Abstract: A method of planning an image-guided interventional procedure to be performed on a patient, where expected motion of the patient, such as that of a breathing cycle, is determined on a sequence of preoperative images, and the procedure trajectory is planned accordingly. The method takes into account the initial positions of the interventional entry, the target region, and any obstructions or forbidden regions between the entry point and the target region, and uses object tracking methods of image processing on the preoperative images to determine how the positions of these three elements change relative to each other during the patient's motion cycle. The method may automatically search in at least some of the preoperative images taken at different temporal points of the motion cycle, for a path connecting the entry point with the target and avoiding the obstacles, which provides minimal lateral pressure on the patient's tissues.

Abstract: Provided is a technology for extracting an image of a target plane from 2D or 3D image data acquired by a medical imaging apparatus with a small amount of computation and at high speed. A plane of a target plane including a predetermined structure is extracted from image data of a subject. A region of the predetermined structure included in the plane is detected by applying a learning model learned using learning data including a target plane for learning including an image of the structure and a region-of-interest plane for learning obtained by cutting out and enlarging a partial region including the structure in the target plane for learning to a plurality of planes obtained from the image data, and the plane of the target plane is extracted based on the detected region of the predetermined structure.

Abstract: A system and kit for capturing a 3D image of a body a user includes a plurality of pillar segments being configurable between an assembled configuration and a disassembled configuration. In the assembled configuration, the pillar segments are joined to form one or more upstanding sensing pillars. A plurality of sensors operable to capture image data are distributed along the one or more sensing pillars. The plurality of sensors have fields of view that are overlapping when supported on the sensing pillars. In the disassembled configuration, transportation of the pillar segments is facilitated. The system and kit may be suitable for use at a remote location. Additional functionalities may include a power storage unit, solar charging panels, climate control subsystem, and wireless communication submodule. In operation, the sensing pillars may be enclosed within an enclosure.

Abstract: A medical processing apparatus comprises processing circuitry configured to: receive an image data set for rendering; for each of a plurality of a pixels or voxels in the image data set: set a region of interest around the pixel or voxel; determine a maximum data value and a minimum data value for pixels or voxels in the region of interest; and designate the pixel or voxel as visible or as non-visible based on the maximum data value and the minimum data value for the region of interest; and perform a rendering process using the pixels or voxels of the image data set that designated as visible.

Abstract: The present disclosure relates to methods and systems for obtaining image information of an organism including a set of optical data; calculating a growth index based on the set of optical data; and calculating an anticipated harvest time based on the growth index, where the image information includes at least one of: (a) visible image data obtained from an image sensor and non-visible image data obtained from the image sensor, and (b) a set of image data from at least two image capture devices, where the at least two image capture devices capture the set of image data from at least two positions.

Abstract: The present application belongs to the technical field of oil and gas exploration and development, and specifically provides a rock stratification identification method and apparatus, a device and a storage medium. The method includes: acquiring multiple sets of CT slice images of a rock, where each set of the CT slice images include a first CT slice image and a second CT slice image, the first CT slice image and the second CT slice image are acquired by scanning a same depth section of the rock, scanning energy corresponding to the first CT slice image is different form scanning energy corresponding to the second CT slice image; determining multiple dual energy indices of the rock according to the multiple sets of CT slice images; and determining a rock stratification according to the multiple dual energy indices, which can identify stratification of a large-scale rock by using CT.

Abstract: The present disclosure may provide a method. The method may include processing an image of a subject using a detection model to generate one or more detection results corresponding to one or more objects in the image; and generating an image metric of the image based on the one or more detection results corresponding to the one or more objects.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a plurality of possible segmentations of an image. In one aspect, a method comprises: receiving a request to generate a plurality of possible segmentations of an image; sampling a plurality of latent variables from a latent space, wherein each latent variable is sampled from the latent space in accordance with a respective probability distribution over the latent space that is determined based on the image; generating a plurality of possible segmentations of the image, comprising, for each latent variable, processing the image and the latent variable using a segmentation neural network having a plurality of segmentation neural network parameters to generate the possible segmentation of the image; and providing the plurality of possible segmentations of the image in response to the request.

Abstract: Disclosed is a monitoring method wherein: a target is prepared using terrain model data including terrain location information; at a first time, an image of the target is picked up by means of an image pickup unit of a surveying device, and first image data is generated; at a second time after the first time, an image of the target is picked by means of the image pickup unit of the surveying device, and second image data is generated; and displacement of the target is detected using a first image based on the first image data, and a second image based on the second image data.

Abstract: A camera mounted on a seafaring vessel obtains an image showing an object. The distance to the object is computed using, in part, a normal vector of the plane containing the camera and the horizon.

Abstract: Apparatus for an automatic identification of medically relevant video elements, the apparatus comprising a data input, configured to receive a data stream of image slices, wherein the data stream of image slices represents a temporal course of a view of image slices defined by a masking strip of video images from a video which has been recorded during a medical surgery on a patient an analysis apparatus configured to analyze the data stream of image slices via an analysis comprising at least one predefined analysis step for the presence of at least one sought-for feature and to output a result of the presence, and a processing device configured to output a start mark which indicates a correspondence between the presence and a position in the data stream of image slices if the result indicates the presence of the sought-for feature. Also, a corresponding method is disclosed.

Abstract: A method and system for classification of cells and particles in a biological sample using an automated image-based feature extraction and classification architecture. A method operates by applying a mask or series of masks to an image, extracting features from the unmasked portions of the image based on the content and location of colored pixels, selecting a subset of the extracted features, and mapping the subset of the extracted features into a classifier architecture. In a majority of cases, the first level model architecture provides an accurate identification of the cell or particle. In a minority of cases, the classification of the cell or particle requires a second level step requiring the use of numerical or categorical values from the first level in combination with a second level model.

Abstract: A diagnosis support system having a processor configured to acquire medical images; detect a medicine and/or equipment used when the medical images are captured, from the medical images by image recognition; detect a region of interest from the medical images by image recognition; assign, to the medical image from which the medicine and/or equipment is detected, first detection information indicating the detected medicine and/or equipment; and assign, to the medical image from which the region of interest is detected, second detection information indicating the detected region of interest, display, on a display device, the medical images in a list in a display form according to the first detection information and the second detection information.

Abstract: A method of recognizing animals includes recognizing a plurality of body parts of a plurality of animals based on at least one image of the animals, in which the plurality of body parts include a plurality of types of body parts, including determining first estimated positions of the recognized body parts in the at least one image. The method includes estimating a plurality of first associations of body parts based on the at least one image of the animals, each first association of body parts associates a body part of an animal with at least one other body part of the same animal, including determining relative positions of the body parts in each estimated first association of body parts in the at least one image.

Abstract: A non-transitory storage medium stores instructions readable and executable by an electronic processor (20) to perform a method (100) for estimating singles rates for detectors (16) of a detector array (14) of a positron emission tomography (PET) imaging device (12).

Abstract: In one embodiment, a video analysis service receives video data captured by one or more cameras at a particular location. The service applies a neural network-based model to portions of the video data, to identify objects within the video data. The service maps outputs of the neural network-based model to symbols using a conceptual space. The outputs of the model comprise the identified objects. The service applies a symbolic reasoning engine to the symbols, to generate an alert. The service sends the alert to a user interface in conjunction with the video data.

Abstract: The present invention relates to a method and a device for estimating a full shape of a lens of an eye from measurements of the lens taken in-vivo by optical imaging techniques, the measurements comprising visible portions of the lens, the method comprises defining non-visible portions of the lens parting from the in-vivo measurements and using a geometrical model of a lens previously built from ex-vivo measurements. The full shape parameters of the crystalline lens can be estimated in the present invention from optical imaging techniques to improve the estimation of the IOL position and thus the IOL power selection.

Abstract: An all-weather target detection method based on a vision and millimeter wave fusion includes: simultaneously acquiring continuous image data and point cloud data using two types of sensors of a vehicle-mounted camera and a millimeter wave radar; pre-processing the image data and point cloud data; fusing the pre-processed image data and point cloud data by using a pre-established fusion model, and outputting a fused feature map; and inputting the fused feature map into a YOLOv5 detection network for detection, and outputting a target detection result by non-maximum suppression. The method fully fuses millimeter wave radar echo intensity and distance information with the vehicle-mounted camera images. It analyzes different features of a millimeter wave radar point cloud and fuses the features with image information by using different feature extraction structures and ways, so that the advantages of the two types of sensor data complement each other.

Abstract: Example implementations described herein are directed to depression detection on roadways (e.g., potholes, horizontal panel lines of a roadway, etc.) through using vision sensor to realize improved safety for advanced driver assistance systems (ADAS) and autonomous driving (AD). Example implementations described herein detect candidate depressions in the roadway in real time and adjust the control of the vehicle system according to the detected depressions.

Abstract: In some embodiments, a method comprises: obtaining a 2D ultrasound image of an imaged region of a subject, the imaged region comprising bone; identifying model template cross-sections of a 3D model of the bone corresponding to the 2D image at least in part by registering the 2D ultrasound image to the 3D model, wherein the model template cross-sections are defined prior to obtaining such 2D image, the model template cross-sections having size and shape representative of a population of potential subjects; identifying at least one location of at least one landmark feature of the bone in the 2D image based on results of the registration; and generating a visualization that includes: a visualization of the 2D image and a visualization of one of the identified cross-sections of the 3D model, wherein the visualization indicates the at least one location of the at least one landmark feature.