Embodiments predict early stage NSCLC recurrence, and include processors configured to access a pathology image of a region of tissue demonstrating early stage NSCLC; extract a set of pathomic features from the pathology image; access a radiological image of the region of tissue; extract a set of radiomic features from the radiological image; generate a combined feature set that includes at least one member of the set of pathomic features, and at least one member of the set of radiomic features; compute a probability that the region of tissue will experience NSCLC recurrence based, at least in part, on the combined feature set; and classify the region of tissue as recurrent or non-recurrent based, at least in part, on the probability. Embodiments may display the classification, or generate a personalized treatment plan based on the classification.

The present invention discloses a method for finding a cell nucleus of a target cell from a cell image, wherein the cell image includes the target cell and at least one variation cell, and the target cell includes cytoplasm and the cell nucleus. The method includes steps of: (a) processing the cell image via an image processor such that the cytoplasm, the cell nucleus and the variation cell have different shades of color; (b) demarcating the outlines of the cytoplasm, the cell nucleus and the variation cell; (c) calculating geometrical reference points of the outlines; (d) calculating the distances from the geometrical reference point of the cytoplasm outline to the geometrical reference point of the cell nucleus outline and to the geometrical reference points of the variation cell outlines; and (e) finding a specific geometrical reference point having a shortest distance to locate a specific outline corresponding to the specific geometrical reference point as the cell nucleus.

A system and a method for assessing quality of a high-dynamic range (HDR) image. The system comprises a feature extraction module arranged to extract a plurality of frequency features on a pair of reference image and a distorted image generated based on the reference image; a comparison module arranged to compare a pair of feature maps obtained by processing the extracted frequency features on both the reference image and the distorted image; and a scoring module arrange to output an image quality assessment (IQA) score of the distorted image with reference to the reference image provided; wherein the plurality of frequency features are associated with sensitive information in a human visual system (HVS).

Disclosed herein are an apparatus and method for processing a textured image. The apparatus includes a filter unit for detecting an edge of an input image and transforming the input image into an image in which a density of the edge is represented; a smoothing unit for removing noise from the transformed image and smoothing the image; a clustering unit for changing a number of regions into which the smoothed image is to be segmented and clustering the smoothed image a preset number of times; and a cluster optimization unit for setting a final number of clusters for the input image by optimizing a number of clusters based on a previously learned ground truth, for selecting an image corresponding to the final number of clusters from results of clustering by which the image is segmented into a different number of regions, and for outputting the selected image.

An apparatus and method for local quantization for convolutional neural networks. For example, one embodiment of an apparatus comprises: a convolutional neural network module comprising a neuron network structure to perform pattern recognition within an input image using a set of input image values; and a quantization module to quantize input image values to reduce processing requirements within one or more stages of the neuron network structure; the quantization module to perform quantization of each of a plurality of patches of the input image using a first quantization policy to generate a first matrix of quantized input data and to perform quantization of each of a plurality of kernel data using a second quantization policy to generate a second matrix of quantized kernel data.

A method is provided to perform local de-noising of an image. The method includes obtaining a region of interest and a region of noise within a scan. The method also includes determining, for a first image based on the region of interest and a second image based on the region of noise, sample blocks and atoms for each image, where each atom contributes to a weighted sum that approximates a sample block in the image. The method also includes determining a measure of similarity of each atom from the first image with atoms from the second image and removing an atom from the first image if the measure of similarity exceeds a predetermined threshold value. The method also includes reconstructing a de-noised image based on atoms remaining in the first image after removing the atom from the first image, and presenting the de-noised image on a display device.

A method for vessel mapping and quantification. The method comprises pre-processing a retinal image to generate a vessel segmented image and processing the vessel segmented image to generate an image with a central light reflex. The method further includes identifying a cylindrical or tube-shaped region in the central light reflex and determining a closed contour representing the cylindrical shaped region and representing the closed contour by a function. The method computes a ratio of a minimum and maximum radius of the cylinder to determine an average shape of the cylinder associated with the central light reflex by using the function. The image is further processed to apply a morphological skeletonization operation to generate vessel centerlines and the segmented vascular network of the retinal image. In an example embodiment, a method for artery-vein nicking quantification for retinal blood vessels is performed by computing width of the vessel near and away from a cross over point of the vessels. In another example embodiment, a feature associate with the central light reflex is identified and compared with a second feature in the same location evaluated at a different time zone to confirm the associated shape of the light reflex. In another example embodiment, retinal focal arteriolar narrowing (FAN) is identified and quantified value is generated. In another example embodiment, a true optic disc is identified based on a combination of features and parameters associate with the vessel.

Different machine vision acuity levels for anomaly detection in an image. An image sensing pixel array generates image data representative of the image having a first region (e.g., focal region) and a second region (e.g. periphery). A memory cell array stores a first weight matrix representative of a first kernel of a convolutional neural network and a second weight matrix representative of a second kernel. A logic circuit can apply the first kernel to the first region using the first weight matrix to generate first feature data at a first stride length with quantization at a first precision level. The logic circuit can apply the second kernel to the second region using the second weight matrix to generate second feature data at a second stride length with quantization at a second precision level.

Disclosed is a method for identifying lawn grass which includes capturing an image of the terrain in front of a mower, segmenting the image into neighborhoods, calculating at least two image statistics for each of the neighborhoods, generating a binary representation of each image statistic. The binary representation of each image statistic is generated by comparing the calculated image statistic values to predetermined image statistic values for grass. The method further includes weighting each of the binary representations of each image statistic, and summing corresponding neighborhoods for all image statistics. A binary threshold is applied to each of the summed neighborhoods to generate a binary map representing grass containing areas and non-grass containing areas.

A method for encoding space-time signals comprises: collecting space-time signals of various local spatial positions in a monitoring area, and accumulating the space-time signals according to time, so as to obtain cumulative signal intensity values; transforming the cumulative signal intensity values by means of a filter, and outputting a pulse signal when a transformation result exceeds a specific threshold; arranging pulse signals corresponding to a local spatial position into a sequence according to the time, so as to obtain a pulse sequence expressing the local spatial position signals and a change process thereof; and arranging the pulse sequences of all local spatial positions into a pulse sequence array according to interrelation among the spatial positions to serve as an encoding for dynamic space-time signals of the monitoring area.