data acquired in imaging based on the imaging information. The control method may conclude by performing processing of the acquired data with the allocated data processing resource.

Abstract: A general workflow for deep learning based image restoration in X-ray and fluoroscopy/fluorography is disclosed. Higher quality images and lower quality images are generated as training data. This training data can further be categorized by anatomical structure. This training data can be used to train a learned model, such as a neural network or deep-learning neural network. Once trained, the learned model can be used for real-time inferencing. The inferencing can be more further improved by employing a variety of techniques, including pruning the learned model, reducing the precision of the learned mode, utilizing multiple image restoration processors, or dividing a full size image into snippets.

Abstract: A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry acquires image data including image data of a blood vessel of a subject. The processing circuitry performs analysis related to the blood vessel by using the image data, and specifies a region of interest in the blood vessel based on a result of the analysis. The processing circuitry performs fluid analysis on a region other than the region of interest at a first accuracy, and performs fluid analysis on the region of interest at a second accuracy that is higher than the first accuracy.

Abstract: A system and a method by which multiple regions or objects of interest can be indicated within an X-ray image, from which a user can select a primary region or object of interest and accordingly adjust the appropriate X-ray dose for obtaining a better quality image of the selected regions or objects of interest.

Abstract: A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry acquires image data including image data of a blood vessel of a subject. The processing circuitry performs analysis related to the blood vessel by using the image data, and specifies a region of interest in the blood vessel based on a result of the analysis. The processing circuitry performs fluid analysis on a region other than the region of interest at a first accuracy, and performs fluid analysis on the region of interest at a second accuracy that is higher than the first accuracy.

Abstract: A method of imaging includes obtaining a first image including projection data representing an intensity of X-rays detected by a plurality of detectors at a first X-ray exposure setting, the X-rays being emitted from an X-ray source; based on a detection result of a first object in the first image: determining a background region of interest (ROI) around the first object, the background ROI including background ROI pixels having a first intensity value corresponding to the intensity of the X-rays; and converting, for each pixel of the background ROI pixels, the first intensity values of the background ROI pixels to a normalized X-ray attenuation factor; and determining a second X-ray exposure setting for use in obtaining a second image based on the background ROI pixels converted to the normalized X-ray attenuation factor.

Abstract: A system, method and computer readable medium to render, as a single image, source data from a network of data providers, that provide source data of a respective data type. A composition space contains two-dimensional (2D) display surfaces to which the source data is provided from the data providers, and transformation operator surfaces, which are located at different positions in a depth direction than the 2D display surfaces. Each of the transformation operator surfaces represent a respective visual transformation operation on surfaces of the 2D display surfaces that are positioned at lesser depths than the transformation operator surface. Using data-centric communication, updates are published to the 2D display surfaces, the updates including the source data from the data providers, and, upon detecting an update to a subscribed 2D display surface, the subscribed 2D display surface is rendered as the single image by performing the visual transformation operations.

Abstract: A system, method and computer readable medium to render, as a single image, source data from a network of data providers, that provide source data of a respective data type. A composition space contains two-dimensional (2D) display surfaces to which the source data is provided from the data providers, and transformation operator surfaces, which are located at different positions in a depth direction than the 2D display surfaces. Each of the transformation operator surfaces represent a respective visual transformation operation on surfaces of the 2D display surfaces that are positioned at lesser depths than the transformation operator surface. Using data-centric communication, updates are published to the 2D display surfaces, the updates including the source data from the data providers, and, upon detecting an update to a subscribed 2D display surface, the subscribed 2D display surface is rendered as the single image by performing the visual transformation operations.

Abstract: An apparatus and method are provided for computed tomography (CT) imaging to reduce artifacts due to objects outside the field of view (FOV) of a reconstructed image. The artifacts are suppressed by using an iterative reconstruction method to minimize a cost function that includes a de-emphasis operator. The de-emphasis operator operates in the data domain, and minimizes the contributions of data inconsistencies arising from attenuation due to objects outside the FOV. This can be achieved by penalizing images that manifest indicia of artifacts due to outside objects especially those outside objects have high-attenuation densities and minimizing components of the data inconsistency likely attributable to the outside object.

Abstract: A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry acquires image data including image data of a blood vessel of a subject. The processing circuitry performs analysis related to the blood vessel by using the image data, and specifies a region of interest in the blood vessel based on a result of the analysis. The processing circuitry performs fluid analysis on a region other than the region of interest at a first accuracy, and performs fluid analysis on the region of interest at a second accuracy that is higher than the first accuracy.

Abstract: A method and apparatus is provided to generate two X-ray projection images, using different focal-spot sizes in the X-ray source. The large and small focal-spot images have different image qualities (e.g., different signal-to-noise rations (SNR) and different resolution). The two images are combined, in either the spatial or frequency domains, to generate a combined image, exhibiting the best attributes of the constitutive small and large focal-spot images. In the spatial domain, change regions and uniform regions are determined based on spatial variations within the images, and the superposition generating the combined image weights the small focal-spot image more in the change regions and the large focal-spot image more in the uniform regions. In the frequency domain, the combined image superimposes low-frequency components of the large focal-spot image with high-frequency components of the small focal-spot image.