A medical image diagnostic apparatus according to an embodiment includes memory circuitry and processing circuitry. The memory circuitry stores therein a plurality of anatomical landmarks in a subject in association with a plurality of groups. The processing circuitry generates three-dimensional image data of the subject. The processing circuitry selects at least one group among the groups based on set examination information and a type of scan to be performed, and detects a site of the subject corresponding to at least one group, based on anatomical landmarks corresponding to a selected group. The processing circuitry controls to output information indicating a detected site.

An X-ray device includes a camera to image an object and output the image of the object, a display member using a touch screen to display the image of the object output from the camera, and an X-ray irradiation region of the object, an X-ray irradiation region controller to control a region of the object to which an X-ray is irradiated, and a control member to enable the irradiation region controller to control the region of the object to which an X-ray is irradiated according to the X-ray irradiation region, when the X-ray irradiation region is determined, based on the image of the object displayed in the display member.

According to one embodiment, a medical image diagnostic apparatus includes a storage memory, processing circuitry, and a display. The storage memory stores data of a plurality of FFR distribution maps constituting a time series regarding a coronary artery, and data of a plurality of morphological images corresponding to the time series. The processing circuitry converts the plurality of FFR distribution maps into a plurality of corresponding color maps, respectively. The display displays a plurality of superposed images obtained by superposing the plurality of color maps and the plurality of morphological images respectively corresponding in phase to the plurality of color maps. The display restricts display targets for the plurality of color maps based on the plurality of FFR distribution maps or the plurality of morphological images.

A conversion device (20) is operable to perform a learning-based method of generating a synthetic electron density image (sCT) of an anatomical portion based on one or more magnetic resonance, MR, images. The method is processing-efficient and capable of producing highly accurate sCT images irrespective of misalignment in the underlying training set. The conversion device (20) receives and installs a machine-learning model (22) trained to predict coefficients of an image transfer function (24). The conversion device (20) then receives a current set of MR images (MRI) of the anatomical portion, computes current coefficients ([C]) of the image transfer function (24) by operating the machine-learning model (22) on the current set of MR images (MRI), and computes a current sCT image of the anatomical portion by operating the current coefficients ([C]), in accordance with the image transfer function (24), on the current set of MR images (MRI).

A medical image-processing apparatus according to embodiments includes processing circuitry. The processing circuitry is configured to acquire image data including a blood vessel of a subject. The processing circuitry is configured to acquire an index value relating to blood flow at each position of the blood vessel by performing fluid analysis of a structure of the blood vessel included in the acquired image data. The processing circuitry is configured to acquire information indicating a display condition of the index value, as switching information to switch a display mode at displaying the index value. The processing circuitry is configured to generate a result image in which pixel values reflecting the index value are assigned in a display mode according to the switching information, for an image indicating a blood vessel of the subject. The processing circuitry is configured to cause a display to display the result image.

Systems and methods for four-dimensional CT scan are provided. The methods may include determining a first region of a subject and a second region. A movement of the subject may occur within the second region. The methods may further include generating a first image set by performing, based on a first operation parameter corresponding to a first scan, the first scan on the first region of the subject, and generating a second image set by performing, based on a second operation parameter corresponding to a second scan, the second scan on a second region of the subject. The methods may further include obtaining movement information corresponding to the movement of the subject and determining a final image set based on the first image set, the movement information, and the second image set.

Systems and methods for multi-modal, multi-resolution deep learning neural networks for segmentation, outcomes prediction and longitudinal response monitoring to immunotherapy and radiotherapy are detailed herein. A structure-specific Generational Adversarial Network (SSGAN) is used to synthesize realistic and structure-preserving images not produced using state-of-the art GANs and simultaneously incorporate constraints to produce synthetic images. A deeply supervised, Multi-modality, Multi-Resolution Residual Networks (DeepMMRRN) for tumor and organs-at-risk (OAR) segmentation may be used for tumor and OAR segmentation. The DeepMMRRN may combine multiple modalities for tumor and OAR segmentation. Accurate segmentation is may be realized by maximizing network capacity by simultaneously using features at multiple scales and resolutions and feature selection through deep supervision. DeepMMRRN Radiomics may be used for predicting and longitudinal monitoring response to immunotherapy. Auto-segmentations may be combined with radiomics analysis for predicting response prior to treatment initiation. Quantification of entire tumor burden may be used for automatic response assessment.

The present invention discloses a method and a system of vertebral compression fracture detection. The method of vertebral compression fracture detection includes: recombining a plurality of anatomical images captured in at least a spine segment of a target individual into a 3D image; using a multi-planar reconstruction method to reformat the 3D image to obtain at least one sagittal reformatted image; using a classification model to determine whether the sagittal reformatted image covers the middle section of the vertebral column or not; using a vertebral detection method to detect each vertebral body in the sagittal reformatted image covering the middle section of the vertebral column; using a keypoint localization method to localize a plurality of keypoints of each vertebral body which was detected in the sagittal reformatted image; evaluating the compression fracture grade of each vertebral body in the sagittal reformatted image.

An imaging apparatus and associated methods are provided to efficiently estimate scatter during multi-fraction treatments for improved quality and workflow. Estimated scatter from one fraction during a treatment course can be utilized during subsequent fractions, allowing for measurements with higher scatter-to-primary ratios. The quality of scatter estimates can be maintained, while workflow improves and dosage decreases. Scan configuration limits can be utilized to maintain a minimum level of scatter measurement quality. Patient information can be monitored to ensure that prior fraction scatter estimates are still applicable to current patient status.

A computer-implemented system: at least one processor communicably coupled to at least one nontransitory processor-readable storage medium storing processor-executable instructions or data receives segmentation learning data comprising a plurality of batches of labeled anatomical image sets, each image set comprising image data representative of a series of slices of a three-dimensional bony structure, and each image set including at least one label which identifies the region of a particular part of the bony structure depicted in each image of the image set, wherein the label indicates one of a plurality of classes indicating parts of the bone anatomy; trains a segmentation CNN, that is a fully convolutional neural network model with layer skip connections, to segment semantically at least one part of the bony structure utilizing the received segmentation learning data; and stores the trained segmentation CNN in at least one nontransitory processor-readable storage medium of the machine learning system.