Abstract: In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a plurality of cameras. The processor is to obtain metadata associated with an initial state of an object, wherein the object is captured by a first camera in a first video stream at a first point in time, and wherein the metadata is obtained based on the first video stream. The processor is further to predict, based on the metadata, a future state of the object at a second point in time, and identify a second camera for capturing the object at the second point in time. The processor is further to configure the second camera to capture the object in a second video stream at the second point in time, wherein the second camera is configured to capture the object based on the future state of the object.

Abstract: An artificial intelligence (AI) decoding apparatus includes a memory storing one or more instructions, and a processor configured to execute the stored one or more instructions, to obtain image data corresponding to a first image that is encoded, obtain a second image corresponding to the first image by decoding the obtained image data, determine whether to perform AI up-scaling of the obtained second image, based on the AI up-scaling of the obtained second image being determined to be performed, obtain a third image by performing the AI up-scaling of the obtained second image through an up-scaling deep neural network (DNN), and output the obtained third image, and based on the AI up-scaling of the obtained second image being determined to be not performed, output the obtained second image.

Abstract: A method of training an image classification model includes obtaining training images associated with labels, where two or more labels of the labels are associated with each of the training images and where each label of the two or more labels corresponds to an image classification class. The method further includes classifying training images into one or more classes using a deep convolutional neural network, and comparing the classification of the training images against labels associated with the training images. The method also includes updating parameters of the deep convolutional neural network based on the comparison of the classification of the training images against the labels associated with the training images.

Abstract: Systems and methods for automated assessment of a vessel are provided. One or more input medical images of a vessel of a patient are received. A plurality of vessel assessment tasks for assessing the vessel is performed using a machine learning based model trained using multi-task learning. The plurality of vessel assessment tasks are performed by the machine learning based model based on shared features extracted from the one or more input medical images. Results of the plurality of vessel assessment tasks or a combination of the results of the plurality of vessel assessment tasks are output.

Abstract: In a method for generating synthetic medical image data, first image data of an object under examination including a first value for a property is acquired, second image data of the object under examination including a second value for the property is acquired, the second value of the property of the second image data is matched to the first value to modify the second image data to generate synthetic image data, and the synthetic image data is provided (e.g. in electronic form as a data file). The first image data can be captured with a first magnetic resonance device at a first point in time, and the second image data can be captured with a second magnetic resonance device at a second point in time.

Abstract: The present disclosure is related to imaging systems and methods. The method includes obtaining image data of a subject to be scanned by a medical device. The method includes determining a scan range of the subject based on the image data. The scan range includes at least one scan area of the subject. The method includes determining at least one parameter value of at least one scan parameter based on the at least one scan area of the subject.

Abstract: An image processing system, which estimates a position and a pose of a camera and performs three-dimensional reconstruction processing of an object having a cylindrical shape by using a photographed image acquired by photographing an inside of the object with the camera, includes a processor. The processor estimates a first center axis of the cylindrical shape by using a group of three-dimensional points obtained by reconstructing, in a three-dimensional space, a group of feature points extracted from the photographed image. In addition, the processor performs bundle adjustment for correcting the position and the pose of the camera and the coordinates of the group of three-dimensional points by using a condition for minimizing a total sum of differences between a radius of the cylindrical shape and respective distances from the first center axis to individual three-dimensional points that constitute the group of three-dimensional points.

Abstract: The invention provides for a magnetic resonance imaging system (100) for acquiring magnetic resonance data (144, 146) of a subject (118) within an imaging zone (108), wherein the magnetic resonance imaging system comprises a memory storing a set of parameter ranges (150). At least a portion of the parameter ranges are user configurable.

Abstract: Provided is an artificial intelligence (AI) decoding apparatus includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory, the processor is configured to: obtain AI data related to AI down-scaling an original image to a first image; obtain image data corresponding to an encoding result on the first image; obtain a second image corresponding to the first image by performing a decoding on the image data; obtain deep neural network (DNN) setting information among a plurality of DNN setting information from the AI data; and obtain, by an up-scaling DNN, a third image by performing the AI up-scaling on the second image, the up-scaling DNN being configured with the obtained DNN setting information, wherein the plurality of DNN setting information comprises a parameter used in the up-scaling DNN, the parameter being obtained through joint training of the up-scaling DNN and a down-scaling DNN, and wherein the down-scaling DNN is used to

Abstract: A determining method includes acquiring first direction information, when a first captured image captured by an imaging device is acquired, by referring to a storage storing a plurality of pieces of direction information indicating a plurality of directions associating with respective shapes of a plurality of contours of an object according to a plurality of directions of the object, the first direction information associated with a shape of a contour that corresponds to a shape of a contour of the subject included in the acquired first captured image among the shapes of the contours, and acquiring second direction information, when a second captured image newly captured by the imaging device is acquired, by referring to the storage to acquire second direction information associated with a shape of a contour that corresponds to a contour of the subject included in acquired second captured image among the shapes of contours.

Abstract: A computer-implemented method includes preprocessing a variable dimension medical image, identifying one or more areas of interest in the medical image; and analyzing the one or more areas of interest using a deep learning model. A computing system includes one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to preprocess a variable dimension medical image, identify one or more areas of interest in the medical image; and analyze the one or more areas of interest using a deep learning model. A non-transitory computer readable medium contains program instructions that when executed, cause a computer to preprocess a variable dimension medical image, identify one or more areas of interest in the medical image, and analyze the one or more areas of interest using a deep learning model.

Abstract: A processor of an endoscope system detects from the observation images a lesion area which is an observation target of the endoscope, judges a level of an oversight risk which is a risk that an operator may overlook the lesion area, on the basis of the observation images, and controls notification methods of detection of the lesion area on the basis of the level of the oversight risk. The processor displays the marker image indicating the lesion area only in a second image region of the display apparatus when a level of the oversight risk relating to the lesion area is a first level and displays the marker image in both a first image region and the second image region which is smaller than the first image region when a level of the oversight risk relating to the lesion area is a second level higher than the first level.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for determining reflectance of an image on a per-pixel basis. More specifically, a characterization module can initially acquire a first data set generated by a multi-channel light source and a second data set generated by a multi-channel image sensor. The first data set may specify the illuminance of each color channel of the multi-channel light source (which is configured to produce a flash), while the second data set may specify the response of each sensor channel of the multi-channel image sensor (which is configured to capture an image in conjunction with the flash). Thus, the characterization module may determine reflectance based on illuminance and sensor response. The characterization module may also be configured to determine illuminance based on reflectance and sensor response, or determine sensor response based on illuminance and reflectance.

Abstract: Digital pathology is the concept of capturing digital images from glass microscope slides in order to record, visualize, analyze, manage, report, share and diagnose pathology specimens. The present disclosure is directed to a desktop slide scanner, which enables pathologists to scan slides at a touch of a button. Included is a workflow for reliable imaging, diagnosis, quantification, management, and sharing of a digital pathology library. Also disclosed herein is an analysis framework that provides for pattern recognition of biological samples represented as digital images to automatically quantitatively score normal cell parameters against disease state parameters. The framework provides a pathologist with an opportunity to see what the algorithm is scoring, and simply agree, or edit the result. This framework offers a new tool to enhance the precision of the current standard of care.

Abstract: Embodiments provide a computer-implemented method of deriving a periodic motion signal from imaging data for continuous bed motion acquisition, including: acquiring a time series of three dimensional image volumes; estimating a first motion signal through a measurement of distribution of each three dimensional image volume; dividing the time-series of three dimensional image volumes into a plurality of axial sections overlapping each other by a predetermined amount; performing a spectral analysis on each axial section to locate a plurality of three dimensional image volumes which are subject to a periodic motion; performing a phase optimization on each axial section to obtain a three dimensional mask; estimating a second motion signal through the three dimensional mask and the time-series of three dimensional image volumes; and estimating a final motion signal based on the first motion signal and the second motion signal.

Abstract: Methods and systems for determining a tumor volume from image data obtained from a functional scanner. The methods and systems can include identifying a portion within a region of interest corresponding to a liver that varies in intensity with its corresponding neighboring portion by a threshold. The method and systems can further include determining a volume of the portion without identifying a boundary of the portion. The portion can also be tracked over time. The image data can include a scan from a SPECT scanner.

Abstract: A method includes receiving, with a computing system, a video item. The method further includes identifying a first set of features within a first frame of the video item. The method further includes identifying, with the computing system, a second set of features within a second frame of the video item, the second frame being subsequent to the first frame. The method further includes determining, with the computing system, differences between the first set of features and the second set of features. The method further includes assigning a clip category to a clip extending between the first frame and the second frame based on the differences.

Abstract: The present invention relates to a pose estimation method of an interventional medical device using a single-view X-ray image which is captured using a bendable interventional medical device equipped with a plurality of radiopaque markers and using an X-ray source. The pose estimation method includes an operation (a) of defining a circle assuming that the interventional medical device is bent at a constant curvature, an operation (b) of extracting a position value of the marker from an X-ray image obtained by the X-ray source projecting X-rays onto the markers, and an operation (c) of setting a projection plane and estimating a shape of the circle using a position value of the marker extracted from a projected image obtained by perspective-projecting the circle onto the projection plane and using the position value of the marker extracted from the X-ray image.

Abstract: A method and ultrasound imaging system includes generating a cine including a plurality of cardiac views based on the cardiac ultrasound data, segmenting a plurality of cardiac chambers from each of the plurality of cardiac images, and automatically determining a cardiac chamber area for each of the plurality of cardiac chambers. The method and ultrasound imaging system includes displaying the cine on a display device and displaying a plurality of single trace curves on the display device at the same time as the cine to provide feedback regarding an acquisition quality of the cine, wherein each of the single trace curves represents the cardiac chamber area for a different one of the plurality of cardiac chambers over the plurality of cardiac cycles.

Abstract: The present disclosure is directed, in part, to methods and systems of intra-operatively identifying a retained surgical item by imaging a surgical item with an intra-operative imaging device to obtain image data, imaging a patient suspected of having a retained surgical item with an intra-operative imaging device to obtain image data, interacting the image data to a module configured to identify the surgical item from the intra-operative surgical item image data, and identifying the retained surgical item from the surgical item image data.