-
公开(公告)号：US11727534B2
公开(公告)日：2023-08-15
申请号：US17114924
申请日：2020-12-08
IPC分类号： G06T5/00
CPC分类号： G06T5/001 , G06T2200/24 , G06T2207/10101 , G06T2207/20081 , G06T2207/20084
摘要： In an aspect for generating device-specific OCT image, one or more processors may be configured for receiving, at a unified domain generator, first image data corresponding to OCT image scans captured by one or more OCT devices; processing, by the unified domain generator, the first image data to generate second image data corresponding to a unified representation of the OCT image scans; determining by a unified discriminator, third image data corresponding to a quality subset of the unified representation of the OCT image scans having a base resolution satisfying a first condition and a base noise type satisfying a second condition; and processing, using a conditional generator, the third image data to generate fourth image data corresponding to device-specific OCT image scans having a device-specific resolution satisfying a third condition and a device-specific noise type satisfying a fourth condition.
-
2.发明授权公开(公告)号：US10762459B2
公开(公告)日：2020-09-01
申请号：US14984417
申请日：2015-12-30
发明人： Rahil Garnavi , James R. Kozloski , Timothy Lynar , John Wagner
摘要： Methods and systems for predicting injury risk include generating state sequences that precede a hazard event based on information regarding a user's state. A cognitive suite of workplace hygiene and injury predictors (WHIP) is generated based on the state sequences using a processor. The cognitive WHIP predicts a degree of risk correlated with each particular user state sequence. An advantageous relationship between the user and one or more socially connected users is determined. An ameliorative action is triggered when a user enters a high-risk state based on the advantageous relationship to the one or more connected users and proximity of the user to one or more other users.
-
公开(公告)号：US10692013B2
公开(公告)日：2020-06-23
申请号：US15175620
申请日：2016-06-07
摘要： Solar irradiation may be predicted based on input terrestrial sky images comprising cloud images, the terrestrial sky images taken from a plurality of geographic locations by a plurality of devices; for example, wherein the terrestrial sky images are crowd sourced from the plurality of devices. A model may be generated that predicts solar irradiation in a geographic area based on the input terrestrial sky images and the geographic locations from where the terrestrial sky images were taken. A signal representing the solar irradiation predicted by the model is output.
-
公开(公告)号：US10402979B2
公开(公告)日：2019-09-03
申请号：US15593497
申请日：2017-05-12
发明人： Mani Abedini , Rajib Chakravorty , Rahil Garnavi , Munawar Hayat
IPC分类号： G06T7/10 , G06T7/13 , G06K9/46 , G06K9/52 , G06K9/62 , G06T7/00 , G06K9/68 , G06T7/143 , G06T7/90 , G06T7/11
摘要： A robust segmentation technique based on multi-layer classification technique to identify the lesion boundary is described. The inventors have discovered a technique based on training several classifiers such that to classify each pixel as lesion versus normal Each classifier is trained on a specific range of image resolutions. Then, for a new test image, the trained classifiers are applied on the image. Then by fusing the prediction results in pixel level a probability map is generated. In the next step, a thresholding method is applied to convert the probability map to a binary mask, which determines a mole border.
-
5.发明申请公开(公告)号：US20190156449A1
公开(公告)日：2019-05-23
申请号：US15819730
申请日：2017-11-21
发明人： Mani Abedini , Rajib Chakravorty , Rahil Garnavi , Zongyuan Ge
摘要： A computer-implemented screening method, system, and computer program product including detecting at least two disassembled components of an object spread across multiple sensor scan images of at least one container, storing a record of each disassembled component correlated with contextual information of each owner of each container corresponding to a sensor scan image, and flagging the owner of the container in the sensor scan image based on a joint assessment of the sensor scan image including a disassembled component that can be combined with another disassembled component in a different sensor scan image to assemble the object and the contextual information of each owner.
-
6.发明授权公开(公告)号：US10223788B2
公开(公告)日：2019-03-05
申请号：US15442151
申请日：2017-02-24
摘要： A dermoscopic lesion area is identified by: Obtaining a dermoscopic image and running a convolutional neural network image classifier on the dermoscopic image to obtain pixelwise lesion prediction scores. Segmenting the dermoscopic image into super-pixels, and computing for each super-pixel an average of the pixelwise prediction scores for pixels within that super-pixel. Computing a mean prediction score across the plurality of super-pixels. Assigning a confidence indicator of “1” to each super-pixel with a prediction score equal or greater than the mean prediction score, and a confidence indicator of “0” to each super-pixel with a prediction score less than the mean prediction score. Constructing a super-pixel graph G=(V,E,W) wherein w ij = exp ( - x i - x j 2 σ ) and di=Σi=1Nwij; computing a confidence score function F according to {circumflex over (F)}=arg min(FTLF+μ∥F−Y∥2); and integrating the confidence score function F with the pixelwise prediction scores to produce a final segmentation of the dermoscopic image into lesion and background areas.
-
公开(公告)号：US10176574B2
公开(公告)日：2019-01-08
申请号：US15859590
申请日：2017-12-31
摘要： A structure-preserving composite model for skin lesion segmentation includes partitioning a dermoscopic image into superpixels at a first scale. Each superpixel is a vertex on a graph defined by color coordinates and spatial coordinates, and represents a number of pixels of the dermoscopic image according to the first scale. Further, constructing a plurality of k background templates by k-means clustering selected ones of the superpixels in space and color. Additionally, generating sparse representations of the plurality of superpixels based on the plurality of background templates. Also, calculating a reconstruction error for each superpixel by comparison of its sparse representation to its original color coordinates and spatial coordinates. Furthermore, outputting a confidence map that identifies each pixel of the dermoscopic image as belonging or not belonging to a skin lesion, based on the reconstruction errors of the representative superpixels.
-
公开(公告)号：US10109110B2
公开(公告)日：2018-10-23
申请号：US14753041
申请日：2015-06-29
摘要： An augmented reality display system used to diminish (for example, obscure, obfuscate, hide, make less distracting, block out, “white wash” and/or make less discernible) certain portions of a base image (for example, a user's view of a part of the real world as seen through eyeglasses). Some examples of visual subject matter that can be diminished include: (i) driver distraction phenomena; (ii) advertising; and/or (iii) subject matter the user is not authorized to view.
-
9.发明授权公开(公告)号：US09962087B2
公开(公告)日：2018-05-08
申请号：US14986541
申请日：2015-12-31
CPC分类号： A61B5/0044 , A61B5/055 , G06T7/0012 , G06T7/0016 , G06T7/136 , G06T7/20 , G06T11/008 , G06T2207/10076 , G06T2207/10081 , G06T2207/10088 , G06T2207/10104 , G06T2207/30048
摘要： A method for automatically identifying and localizing anatomical regions of a left ventricle of a heart using a segment model, the method including receiving a volumetric MR image series of one or more time-points in a heart cycle with associated myocardial boundaries, representing the heart, performing a long-axis partitioning on each image of the volumetric image series, performing a short-axis partitioning volumetric image series, generating a polar map, wherein each image of the volumetric image series is mapped to a location on the polar map, wherein the location is characterized using the long-axis partitioning and the short-axis partitioning, and generating a mapping from the polar map to a voxel in an associated image of the volumetric image series representing an anatomical location.
-
公开(公告)号：US20180122065A1
公开(公告)日：2018-05-03
申请号：US15336293
申请日：2016-10-27
CPC分类号： G06T7/0012 , G06K9/4642 , G06K9/6212 , G06K2209/05 , G06T7/73 , G06T2207/20081 , G06T2207/30096
摘要： A method for image analysis comprises receiving one or more images of a plurality of lesions captured from a body of a person, extracting one or more features of the plurality of lesions from the one or more images, analyzing the extracted one or more features, wherein the analyzing comprises determining a distance between at least two lesions with respect to the extracted one or more features, and determining whether any of the plurality of lesions is an outlier based on the analyzing.
-
-
-
-
-
-
-
-
-
搜索结果
100 条记录 (耗时 0.027 秒)
