Systems and methods of detecting a presence of opacification or pneumatization in skeletal structures of patients are disclosed. The systems and methods include receiving images, processing the images using a convolutional neural network, and generating, with the convolutional neural network, an opacification score for the image. Systems and methods include training the convolutional neural network to delineate skeletal structure pixels within a computed tomography scan image and to generate an intensity value for each skeletal structure pixel within a computed tomography scan image to determine an opacification score for the computed tomography scan image.

A system and method for generating a parametric map of a subject's brain includes receiving non-contrast computed tomography (NCCT) imaging data and receiving computed tomography perfusion (CTP) data. The method further includes creating a baseline image by utilizing the NCCT data and generating a parametric map using the CTP data and the baseline image.

The present disclosure provides methods of imaging cancerous cells in a subject, wherein the cancerous cells are localized to the skeletal system or central nervous system of the subject, the method comprising administering to the subject an effective amount of 18F-fluoroacetate, detecting a first signal emitted by 18F-fluoroacetate, and generating an image representative of the location and/or amount of the first signal to image the cancerous cells. In some embodiments, the methods further comprising diagnosing, prognosing, staging, and/or monitoring the progression of a disease or disorder, such as acute lymphoblastic leukemia and/or leptomeningeal disease.

Disclosed herein are systems and methods for interactive graphical user interfaces (GUIs) that users (e.g., medical professionals) can use to interact with modelled versions of brains and easily and intuitively analyze deep and/or lateral structures in the brain. A user can, for example, selectively view structures and their connectivity data (e.g., nodes and edges) relative to other structures and connectivity data over a representation of a particular patient's brain. Emphasis can be minimized for certain foreground nodes and edges (e.g., lateral structures) to make it easier for the user to focus on and analyze deeper structures that otherwise can be challenging to visualize and understand. A method can include overlaying deep and non-deep nodes on a representation of a brain, displaying the representation of the brain in a GUI, receiving user input indicating interest in focusing on one or more deep nodes, and taking an action based on the input.

The present disclosure is related to systems and methods for image processing. The method may include obtaining an image including at least one of a first type of artifact or a second type of artifact. The method may include determining, based on a trained machine learning model, at least one of first information associated with the first type of artifact or second information associated with the second type of artifact in the image. The trained machine learning model may include a first trained model and a second trained model. The first trained model may be configured to determine the first information. The second trained model may be configured to determine the second information. The method may include generating a target image based on at least part of the first information and the second information.

The present invention relates to sedation assessment. In order to facilitate sedation depth monitoring in an autonomous imaging setting, it is proposed to use the imaging modality itself to measure the response to suitable reflexes in order to determine the depth of sedation wherein suitable reflexes include, but are not limited to, the pupil reflex, so-called superficial reflexes and the withdrawal reflexes. In one embodiment, the pupil reflex may be measured in an MRI system by repeated interleaving of dedicated iris MR imaging with the conventional scan protocol. In another embodiment, superficial reflexes in response to stroking of the skin may be measured. This may involve a dedicated actuator that may be closely integrated with the imaging modality, e.g. an MR receive coil applied to the patient. Alternatively, remote haptic systems may be used. The reflex is then acquired with a suitable diagnostic imaging method. In another embodiment, the withdrawal reflex in response to pain may be measured. This may involve an actuator that induces sudden stitching pain or very local temperature-induced pain and that is closely integrated with the imaging modality, e.g. a pinching device integrated with a patient support or an MR receive coil applied to the patient. The reflex is then acquired with a suitable diagnostic imaging method.

The disclosure discloses a method, a device, a system and a computer storage medium for obtaining the CT perfusion imaging parameter maps of brain. The method includes: obtaining CT perfusion images, pre-processing the CT perfusion images, and obtaining discrete contrast agent concentration curves C(n) of each pixel point in the brain tissue; reading the acquisition time information of the CT perfusion images to obtain the acquisition time arrays T(n); intercepting the acquisition time arrays T(n) to obtain the relative acquisition time arrays t(n); combining the discrete contrast agent concentration curves C(n) with the corresponding relative acquisition time arrays t(n) to obtain the discrete time-concentration curves C(t.sub.n) of each pixel point in the brain tissue; after fitting or interpolating the discrete time-concentration curves C(t.sub.n), re-discretizing at the same time interval, and obtaining the discrete time-concentration curves C(n)′ of each pixel point in brain tissue.

The invention relates to a problem of setting mutual position of an anatomy being imaged and imaging means of a computed tomography imaging apparatus so that specifically the very volume of the anatomy desired to be imaged actually is imaged. To further the positioning, a positioning tool in a form of a three-dimensional virtual positioning model (40), generated from the anatomy to be imaged, is shown on a display from which the volume (41) of the anatomy desired to be imaged can be pointed, selected or defined.

This invention relates generally to methods for localization and visualization of implanted electrodes and penetrating probes in the brain in 3D space with consideration of functional brain anatomy. Particularly, this invention relates to precise and sophisticated methods of localizing and visualizing implanted electrodes to the cortical surface and/or topological volumes of a patient's brain using 3D modeling, and more particularly to methods of accurately mapping implanted electrodes to the cortical topology and/or associated topological volumes of a patient's brain, such as, for example, by utilizing recursive grid partitioning on a manipulable virtual replicate of a patient's brain. This invention further relates to methods of surgical intervention utilizing accurate cortical surface modeling and/or topological volume modeling of a patient's brain for targeted placement of electrodes and/or utilization thereof for surgical intervention in the placement of catheters or other probes into it.

A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry acquires medical images of multiple time phases. The processing circuitry generates a vascular territory image showing plural vascular territories included in the subject tissue. The processing circuitry sets a region of interest in the subject tissue. The processing circuitry sets at least two regions out of the vascular territories and an ischemia area in the region of interest based on the vascular territory image. The processing circuitry calculates a ratio of each of the at least two regions to the region of interest. The processing circuitry outputs information about the ratio.