专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2022256458A1 WHOLE SLIDE IMAGE SEARCH 审中-公开
公开(公告)号：WO2022256458A1
公开(公告)日：2022-12-08
申请号：PCT/US2022/031845
申请日：2022-06-01
申请人： GENENTECH, INC. , HOFFMANN-LA ROCHE INC. , ROCHE MOLECULAR SYSTEMS, INC. , ROCHE DIAGNOSTICS GMBH , F. HOFFMANN-LA ROCHE AG
发明人： BEN-SHAUL, Ido , CANAMERO, Marta , ETZ HADAR, Ofir , GILDENBLAT, Jacob , HU, Fang-Yao , KLAIMAN, Eldad
IPC分类号： G06F16/532 , G06F16/51 , G06F16/56 , G06T7/00 , G06V10/44 , G06V20/69 , G16H30/20 , G16H30/40 , G16H50/70
摘要： In one embodiment, a method includes indexing a whole slide image dataset to generate one or more dataset embeddings corresponding to one or more respective regions of one or more whole slide images. Each dataset embedding includes a feature vector mapping the respective region to a feature embedding space. The method includes accessing a query image and generating an embedding for the query image that includes a feature vector mapping the query image to the feature embedding space. The method includes identifying result tiles by comparing the embedding for the query image to one or more of the dataset embeddings. The comparison is based on a distance between the embedding for the query image and the one or more of the dataset embeddings in the feature embedding space. The method includes generating a user interface including a display of the result tiles

2. 发明公开

EP4348452A1 WHOLE SLIDE IMAGE SEARCH 审中-实审
公开(公告)号：EP4348452A1
公开(公告)日：2024-04-10
申请号：EP22740578.4
申请日：2022-06-01
申请人： Genentech, Inc. , Roche Diagnostics GmbH , F. Hoffmann-La Roche AG
发明人： BEN-SHAUL, Ido , CANAMERO, Marta , ETZ HADAR, Ofir , GILDENBLAT, Jacob , HU, Fang-Yao , KLAIMAN, Eldad
IPC分类号： G06F16/532 , G06F16/51 , G06F16/56 , G06T7/00 , G06V10/44 , G06V20/69 , G16H30/20 , G16H30/40 , G16H50/70

3. 发明申请

WO2022094629A1 ATTENTION-BASED MULTIPLE INSTANCE LEARNING 审中-公开
公开(公告)号：WO2022094629A1
公开(公告)日：2022-05-05
申请号：PCT/US2021/072166
申请日：2021-11-01
申请人： GENENTECH, INC. , F. HOFFMANN-LA ROCHE AG , HOFFMAN-LA ROCHE INC. , VENTANA MEDICAL SYSTEMS, INC. , NIE, Yao
发明人： LI, Xiao , NGUYEN, Trung Kien , GAIRE, Fabien , KLAIMAN, Eldad , BEN-SHAUL, Ido , GILDENBLAT, Jacob , HADAR, Ofir Etz
IPC分类号： G06V10/82 , G06V20/69 , G06T7/00
摘要： Systems and methods relate to predicting disease progression by processing digital pathology images using neural networks. A digital pathology image that depicts a specimen stained with one or more stains is accessed. The specimen may have been collected from a subject. A set of patches are defined for the digital pathology image. Each patch of the set of patches depicts a portion of the digital pathology image. For each patch of the set of patches and using an attention-score neural network, an attention score is generated. The attention-score neural network may have been trained using a loss function that penalized attention-score variability across patches in training digital pathology images labeled to indicate no or low subsequent disease progression. Using a result-prediction neural network and the attention scores, a result is generated that represents a prediction of whether or an extent to which a disease of the subject will progress.

4. 发明公开

EP4238069A1 ATTENTION-BASED MULTIPLE INSTANCE LEARNING 审中-实审
公开(公告)号：EP4238069A1
公开(公告)日：2023-09-06
申请号：EP21815084.5
申请日：2021-11-01
申请人： Genentech, Inc. , F. Hoffmann-La Roche AG , Ventana Medical Systems, Inc.
发明人： NIE, Yao , LI, Xiao , NGUYEN, Trung Kien , GAIRE, Fabien , KLAIMAN, Eldad , BEN-SHAUL, Ido , GILDENBLAT, Jacob , HADAR, Ofir Etz
IPC分类号： G06V10/82 , G06V20/69 , G06T7/00

5. 发明申请

WO2019057944A1 ARTIFACTS REMOVAL FROM TISSUE IMAGES 审中-公开
公开(公告)号：WO2019057944A1
公开(公告)日：2019-03-28
申请号：PCT/EP2018/075708
申请日：2018-09-21
申请人： F. HOFFMANN-LA ROCHE AG , HOFFMANN-LA ROCHE INC.
发明人： KLAIMAN, Eldad
IPC分类号： G06T5/00
摘要： The invention relates to a digital pathology method of generating program logic configured for removing artifacts from digital tissue images. The method comprises generating, for each of a plurality of original images, a first artificially degraded image by applying a first image-artifact-generation logic on each of the original images; and generating the program logic by training an untrained version of a first machine-learning logic that encodes a first artifacts-removal logic on the original images and their respectively generated first degraded images; and returning the trained first machine-learning logic as the program logic or as a component thereof. The first image-artifact-generation logic is A) an image-acquisition-system-specific image-artifact-generation logic or B) a tissue-staining-artifact-generation logic.

6. 发明申请

WO2017198790A1 TUMOR PROXIMITY MEASURE 审中-公开
标题翻译：肿瘤接近度测量
公开(公告)号：WO2017198790A1
公开(公告)日：2017-11-23
申请号：PCT/EP2017/062037
申请日：2017-05-18
申请人： F. HOFFMANN-LA ROCHE AG , HOFFMANN-LA ROCHE INC.
发明人： GAIRE, Fabien , KLAIMAN, Eldad , KORSKI, Konstanty
IPC分类号： G06T7/00
摘要： The invention relates to an image analysis system (100) for tumor classification. The system is configured for: receiving (202) at least one digital image (118) of a tissue sample; analyzing (204) the at least one received image for identifying immune cells and tumor cells in the at least one received image; for each of the identified tumor cells, determining (206) the distance of said tumor cell to the nearest immune cell; computing (208) a proximity measure as a function of the determined distances; in dependence on the proximity measure, classifying (210) the identified tumor cells into tumor cells of an inflammatory tumor or as tumor cells of a non-inflammatory tumor; and storing (212) the classification result on a storage medium and/or displaying (214) the classification result on a display device (102).
摘要翻译：本发明涉及用于肿瘤分类的图像分析系统（100）。该系统被配置用于：接收（202）组织样本的至少一个数字图像（118）分析（204）所述至少一个接收的图像以用于识别所述至少一个接收的图像中的免疫细胞和肿瘤细胞; 对于每个鉴定的肿瘤细胞，确定（206）所述肿瘤细胞与最近的免疫细胞的距离; 作为所确定的距离的函数来计算（208）接近度量度; 根据所述接近度量度，将所识别的肿瘤细胞分类（210）到炎性肿瘤的肿瘤细胞中或作为非炎性肿瘤的肿瘤细胞; 和将分类结果存储（212）在存储介质上和/或在显示设备（102）上显示（214）分类结果。

7. 发明申请

WO2020193708A1 MACHINE LEARNING USING DISTANCE-BASED SIMILARITY LABELS 审中-公开
公开(公告)号：WO2020193708A1
公开(公告)日：2020-10-01
申请号：PCT/EP2020/058570
申请日：2020-03-26
申请人： F. HOFFMANN-LA ROCHE AG , HOFFMANN-LA ROCHE INC.
发明人： KLAIMAN, Eldad , GILDENBLAT, Jacob
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62 , G06N3/04 , G06N3/08 , G06T7/00 , G16H30/40
摘要： The invention relates to a computer-implemented self-supervised learning method for digital pathology. The method comprises: Receiving (102) a plurality of digital images each depicting a tissue sample; Splitting (104) each of the received images into a plurality of tiles; automatically generating (106) tile pairs (312, 313, 314, 315, 422), each tile pair having assigned a label (403) being indicative of the degree of similarity of two tissue patterns depicted in the two tiles of the pair, wherein the degree of similarity is computed as a function of the spatial proximity (d1, d2, d3, d4) of the two tiles in the pair, wherein the distance positively correlates with dis- similarity; and training a machine learning module - MLM - (400, 402, 403, 600) using the labeled tile pairs as training data to generate a trained MLM, the trained MLM being adapted for performing an image analysis of digital histopathology im- ages.

8. 发明申请

WO2019154987A1 TRANSFORMATION OF DIGITAL PATHOLOGY IMAGES 审中-公开
公开(公告)号：WO2019154987A1
公开(公告)日：2019-08-15
申请号：PCT/EP2019/053137
申请日：2019-02-08
申请人： F. HOFFMANN-LA ROCHE AG , HOFFMANN-LA ROCHE INC.
发明人： KLAIMAN, Eldad
IPC分类号： G06T7/00 , G06K9/20
CPC分类号： G06T7/0012 , G06K9/2054 , G06K2209/051 , G06T2207/20081 , G06T2207/20084 , G06T2207/30024
摘要： The invention relates to a method (100) of identifying a biomarker in a tissue sample (324). The method comprises receiving (102) an acquired image (202, 204, 316) depicting a tissue sample, the pixel intensity values of the acquired image correlating with an autofluorescence signal or of an X-ray induced signal or a signal of a non-biomarker specific stain or a signal of a first biomarker specific stain adapted to selectively stain a first biomarker. The acquired image is input (106) into a trained machine learning logic - MLL (308) which automatically transforms (108) the acquired image into an output image (206, 208, 318) highlighting tissue regions predicted to comprise a second biomarker.

9. 发明申请

WO2018189370A1 TARGET MOLECULE DENSITY DETERMINATION IN A FLUORESCENCE IMAGE 审中-公开
公开(公告)号：WO2018189370A1
公开(公告)日：2018-10-18
申请号：PCT/EP2018/059528
申请日：2018-04-13
申请人： F. HOFFMANN-LA ROCHE AG , HOFFMANN-LA ROCHE INC.
发明人： KLAIMAN, Eldad
IPC分类号： G01N21/64
摘要： The invention relates to an image analysis system (100) configured for determining the density of target molecules in a tissue sample, the determination comprising: - receiving (202) a digital image (130) of a slide (150), the slide comprising the tissue sample (152), a target dot (TD) and a fluoro dot (FD), the fluoro dot comprising a known density (1 14) of fluorescence-inducing molecules (408), the target dot comprising a known density (1 16) of target molecules (402), the tissue sample and the target dot having been stained in the same staining procedure with the same type of fluorescence-inducing molecules as contained in the fluoro dot, the digital image comprising intensity values of the tissue sample, intensity values (122) of the target dot and intensity values (120) of the fluoro dot, the fluorescence-inducing molecules being adapted to directly or indirectly bind to the target molecules during the staining procedure; - receiving (204): - pixel intensities (120) of the fluoro dot depicted in the image; - pixel intensities (122) of the target dot depicted in the image; - pixel intensities (1 18) of an area (154) of the tissue sample depicted in the image; - fluorescence-inducing molecule density information (1 14) indicative of the known density of the fluorescence-inducing molecules in the fluoro dot; - target molecule density information (1 16) indicative of the known density of the target molecules in the target dot; - computing (206) the density of target molecules in the area (154) of the tissue sample as a function of the received pixel intensities and the received molecule density information.

10. 发明申请

WO2021099584A1 MULTIPLE INSTANCE LEARNER FOR TISSUE IMAGE CLASSIFICATION 审中-公开
公开(公告)号：WO2021099584A1
公开(公告)日：2021-05-27
申请号：PCT/EP2020/082917
申请日：2020-11-20
申请人： F. HOFFMANN-LA ROCHE AG , HOFFMANN-LA ROCHE INC.
发明人： KLAIMAN, Eldad , GILDENBLAT, Jacob , SHAUL, Ido Ben
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62 , G16H50/70 , G16H30/20 , G16H30/40
摘要： The invention relates to a method for classifying tissue images. The method comprises: receiving (102) a plurality of digital tissue images; splitting (104) each received image into a set of image tiles; for each of the tiles, extracting (106) a feature vector from the tile; providing (108) a Multiple-Instance-Learning (MIL) program configured to use a model for classifying any input image as a member of one out of at least two different classes based on feature vectors extracted from all tiles of said image; for each of the tiles, computing (110) a certainty value indicating the certainty of the model regarding the contribution of the tile's feature vector on the classification of the image; for each of the images, using (114), by the MIL-program, a certainty-value- based pooling function for aggregating the feature vectors of the image or predictive values computed from the feature vectors of the image into an aggregated predictive value as a function of the certainty values of the tiles of the image; and classifying (116) each of the images as a member of one of the classes based on the aggregated predictive value.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式