公开(公告)号：US08929629B1

公开(公告)日：2015-01-06

申请号：US14262078

申请日：2014-04-25

Applicant: Given Imaging Ltd.

Inventor： Stas Rozenfeld

IPC: G06K9/00 ,  G06T7/00 ,  A61B5/00 ,  G06K9/62

CPC classification number: G06T7/0012 ,  A61B5/07 ,  A61B5/7275 ,  G06K9/6292 ,  G06K2209/05 ,  G06T2207/10068 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30092

Abstract: A system and method for ulcer detection which may generate a vector of grades including grades indicative of a probability that the image includes an ulcer, for example an ulcer of specific type. For each grade, generating may include finding ulcer candidates within the image, and for each ulcer candidate, building a property vector describing properties of the ulcer candidate and employing a trained classifier to generate the grade from the property vector. The grades may be combined to obtain an indication or score of the probability that the image includes an ulcer.

Abstract translation: 一种用于溃疡检测的系统和方法，其可以产生等级的矢量，包括指示图像包括溃疡（例如特定类型的溃疡）的概率的等级。 对于每个等级，生成可以包括在图像内发现溃疡候选物，并且对于每个溃疡候选物，构建描述溃疡候选物的性质的性质向量，并且使用经过训练的分类器从属性向量生成等级。 可以组合等级以获得图像包括溃疡的概率的指示或得分。

公开(公告)号：US20230401700A1

公开(公告)日：2023-12-14

申请号：US18035417

申请日：2021-11-14

Applicant: Given Imaging LTD.

Inventor： Eyal Dekel ,  Almog Elharar ,  Stas Rozenfeld

IPC: G06T7/00 ,  G16H50/20

CPC classification number: G06T7/0012 ,  G16H50/20 ,  G06T2207/10068 ,  G06T2207/30028

Abstract: A method for detecting indicators of a disease characterized by a presence of villous atrophy in images of a gastrointestinal tract (GIT), includes accessing a consecutive set of images of a portion of the GIT comprising a small bowel. Each image is associated with one or more classification scores, and each classification score is indicative of the associated image including a respective indicator of a disease characterized by the presence of villous atrophy. The method further includes selecting a subset of images from the consecutive set of images based on the one or more classification scores of each image of the consecutive set of images, identifying a segment of images which includes all of the images that show a proximal portion of the small bowel, selecting a plurality of images from the identified segment of images that represent the proximal portion of the small bowel, and displaying the selected images.

公开(公告)号：US11445896B2

公开(公告)日：2022-09-20

申请号：US16073125

申请日：2017-01-24

Applicant: Given Imaging Ltd.

Inventor： Ron Nadiv ,  Ori Hay ,  Moran Horesh ,  Dori Peleg ,  Stas Rozenfeld

IPC: A61B1/045 ,  A61B1/00 ,  A61B1/04 ,  G06T7/246 ,  A61B5/01 ,  A61B5/03 ,  A61B5/07 ,  A61B5/145 ,  A61B5/00 ,  G06T7/00 ,  H04N5/343 ,  H04N5/345 ,  H04N5/347 ,  H04N5/369 ,  G06T7/73

Abstract: Methods for capturing and transmitting images by an in-vivo device comprise operating a pixel array in a superpixel readout mode to capture probe image, for example, according to a time interval. Concurrently to capturing of each probe image, the probe image is evaluated alone or in conjunction with other probe image(s), and if it is determined that no event of interest is detected by the last probe image, or by the last few probe images, the pixel array is operated in the superpixel readout mode and a subsequent probe image is captured. However, if it is determined that the last probe image, or the last few probe images, detected an event of interest, the pixel array is operated in a single pixel readout mode and a single normal image, or a series of normal image, is captured and transmitted, for example, to an external receiver.

公开(公告)号：US09767559B1

公开(公告)日：2017-09-19

申请号：US14670487

申请日：2015-03-27

Applicant: GIVEN IMAGING LTD.

Inventor： Stas Rozenfeld

IPC: G06T7/00 ,  A61B6/00

CPC classification number: G06T7/0016 ,  A61B6/12 ,  A61B6/4057 ,  A61B6/4208 ,  A61B6/481 ,  A61B6/52 ,  G06K2209/057 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/10121 ,  G06T2207/10124 ,  G06T2207/30004

Abstract: A system and method for reconstructing locations of sensors in radiopaque images may estimate sensor locations in two groups of good radiographic images and use them to estimate candidate sensor locations in a group of bad radiographic images B1, . . . , Bn in which many sensors are indiscernible. A first iterative process pervading from the first image B1 to the last image Bn may determine a first set of candidate sensor locations, and a second iterative process pervading from the last image Bn to the first image B1 may determine a second set of candidate sensor location for each image. Location of a sensor in each image Bi may be estimated based on the pertinent first and second candidate sensor locations related, or determined for, the particular sensor in the particular image. Sensor locations still missing in the series of images are, then, estimated using the already estimated sensor locations.