Abstract: An image processing system (IPS) and related method. The system (IPS) comprises an input interface (IN) for receiving an image (IM) of an object (OB) acquired by an imaging apparatus (IA). A kernel provider (KP) of the system (IPS) is configured to provide respective scatter kernels for at least two scatter types. A scatter correction module (SCM) of the system (IPS) is configured to perform a correction in the image based on the provided at least two kernels.

Abstract: A probe includes a working channel, at least one optical element provided in the working channel and configured to acquire a spectral image of surface information of an object, and an ultrasonic transducer arranged in the working channel and configured to acquire an ultrasonic image of depth information of the target and move with respect to the at least one optical element.

Abstract: A search pattern is generated based on an input search word comprising a first sequence of bits. The search pattern comprises a representation of the input search word and a representation of an inverse of the input search word. The search pattern is provided as input to search lines of a ternary content-addressable memory (TCAM) block. A subset of the search lines is set to a logical high state based on a first portion of the input search word being designated as don't-care bits. The search pattern causes at least one string in the CAM block to be conductive and provide a signal in response to a data entry stored on the string comprising a second portion of the input search word that excludes the don't-care bits. A location of the data entry is determined and output.

Abstract: A non-volatile memory includes a first semiconductor layer vertically stacked on a second semiconductor layer and including a first memory group, a second memory group, a third memory group and a fourth memory group. The second semiconductor layer includes a first region, a second region, a third region and a fourth region respectively underlying the first memory group, second memory group, third memory group and fourth memory group. The first region includes one driving circuit connected to memory cells of one of the second memory group, third memory group and fourth memory group through a first word line, and another driving circuit connected to memory cells of the first memory group through a first bit line, wherein the first word line and first bit line extend in the same horizontal direction.

Abstract: A method of using a machine learning model to output a task-specific prediction may include receiving a digitized cytology image of a cytology sample and applying a machine learning model to isolate cells of the digitized cytology image. The machine learning model may include identifying a plurality of sub-portions of the digitized cytology image, identifying, for each sub-portion of the plurality of sub-portions, either background or cell, and determining cell sub-images of the digitized cytology image. Each cell sub-image may comprise a cell of the digitized cytology image, based on the identifying either background or cell. The method may further comprise determining a plurality of features based on the cell sub-images, each of the cell sub-images being associated with at least one of the plurality of features, determining an aggregated feature based on the plurality of features, and training a machine learning model to predict a target task based on the aggregated feature.

Abstract: An apparatus for performing fuzzy template matching includes multiple damped oscillators arranged in at least one two-dimensional matrix, each of the damped oscillators being capacitively coupled to at least one adjacent damped oscillator in the matrix. The apparatus further includes peripheral circuitry coupled with the damped oscillators. The peripheral circuitry is configured to selectively interface with the damped oscillators, as a function of one or more control signals supplied to the peripheral circuitry, and to generate at least one output signal indicative of an accuracy of matching between a template pattern and an input pattern.

Abstract: Disclosed is a method, a computer readable storage medium and an apparatus for processing medical image data. Input medical image data is received at a data processing system, which is an artificial intelligence-based system. An identification process is performed at the data processing system on the input medical image data to identify a volume of interest within which an instance of a predetermined anatomical structure is located. First and second determination processes are performed at the data processing system to determine, respectively, first and second anatomical directions for the instance of the anatomical structure that are defined relative to the coordinate system of the input medical image data. Output data relating to the first and second anatomical directions is output from the data processing system.

Abstract: A memory is disclosed that includes a logic die having first and second memory interface circuits. A first memory die is stacked with the logic die, and includes first and second memory arrays. The first memory array couples to the first memory interface circuit. The second memory array couples to the second interface circuit. A second memory die is stacked with the logic die and the first memory die. The second memory die includes third and fourth memory arrays. The third memory array couples to the first memory interface circuit. The fourth memory array couples to the second memory interface circuit. Accesses to the first and third memory arrays are carried out independently from accesses to the second and fourth memory arrays.

Abstract: A resistive random-access memory (ReRAM) array is provided. The ReRAM array includes a silicon over insulator (SOI) substrate; a first bit line; a first inverted bit line of the first bit line; a second bit line; a second inverted bit line of the second bit line; a first word line; a first inverted word line of the first word line; a first ReRAM cell comprising a first MOSFET, a second MOSFET, and a resistive element; and a second ReRAM cell comprising a first MOSFET, a second MOSFET, and a resistive element connected in series; wherein upon applying a predefined potential on elements of the first ReRAM cell, a state of the first ReRAM cell is adjusted without effecting a state of the second ReRAM.

Abstract: A method for predicting a pulmonary disease includes acquiring a three-dimensional computed tomography (CT) image from two-dimensional CT images, each of which captures a respective body position of a first patient, dividing the three-dimensional CT image into a plurality of regions to obtain region-based three-dimensional CT images configured to be used for fractal analysis, calculating a region-based fractal dimension value indicating a fractal complexity of a respective region-based three-dimensional CT image among the generated region-based three-dimensional computed tomography images, adding additional information to the region-based fractal dimension value to generate high-dimensional data, and generating status information of the first patient based on the complexity of the generated high-dimensional data.

Abstract: Embodiments herein relate to systems, apparatuses, or processes directed to facilitating increased clock speeds on a substrate by lowering the impedance of traces that provide clock signals to components such as DRAM. For example, embodiments may include a substrate with a first layer and a second layer parallel to the first layer with a first trace coupled with the first layer in a routing configuration and a second trace coupled with the second layer in the routing configuration, where the routing configuration of the first trace and the second trace substantially overlap each other with respect to an axis perpendicular to the first layer and the second layer, and where the first trace and the second trace are electrically coupled by a first and a second electrical coupling perpendicular to the first layer and the second layer.

Abstract: To provide a medical image processing apparatus and a medical image processing method enabling a reduction in burden of re-imaging and re-interpretation of a medical image. The medical image processing apparatus for processing a medical image includes: a detection section that detects, from the medical image, a candidate region which is a region including a lesion candidate or target tissue, and that calculates an identification score for the candidate region; a designated region acquisition section that acquires a designated region which is a region designated by an operator; and a redetection section that calculates an identification score for the designated region based on the designated region and multiple predefined regions which are regions used in a process of detecting the candidate region.

Abstract: A device is provided that may include an illuminator operable to interrogate at least a lens of an eye. The illuminator may include at least one light source and a lens positioned with respect to the light source to produce interrogating radiation. The device also may include a detector operable to image the total autofluorescence response of the lens of the eye as viewable through a pupil of the eye, the detector comprising an image sensor. The device can also include a controller operable to control operation of the illuminator and the detector. The controller may interrogate at least the lens of the eye by activating the illuminator for a select time, obtain at least one image of the total autofluorescence response of the lens at the detector during or immediately subsequent to the select time, and transmit the at least one image to a remote device.

Abstract: A method for automatically training and applying automatic segmentation in digital image processing is provided. The method may include, in response to receiving a plurality of digital images wherein each digital image associated with the plurality of digital images comprises only one annotated structure out of a plurality of structures included in each digital image, applying a predictive algorithm to each digital image that determines a predicted probability of each annotation in each digital image, determines a predicted background for each digital image, and merges the predicted probability of each annotation with the predicted background in each digital image. The method may further include, in response to applying the predictive algorithm, using the received plurality of digital images to train and apply an application for automatically segmenting unlabeled digital images.

Abstract: A method for identifying a component part includes receiving a digital image of an object and textual information about the object and accessing images of component parts and textual information about the component parts. The method further includes applying the digital image to a first classifier trained on the images of the component parts to classify the object as a first of the component parts and applying the textual information about the object to a second classifier trained on the textual information about the component parts to recognize the textual information as information about the first of the component parts or a second of the component parts. The method further includes identifying the object as a component part that is the first of the component parts or the second of the component parts and accessing a data record with information about the component part.

Abstract: A memory cell includes a first resistive memory element, a second resistive memory element electrically coupled with the first resistive memory element at a common node, and a switching element comprising an input terminal electrically coupled with the common node, the switching element comprising a driver configured to float during one or more operations.

Abstract: An assessment assembly (10) for assessing a fundus imaging system (12) includes at least one, curved, flexible resolution test chart (40). Each of the resolution test charts (40) can include a chart body (342), and a plurality of spaced apart chart features (344). Moreover, each of the resolution test charts (40) can be fixedly coupled to an artificial retina region (36) of an artificial eye (14). The artificial retina region (36) can be shaped and sized similar to a retina region (19E) of a human eye (19), and the artificial retina region (36) can have scattering and depolarization properties that are similar to the scattering and depolarization properties of the retina region (19E) of the human eye (19). The fundus imaging system (12) can capture one or more images (20) of the resolution test charts (40) that are evaluated to determine a resolution of the fundus imaging system (12).

Abstract: According to one embodiment, a memory device includes: a variable resistance memory region; a semiconductor layer; an insulating layer; first and second word lines; and a first select gate line. When information stored in the first memory cell is read, or when information is written into the first memory cell, after a voltage of the first select gate line is set to a first voltage and voltages of the first and second word lines are set to a second voltage, the voltage of the first select gate line is increased from the first voltage to a third voltage. After the voltage of the first select gate line is increased to at least the second voltage, the voltage of the first word line is decreased from the second voltage to the first voltage, and the voltage of the second word line is increased from the second voltage to a fourth voltage.

Abstract: An x-ray microscopy method that obtains a classification of different particles by distinguishing between different material phases through a combination of image processing involving morphological edge enhancement and possibly resolved absorption contrast differences between the phases along with optional wavelet filtering.

Abstract: Various methods and systems are provided for reducing blur in a diagnostic image. In one example, a method includes reducing blur in a diagnostic image by applying a deconvolution filter to the diagnostic image, the deconvolution filter generated from a point spread function (PSF) estimation of blur at each pixel of the diagnostic image, the PSF estimation generated based on a motion vector field between the diagnostic image and a pre-shot image acquired prior to the diagnostic image.