An X-ray source transmits X-rays through a subject and a detector receives the X-ray energy after having passed through the subject. A processing system generates a pre-shot image of the subject using low energy X-ray intensity from the X-ray source and determines a plurality of acquisition parameters for a main scan of the subject based on the pre-shot image. A saturation time of the detector for the corresponding acquisition parameters is determined based on detector calibration data and to determine a number of time frames required to reach the targeted dose based on the saturation time. An X-ray dosage level of the subject is then applied using the X-ray source based on the number of time frames and to generate the image of the subject based on the detected X-ray energy at the X-ray detector for the applied X-ray dosage level.

There is provided a method, comprising feeding a medical image into a detector component trained on a first training dataset of medical images annotated with ground truth boxes depicting a visual finding, obtaining boxes each associated with a respective box score indicative of likelihood of the visual finding, converting each respective box into a respective patch, feeding patches into a patch classifier trained on a second training dataset that includes patches extracted from the ground truth box labels of the first training dataset, wherein a patch score for a patch corresponds to a box score obtained from a box corresponding to the patch, obtaining patch scores indicative of likelihood of the visual finding being depicted, and computing a dot product of the box scores and the patch scores, and providing the dot product as an image-level indication of likelihood of the visual finding being depicted in the medical image.

A processor derives a linear structure image indicating a high-frequency linear structure from each of a plurality of tomographic images indicating tomographic planes of an object, derives a feature amount indicating features of the linear structure from the linear structure image, selects at least one tomographic image or high-frequency tomographic image including the linear structure or a predetermined tomographic image or high-frequency tomographic image on the basis of the feature amount for each corresponding pixel in each of the tomographic images or the high-frequency tomographic images indicating high-frequency components of the tomographic images, and derive a composite two-dimensional image on the basis of the selected tomographic images or high-frequency tomographic images.

A medical image processing apparatus includes an acquisition unit and a processing unit. The acquisition unit acquires volume data of a subject. The processing unit displays a three-dimensional image by rendering the acquired volume data, on a display unit. The processing unit displays a first object showing (i) a point on a body surface of the subject and (ii) a direction to the volume data in the three-dimensional image, and displays a two-dimensional image of a surface including the point on the body surface and being defined based on the direction, in the volume data. The processing unit acquires information of a first operation to change display of the two-dimensional image, and moves the point on the body surface along the body surface of the subject based on the first operation to update display of the first object and the two-dimensional image.

The present disclosure discloses a three-dimensional automatic location system for an epileptogenic focus based on deep learning. The system includes: a PET image acquisition and labelling module; a registration module mapping PET image to standard symmetrical brain template; a PET image preprocessing module generating mirror image pairs of left and right brain image blocks; a network SiameseNet training module containing two deep residual convolutional neural networks which share weight parameters, an output layer connecting a multilayer perceptron and a softmax layer, and using a training set of an epileptogenic focus image and an normal image to train the network to obtain a network model; a classification module and epileptogenic focus location module, using the trained network model to generate a probabilistic heatmap for the newly input PET image, a classifier determining whether the image is normal or epileptogenic focus sample, and then predicting a position for the epileptogenic focus region.

The medical image processing apparatus according to the present embodiment includes processing circuitry. The processing circuitry is configured to acquire volume data generated based on tomosynthesis imaging of a subject. The processing circuitry is configured to set a virtual focal point at a position different from a focal position in the tomosynthesis imaging. The processing circuitry is configured to generate a pseudo projection image based on the virtual focal point and the volume data.

A system for preparing an ablation procedure is disclosed. The system comprises a generator for generating electrical pulses, a plurality of probes for delivering the electrical pulses to a target tissue, one or more sensors for indicating a position of the probes, a display device, and a processor. The processor is configured to receive an image of the target tissue, obtain a planned probe arrangement for the plurality of probes, identify a projected position for an origin probe based on the image and the planned probe arrangement, and determine a real-time position of the origin probe based on signals from the sensors. The processor is further configured to display the projected position and the real-time position for the origin probe superimposed over the image on a display device, and determine a placed position of the origin probe based on the real-time position.

Systems, methods and instrumentalities are described herein for automating a medical environment. The automation may be realized using one or more sensing devices and at least one processing device. The sensing devices may be configured to capture images of the medical environment and provide the images to the processing device. The processing device may determine characteristics of the medical environment based on the images and automate one or more aspects of the operations in the medical environment. These characteristics may include, e.g., people and/or objects present in the images and respective locations of the people and/or objects in the medical environment. The operations that may be automated may include, e.g., maneuvering and/or positioning a medical device based on the location of a patient, determining and/or adjusting the parameters of a medical device, managing a workflow, providing instructions and/or alerts to a patient or a physician, etc.

A method for determining an abnormality in a medical device from a medical image is provided. The method for determining an abnormality in a medical device comprises receiving a medical image, and detecting information on at least a part of a target medical device included in the received medical image.

A radiographic image capturing system includes the following. A capturing stand includes a holder to hold radiographic image capturing devices. A radiation irradiator irradiates the radiographic image capturing devices loaded in the holder at once. An image processor generates a plurality of images based on image data acquired by the radiographic image capturing devices. The image processor removes a streaky component residing in the generated image to correct the image. Such process includes forming a smoothed image by smoothing with a low-pass filter, and subtracting an interpolation image to extract a streaky image from the smoothing image and adding the streaky image to remove the streaky component. The smoothing includes reflecting smoothing on pixels showing a subject structure using a low-pass filter with a size larger in the horizontal direction compared to pixels other than pixels showing the subject structure.