Abstract: A pattern recognition system including an image gathering unit that gathers at least one digital representation of a field, an image analysis unit that pre-processes the at least one digital representation of a field, an annotation unit that provides a visualization of at least one channel for each of the at least one digital representation of the field, where the image analysis unit generates a plurality of image samples from each of the at least one digital representation of the field, and the image analysis unit splits each of the image samples into a plurality of categories.

Abstract: An image generation device includes: a detection unit 43 that performs processing of detecting a specific feature from a plurality of focus images which include an observation target and are in different focus states; a determination unit 44 that determines a parameter indicating a degree of application of a region image to a combination region image in a case where the combination region image is generated from the region image, for each set of the region images in a plurality of corresponding regions respectively corresponding to the plurality of focus images, based on the specific feature detected by the detection unit 43; and a generation unit 45 that generates the combination region image by combining the region images for each of the plurality of corresponding regions based on the parameter determined by the determination unit 44.

Abstract: A method includes assigning, to first voxels in a model of tissue of a chamber of a heart, respective first values of a parameter at respective locations on the tissue, the first voxels representing the locations, respectively. Some of the locations are on an endocardial surface of the tissue, and others of the locations are on an epicardial surface of the tissue. The method further includes assigning respective second values to second voxels in the model, a subset of which represent a portion of the tissue between the endocardial surface and the epicardial surface, by interpolating the first values. Other embodiments are also described.

Abstract: A method for optimizing an ultrasonic imaging system parameter based on deep learning, comprising the following steps: step 1: collecting samples for training neural networks, the samples comprising ultrasound image samples i, and a corresponding ultrasonic imaging system parameter vector sample p used by an ultrasonic imaging system when the ultrasonic image samples are collected; step 2: establishing a neural network model and training the neural networks to convergence by using the samples collected=in step 1, so as to obtain a trained neural network system onn; and step 3: taking the original ultrasonic imaging system parameter vector p or the original ultrasonic image as an input to be input into the neural network system onn trained in step 2, at this moment, a parameter obtained from an output end of onn being an optimized ultrasonic imaging system parameter vector ep=onn(p).

Abstract: Systems and methods are presented for providing a machine learning model for segmenting an optical coherence tomography (OCT) image. A first OCT image is obtained, and then labeled with identified boundaries associated with different tissues in the first OCT image using a graph search algorithm. Portions of the labeled first OCT image are extracted to generate a first plurality of image tiles. A second plurality of image tiles is generated by manipulating at least one image tile from the first plurality of image tiles, such as by rotating and/or flipping the at least one image tile. The machine learning model is trained using the first plurality of image tiles and the second plurality of image tiles. The trained machine learning model is used to perform segmentation in a second OCT image.

Abstract: A colon cleanliness indicating device including a forward toilet-secured receiving section configured with a recessed receptacle for receiving colonic effluent and a rearward indicating section for indicating a degree of colon cleanliness. The indicating section is formed with one or more channels in fluid communication with the receptacle through which the received colonic effluent is flowable and by which the received colonic effluent can be visualized in order to assess a degree of colon cleanliness.

Abstract: A method, a controller, and a surgical hybrid navigation system for transferring a registration of three dimensional image data of a surgical object from a first to a second surgical navigation system are described. A first tracker that is detectable by a first detector of the first surgical navigation system is arranged in a fixed spatial relationship with the surgical object and a second tracker that is detectable by a second detector of the second surgical navigation system is arranged in a fixed spatial relationship with the surgical object. The method includes registering the three dimensional image data of the surgical object in a first coordinate system of the first surgical navigation system and determining a first position and orientation of the first tracker in the first coordinate system and a second position and orientation of the second tracker in a second coordinate system of the second surgical navigation system.

Abstract: A training device and a training method for training a multi-goal model based on goals in a goal space are provided. The training device includes a memory and a processor coupled to the memory. The processor is configured to set the goal space, to acquire a plurality of sub-goal spaces of different levels of difficulty; change a sub-goal space to be processed from a current sub-goal space to a next sub-goal space of a higher level of difficulty; select, as sampling goals, goals at least from the current sub-goal space, and to acquire transitions related to the sampling goals by executing actions; train the multi-goal model based on the transitions, and evaluate the multi-goal model by calculating a success rate for achieving goals in the current sub-goal space.

Abstract: The present disclosure is related to an optical encoder which is configured to provide precise coding reference data by feature recognition technology. To apply the present disclosure, it is not necessary to provide particular dense patterns on a working surface. The precise coding reference data can be generated by detecting surface features of the working surface.

Abstract: According to an example, a technique for image processing is provided, the technique comprising: obtaining a first image and a second image that at least partially illustrate the same real-world scene, wherein the first image comprises a visible light image and the second image comprises a thermal image; identifying one or more spatial portions of the second image that represent a predefined temperature range; identifying one or more spatial portions of the first image that illustrate the same portions of the real-world scene as illustrated in the identified one or more spatial portions of the second image; and deriving, based on the first image, a composite image wherein the identified one or more spatial portions of the first image are emphasized.

Abstract: A method and a device for performing enhanced thermal digital subtraction angiography comprising infrared video camera, computer cable of subtracting all images produced by tissues having a temperature below a setup point, reconstructing and displaying 2D or 3D images of the received data, performing measurement of the vessels being displayed, conducting data analysis and mathematical calculation of hemodynamic parameters, storing and displaying the images produced. Said device is coupled to embodiments to warm the intravascular injectate, to warm the J-tip guide wire and to warm the intravascular catheter during angiography and during endovascular procedures. Furthermore, the device can be used to perform non-enhanced thermal digital subtraction imaging of part of interest and enhanced thermal digital subtraction imaging for joint, epidural and intrathecal space producing thermal arthrography, epidurography and myelography.

Abstract: A neural network system for identifying positions of objects in an input image can include an object detector neural network, a memory interface subsystem, and an external memory. The object detector neural network is configured to, at each time step of multiple successive time steps, (i) receive a first neural network input that represents the input image and a second neural network input that identifies a first set of positions of the input image that have each been classified as showing a respective object of the set of objects, and (ii) process the first and second inputs to generate a set of output scores that each represents a respective likelihood that an object that is not one of the objects shown at any of the positions in the first set of positions is shown at a respective position of the input image that corresponds to the output score.

Abstract: A method is for actuating a medical imaging device for generating a second three-dimensional image dataset including a target region in a region of interest of a patient with a functional impairment. The method includes providing a first three-dimensional image dataset including the region of interest of the patient; identifying the target region based on the first three-dimensional image dataset, a partial region of the region of interest with the functional impairment being determined; determining an imaging parameter for generating the second three-dimensional image dataset based on the identified target region; and actuating the medical imaging device based on the imaging parameter for the generation of the second three-dimensional image dataset.

Abstract: A magnetic resonance (MR) imaging method of detecting and scoring motion artifacts in MR images of an object is provided. The method includes computing a k-space difference map based at least in part on first MR signals of the object acquired with a first coil and second MR signals of the object acquired with a second coil. The method also includes generating a difference plot based on the k-space difference map, the difference plot including a curve. The method further includes calculating a motion score based on the curve in the difference plot, wherein the motion score indicates the level of motion artifacts in the image caused by motion of the object during acquisition of the first MR signals and the second MR signals, and the motion score includes an area under the curve. Moreover, the method includes outputting the motion score.

Abstract: A multi-modality phantom is provided. The multi-modality phantom includes a container and an insert. The container defines an exterior that is separated from an interior space and designed to receive a tissue-mimicking medium for an ultrasound imaging process. The container further includes at least one access port formed in the container to perform the ultrasound imaging process of the interior space. The insert can be dimensioned to be selectively arranged within the interior space of the container. The insert includes imaging features arranged to simulate an environment and constructed to yield simultaneous imaging results when performing the ultrasound imaging process and at least one non-ultrasound imaging process.

Abstract: The invention discloses an unsupervised content-preserved domain adaptation method for multiple CT lung texture recognition, which belongs to the field of image processing and computer vision. This method enables the deep network model of lung texture recognition trained in advance on one type of CT data (on the source domain), when applied to another CT image (on the target domain), under the premise of only obtaining target domain CT image and not requiring manually label the typical lung texture, the adversarial learning mechanism and the specially designed content consistency network module can be used to fine-tune the deep network model to maintain high performance in lung texture recognition on the target domain. This method not only saves development labor and time costs, but also is easy to implement and has high practicability.

Abstract: The apparati, methods, and computer program products disclosed herein can be used to nondestructively detect undissolved particles, such as glass flakes and/or protein aggregates, in a fluid in a vessel, such as, but not limited to, a fluid that contains a drug.

Abstract: Systems and methods for processing electronic images from a medical device comprise receiving an image frame from the medical device, and determining a first color channel and a second color channel in the image frame. A location of an electromagnetic beam halo may be identified by comparing the first color channel and second color channel. Edges of an electromagnetic beam may be determined based on the electromagnetic beam halo, and size metrics of the electromagnetic beam may be determined based on the edges of the electromagnetic beam. A visual indicator on the image frame may be displayed based on the size metrics of the electromagnetic beam.

Abstract: Systems and methods are disclosed for assessing the quality of medical images of at least a portion of a patient's anatomy, using a computer system. One method includes receiving one or more images of at least a portion of the patient's anatomy; determining, using a processor of the computer system, one or more image properties of the received images; performing, using a processor of the computer system, anatomic localization or modeling of at least a portion of the patient's anatomy based on the received images; obtaining an identification of one or more image characteristics associated with an anatomic feature of the patient's anatomy based on the anatomic localization or modeling; and calculating, using a processor of the computer system, an image quality score based on the one or more image properties and the one or more image characteristics.

Abstract: A non-transitory computer readable medium storing data and computer implementable instructions that, when executed by at least one processor, cause the at least one processor to perform operations for generating cross section views of a wound, the operations including receiving 3D information of a wound based on information captured using an image sensor associated with an image plane substantially parallel to the wound; generating a cross section view of the wound by analyzing the 3D information; and providing data configured to cause a presentation of the generated cross section view of the wound.