Abstract: The method includes generating, for each of a plurality of original images, a first artificially degraded image by applying a first image-artifact-generation logic on each of the original images; and generating the program logic by training an untrained version of a first machine-learning logic that encodes a first artifacts-removal logic on the original images and their respectively generated first degraded images; and returning the trained first machine-learning logic as the program logic or as a component thereof. The first image-artifact-generation logic is A) an image-acquisition-system-specific image-artifact-generation logic or B) a tissue-staining-artifact-generation logic.

Abstract: A system including a hierarchical analytics framework that can utilize a first set of machine learned algorithms to identify and quantify a set of biological properties utilizing medical imaging data is provided. System can segment the medical imaging data based on the quantified biological properties to delineate existence of perivascular adipose tissue. The system can also segment the medical imaging data based on the quantified biological properties to determine a lumen boundary and/or determine a cap thickness based on a minimum distance between the lumen boundary and LRNC regions.

Abstract: An object detection device for detecting a target object from an image, includes: a first detection unit configured to detect a plurality of candidate regions in which the target object exists from the image; a region integration unit configured to determine one or more integrated regions based on the plurality of candidate regions detected by the first detection unit; a selection unit configured to select at least a part of the integrated regions; and a second detection unit configured to detect the target object from the selected integrated region using a detection algorithm different from a detection algorithm used by the first detection unit.

Abstract: The invention relates to a method of identifying a biomarker in a tissue sample. The method comprises receiving an acquired image depicting a tissue sample, the pixel intensity values of the acquired image correlating with an autofluorescence signal or of an X-ray induced signal or a signal of a non-biomarker specific stain or a signal of a first biomarker specific stain adapted to selectively stain a first biomarker. The acquired image is input into a trained machine learning logic—MLL which automatically transforms the acquired image into an output image highlighting tissue regions predicted to comprise a second biomarker.

Abstract: A system and method for planning and performing an interventional procedure based on the spatial relationships between identified points. The system includes a storage device (102) having an image (104) which includes a plurality of targets (107). A spatial determination device (114) is configured to determine distances and/or orientation between each of the targets. The system is configured to compare the distances and generate a warning signal if at least one of the distances is less than a minimum threshold (128). An image generation device (116) is configured to generate a graphical representation for display to the user which shows the spatial information between a selected target with respect to the other targets. A planning device (126) is configured to modify or consolidate targets automatically or based on a user's input in order to more effectively plan or execute an interventional procedure.

Abstract: A colon polyp image processing method and apparatus and a system are disclosed in the embodiments of this application to detect a position of a polyp in real time and determine a property of the polyp, and thereby improve the processing efficiency of a polyp image. Embodiment of this application provide a colon polyp image processing method that can include detecting a position of a polyp in a to-be-processed endoscopic image by using a polyp positioning model, and positioning a polyp image block in the endoscopic image. The polyp image block can include a position region of the polyp in the endoscopic image. The method can further include performing a polyp type classification type on the polyp image block by using a polyp property identification model, and outputting an identification result.

Abstract: Techniques are disclosed to leverage the use of convolutional neural networks or similar machine learning algorithms to predict an underlying susceptibility distribution from MRI phase data, thereby solving the ill-posed inverse problem. These techniques include the use of Deep Quantitative Susceptibility “DeepQSM” mapping, which uses a large amount of simulated susceptibility distributions and computes phase distribution using a unique forward solution. These examples are then used to train a deep convolutional neuronal network to invert the ill-posed problem.

Abstract: An image processing apparatus includes an acquisition unit configured to acquire a first medical image and a second medical image that are three-dimensional images obtained by imaging a subject, a determination unit configured to determine a first resolution based on a resolution of the first medical image and determine a second resolution based on a predetermined resolution, a first generation unit configured to generate a first subtraction image having the first resolution by performing a first subtraction process between the first and second medical images, and generate a second subtraction image having the second resolution by performing a second subtraction process between the first and second medical images, and a second generation unit configured to generate a projection image using the second subtraction image.

Abstract: A method and apparatus include receiving a three dimensional (3D) non-contrast computed tomography (NCCT) image of a head including a hematoma. A plurality of two dimensional (2D) images of the head including the hematoma are generated using the 3D NCCT image of the head including the hematoma. A plurality of 2D hematoma images are generated using a first 2D convolutional neural network (CNN) based on the plurality of 2D images. A 3D region of interest (ROI) that encompasses the hematoma is identified based on the plurality of 2D hematoma images. A plurality of 2D images that correspond to the ROI are generated. A hematoma expansion (HE) prediction score is determined using a second CNN based on the plurality of 2D images that correspond to the ROI. The HE prediction score is provided.

Abstract: A device and a method for post-processing of computed tomography (CT), which are adapted to improve an identification image of a focal nodular hyperplasia (FNH) of a liver, are provided. The method includes: obtaining the identification image including a liver region and a non-liver region and a Hounsfield unit (HU) value of each pixel corresponding the identification image, wherein the liver region includes an FNH candidate region; calculating an average HU of the liver region; adjusting an HU value of the non-liver region to the average HU value of the liver region with respect to the identification image to generate a processed identification image; and updating the FNH candidate region according to a morphological algorithm based on the processed identification image to generate an updated FNH candidate region.

Abstract: A system for objectively analyzing medical image data for the presence of diffuse white matter abnormalities (DWMA) is configured to identify and determine DWMA characteristics that are not visually apparent. As compared to subjective visual diagnosis, objectively determined DWMA characteristics may be automatically compared to each other, and may be compared to and associated with various scales, evaluations, or other assessment criteria used to measure aspects of infant development. As a result, the disclosed system may objectively determine an impact that objectively determined DWMA characteristics will have on one or more developmental scales, which can be expressed as a time deficit, score deficit, or other value indicative of development deficits.

Abstract: Systems and methods for rapid, accurate, fully-automated, brain hemorrhage deep learning (DL) based assessment tools are provided, to assist clinicians in the detection & characterization of hemorrhages or bleeds. Images may be acquired from a subject using an imaging source, and preprocessed to cleanup, reformat, and perform any needed interpolation prior to being analyzed by an artificial intelligence network, such as a convolutional neural network (CNN). The artificial intelligence network identifies and labels regions of interest in the image, such as identifying any hemorrhages or bleeds. An output for a user may also include a confidence value associated with the identification.

Abstract: A medical system comprises processing circuitry configured to: load medical images sequentially from a data store which stores a set of medical images, each having an associated location; receive a current location of a medical image that is currently displayed on the display; receive an input operation from a user; process the input operation to determine whether the input operation is of a first type or the input operation is of a second type, wherein the first type of input operation is intended to be less precise than the second type of input operation, and to determine a destination location in dependence on the current location and the input operation; perform a first display operation based on the destination location if the input operation is of the first type; and perform a second display operation based on the destination location if the input operation is of the second type.

Abstract: A non-transitory computer readable medium storing instructions readable and executable by an imaging workstation (14) including at least one electronic processor (16) to perform a dataset generation method (100) operating on emission imaging data acquired of a patient for one or more axial frames at a corresponding one or more bed positions, the method comprising: (a) identifying a frame of interest from the one or more axial frames; (b) generating simulated lesion data by simulating emission imaging data for the frame of interest of at least one simulated lesion placed in the frame of interest; (c) generating simulated frame emission imaging data by simulating emission imaging data for the frame of interest of the patient; (d) determining a normalization factor comprising a ratio of the value of a quantitative metric for the simulated patient data and the value of the quantitative metric for the emission imaging data acquired of the same patient for the frame of interest; and (e) generating a hybrid data set

Abstract: The present invention relates to an apparatus (10) for presentation of dark field information. It is described to provide (210) an X-ray attenuation image of a region of interest of an object. A dark field X-ray image of the region of interest of the object is also provided (220). A plurality of sub-regions of the region of interest are defined (230) based on the X-ray attenuation image of the region of interest or based on the dark field X-ray image of the region of interest. At least one quantitative value is derived (240) for each of the plurality of sub-regions, wherein the at least one quantitative value for a sub-region comprises data derived from the X-ray attenuation image of the sub-region and data derived from the dark field X-ray image of the sub-region. A plurality of figures of merit are assigned (250) to the plurality of sub-regions, wherein a figure of merit for a sub-region is based on the at least one quantitative value for the sub-region.

Abstract: The present disclosure provides systems and methods for image processing. The method may include obtaining an initial image; obtaining an intermediate image corresponding to the initial image, the intermediate image including pixels or voxels associated with at least a portion of a target object in the initial image; obtaining a trained processing model; and generating, based on the initial image and the intermediate image, a target image associated with the target object using the trained processing model.

Abstract: There is provided a computer-implemented method and system (100) for determining regions of hyperdense lung parenchyma in an image of a lung. The system (100) comprises a memory (106) comprising instruction data representing a set of instructions and a processor (102) configured to communicate with the memory and to execute the set of instructions. The set of instructions, when executed by the processor (102), cause the processor (102) to locate a vessel in the image, determine a density of lung parenchyma in a region of the image that neighbours the located vessel, and determine whether the region of the image comprises hyperdense lung parenchyma based on the determined density, hyperdense lung parenchyma having a density greater than ?800 HU.

Abstract: A medical image diagnostic system includes processing circuitry configured (to): (a) acquire a trained model generated by using, as learning data, images or signals corresponding to a first group of time-series images acquired by performing a first pre-scan on a first patient injected with a contrast agent in a first examination, as well as timing information about timing of a transition from a first pre-scan to a first main scan in a first examination, and information about appropriateness of the timing; and (b) determine appropriate timing of a transition from a second pre-scan to a second main scan by inputting, to the trained model, images or signals corresponding to a second group of time-series images acquired by performing the second pre-scan on a second patient injected with a contrast agent in the second examination different from the first examination.

Abstract: A probability map of prostate tumor location is generated and displayed in response to receiving anatomic diagnostic medical imaging, such as from magnetic resonance (MR) scanning. A registration process is performed on the images in relation to a model built of prostate anatomy across different subjects in an enhanced prostate template. A probability map is created of tumor locations followed by transforming the imaging to incorporate the probability map and output a resultant image.

Abstract: According to one embodiment, a medical image processing apparatus of an embodiment includes an acquirer, a reliability setter and a learner. The acquirer acquires training data created by a creator on the basis of a medical image. The reliability setter sets, to the training data acquired by the acquirer, reliability information based on a creation situation of the training data or information about the creator who created the training data. The learner generates a learned model using the training data according to weighting based on the reliability information set by the reliability setter.