A method for generating a Birds-Eye-View (BEV) space feature map includes obtaining sensor calibration data related to one or more sensors of a vehicle; generating, based on the sensor calibration data, a list of sample positions within a perspective space of the one or more sensors that correspond to a location within Birds-Eye-View (BEV) space; projecting, based on the list of sample positions, the BEV space onto the perspective space of the one or more sensors using variable sample density; and generating a BEV space feature map using the BEV space projected onto the perspective space of the one or more sensors.

An image processing device receives a calibration operation of adjusting a viewpoint when a three-dimensional image obtained by imaging a three-dimensional structure of a biological tissue based on the basis of tomographic information obtained by a sensor that moves in a lumen of the biological tissue is displayed on a display in accordance with a radiation direction of an X-ray, adjusts relative sizes and positions of an acquired X-ray image and the three-dimensional image on the basis of ratio information and position information each time an X-ray image obtained by fluoroscopically viewing the biological tissue is acquired, and causes the display to display the acquired X-ray image and the three-dimensional image so as to overlap each other as viewed from a viewpoint based on the viewpoint information.

An image processing apparatus includes at least one processor, and the processor is configured to: acquire a radiation image and a plurality of continuously captured ultrasound images while a breast is kept in a compression state by a compression member; acquire correction information related to at least one of a tilt of a probe that has performed scanning on the compression member during the capturing of the plurality of ultrasound images or a deflection of the compression member; generate a corrected ultrasound image corrected based on the correction information from the plurality of acquired ultrasound images; and associate the corrected ultrasound image with the radiation image.

A method for creating image data of an examination object using a magnetic resonance system, including: acquiring a first and at least a second set of measurement data at least of one slice, wherein during each acquisition of measurement data different acceleration factors and/or different field of view shift factors are used; and reconstructing image data based on the acquired sets of measurement data.

Techniques for performing iterative MRI image reconstruction by learning complementary multi-prior knowledge from images, k-space data, and calibration data are disclosed. In one method, k-space data is obtained from an MRI scan. Image-space modifications are performed on the k-space data using a first neural network trained to operate on data in image space. The k-space data is converted from the frequency domain to a spatial domain to produce input image-space data. Using the first neural network, output image-space data is generated, which is then converted from the spatial domain to the frequency domain. K-space modifications are performed on the k-space data using a second neural network trained to operate on data in k-space. ACS are encoded using a third neural network to guide the second neural network in learning consistency-aware k-space correlations. The k-space data is converted from the frequency domain to the spatial domain to obtain a reconstructed image.

The disclosure provides a system for EGRT. The system may include a radiotherapy device for treating a subject. The radiotherapy device may include a scintillation camera that is directed at an ROI of the subject. The subject may be injected with a radioactive tracer or implanted with a radioactive marker before treatment. The ROI may undergo a physiological motion during the treatment. The system may deliver a treatment session to the subject by the radiotherapy device. During the treatment session, the system may acquire a target image of the ROI indicative of a distribution of the radioactive tracer or the radioactive maker in the ROI by the scintillation camera, and adapt a radiation beam to be delivered to the subject with respect to the physiological motion of the ROI by adjusting the radiation beam based on the target image.

The present disclosure provides a non-transitory computer-readable recording medium storing a radiographic image analysis program that causes a computer to execute: acquiring a plurality of frame images generated by performing dynamic imaging by irradiating a subject with radiation under an imaging condition corresponding to a combination of a plurality of types of dynamic analyses set in advance; and executing, based on the plurality of frame images, the plurality of types of dynamic analyses included in the combination.

Disclosed herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and an anatomical detection module (122), and a computational system (104). The execution of the machine executable instructions causes the computational system to: receive (200) a set of magnetic resonance images (124) descriptive of a field of view (109) of a subject (318) acquired according to a synthetic magnetic resonance imaging protocol; receive (202) an anomaly indicator (126) from the anomaly detection module in response to inputting at least one of the set of magnetic resonance images into the anomaly detection module; determine (204) a set of reconstruction parameters (128) using the anomaly indicator; and reconstruct (206) a synthesized magnetic resonance image (134) from the set of magnetic resonance images and the set of reconstruction parameters.

Various systems and methods are provided for denoising spectral CT image data, the system and method comprising determining a denoised linear estimation of spectral CT image data by maximizing or minimizing a first objective function, wherein at least one parameter of the denoised linear estimation is determined by at least one machine learning system. The denoiser is based on a Linear Minimum Mean Square Error (LMMSE) estimator. The LMMSE is very fast to compute, but not commonly used for CT image denoising, due to its inability to adapt the amount of denoising to different parts of the image and the difficulty to derive accurate statistical properties from the CT image data. To overcome these problems, a model-based deep learning model, such as a deep neural network that preserves a model based LMMSE structure.

An image processing apparatus generates a first image by extracting a first region which is a first artifact generation source from a CT image, generates a second image by subtracting a value determined according to a specific part from the first image, generates a third image by performing forward projection and back projection on the second image, generates a fourth image which is a difference image between the second image and the third image, and generates a fifth image by correcting an artifact in the CT image using the fourth image.