A standard blood vessel generation device specifies, for each subject, a blood vessel region in which a blood vessel is depicted in an image, derives a feature line that connects feature points included in a plurality of figures included in the blood vessel region and that is along the blood vessel region, specifies a branch point on the feature line, disposes division points for line division on a line with a start point being one of two adjacent branch points and an end point being the other branch point, executes, for each set of division points having the same order counted from the start point in a plurality of the subjects, a process of calculating a statistic amount of coordinates for the set of the division points and setting a point whose coordinates are equal to the statistic amount as a standard point, and a process of setting a dimension of a predetermined site in the figure including the standard point and included in the blood vessel region as a standard diameter, and generates a standard blood vessel that is a blood vessel whose diameter at the standard point is the standard diameter and that is along a standard line connecting a plurality of the standard points.

A device, as disclosed, may be suitable for use with a tomographic imager comprising an X-ray source and a plane detector that are movable in rotation. The device (e.g., radiopaque device) includes a registration phantom that includes several radiopaque markers and that is placeable along a part of the spine of a patient at a predetermined distance from a volume of interest to be imaged. Several radiopaque screens, integral with the registration phantom, include a lower face, an internal face oriented toward the registration phantom, and an external face oriented toward the X-ray source (410), respectively towards the detector. The radiopaque device is configured so that, when it is placed on the back of a patient, at least part of the X-rays that pass from the X-ray source to the plane detector through the registration phantom see their intensity attenuated by passing through the radiopaque screens.

Various embodiments of a device for in-vivo measurements radiopharmaceuticals used for diagnosis and monitoring of radiotherapy are presented. In some embodiments, the present disclosure relates to a device having a cannula that may include a measurement chamber, a radiation detector and a delivery lumen, wherein the device may be used to both deliver material to the patient (e.g., radiotracers used in radiopharmaceuticals) and measure levels and concentrations of radioactive material in, for example, the patient's blood both during and after administration of the radioactive material. In some embodiments, particles emitted by the radioactive material interact with a scintillation material, resulting in the release of light that may be transmitted, via the scintillation material and/or fiber optic material, to an optical detectors or processor for processing. In some embodiments, particle absorbing materials may be used to limit measurements to materials within the measurement chamber or other area of interest.

An X-ray diagnostic apparatus according to an embodiment includes an X-ray tube, an X-ray detector, image generating circuitry, and processing circuitry. The X-ray tube emits X-rays. The X-ray detector detects X-rays emitted from the X-ray tube and transmitted through a subject. The processing circuitry receives a designating operation related a display mode for a target that is at least one of a region of the subject and an object inserted in the subject. In response to the designating operation, the processing circuitry changes the display mode of the target in an X-ray projection image that is based on a detection result of the X-ray detector, the display mode being changed based on three-dimensional medical image data related to the subject.

This disclosure relates to detecting visual findings in anatomical images. Methods comprise inputting anatomical images into a neural network to output a feature vector and computing an indication of visual findings being present in the images by a dense layer of the neural network that takes as input the feature vector and outputs an indication of whether each of the visual findings is present in the anatomical images. The neural network is trained on a training dataset including anatomical images, and labels associated with the anatomical images and each of the visual findings. The visual findings may be organised as a hierarchical ontology tree. The neural network may be trained by evaluating the performance of neural networks in detecting the visual findings and a negation pair class which comprises anatomical images where a first visual finding is identified in the absence of a second visual finding.

The present invention relates to an X-ray imaging system (10), comprising a radiograph X-ray attenuation image acquisition unit (20), at least one sensor (30), and a processing unit (40). The radiograph X-ray attenuation image acquisition unit is configured to acquire a radiograph image of a patient. The radiograph X-ray attenuation image acquisition unit is configured to provide the radiograph image to the processing unit. The at least one sensor is configured to acquire sensor data of the patient. The at least one sensor is configured to provide the sensor data to the processing unit. The processing unit is configured to determine a magnitude and direction of movement of the patient during a time of acquisition of the radiograph image, the determination comprising utilization of the sensor data. The processing unit is configured to post-process the radiograph image comprising utilization of the determined magnitude and direction of movement of the patient during the time of acquisition of the radiograph image.

The present disclosure is related to systems and methods for image reconstruction. The method may include obtaining at least one positron emission tomography (PET) image of a subject. The at least one PET image may be generated based on PET data acquired during an examination period. In the examination period, the subject may be injected with a tracer. The method may also include determining, based on the at least one PET image, an input function that reflects a concentration change of the tracer in the subject during the examination period. The method may further include generating a parametric image based on the input function and the at least one PET image according to a non-linear parametric estimation algorithm. The parametric image may reflect a kinetic parameter of the tracer in the subject.

Present invention relates to safety features for radiopharmaceutical dispensing system, wherein dispensing system comprises a controller, a source of radiopharmaceutical and other components. The controller is configured to perform automated quality control of the system to ensure that the system complies quality control before radioactive dose dispensing. The quality control comprises scanning the dispensing system, network or connected devices for an unauthorized connection, malware and ensure that system is free of any such cybersecurity threat before dispensing a radioactive dose.

This disclosure relates to detecting visual findings in anatomical images. Methods comprise inputting anatomical images into a neural network to output a feature vector and computing an indication of visual findings being present in the images by a dense layer of the neural network that takes as input the feature vector and outputs an indication of whether each of the visual findings is present in the anatomical images. The neural network is trained on a training dataset including anatomical images, and labels associated with the anatomical images and each of the visual findings. The visual findings may be organised as a hierarchical ontology tree. The neural network may be trained by evaluating the performance of neural networks in detecting the visual findings and a negation pair class which comprises anatomical images where a first visual finding is identified in the absence of a second visual finding.

A method is described for positioning of an examination object for an imaging method. The method is used to record an external image of externally visible features of the examination object. The recording of the external image is used as the basis for determining a position and/or orientation of at least one part of the examination object assigned to the imaged features. Subsequently, a check is performed as to whether the determined position and/or orientation of the at least one part of the examination object conforms to a reference position and/or reference orientation. Finally, if the determined position and/or orientation of the at least one part of the examination object does not conform to the reference position and/or reference orientation, the position and/or orientation of the at least one part of the examination object is corrected. Also described is an object-positioning facility. Furthermore, an imaging medical facility is described.