公开(公告)号：US20230306723A1

公开(公告)日：2023-09-28

申请号：US18126318

申请日：2023-03-24

Applicant: Arizona Board of Regents on behalf of Arizona State University

Inventor： DongAo Ma ,  Jiaxuan Pang ,  Nahid Ul Islam ,  Mohammad Reza Hosseinzadeh Taher ,  Fatemeh Haghighi ,  Jianming Liang

IPC: G06T7/00 ,  G06V10/776 ,  G06V10/774 ,  G06V10/764 ,  G06N3/0895

CPC classification number: G06V10/774 ,  G06N3/0895 ,  G06T7/0012 ,  G06V10/764 ,  G06V10/776 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/30004 ,  G06V2201/03

Abstract: Described herein are systems, methods, and apparatuses for implementing self-supervised domain-adaptive pre-training via a transformer for use with medical image classification in the context of medical image analysis. An exemplary system includes means for receiving a first set of training data having non-medical photographic images; receiving a second set of training data with medical images; pre-training an AI model on the first set of training data with the non-medical photographic images; performing domain-adaptive pre-training of the AI model via self-supervised learning operations using the second set of training data having the medical images; generating a trained domain-adapted AI model by fine-tuning the AI model against the targeted medical diagnosis task using the second set of training data having the medical images; outputting the trained domain-adapted AI model; and executing the trained domain-adapted AI model to generate a predicted medical diagnosis from an input image not present within the training data.

公开(公告)号：US11762541B2

公开(公告)日：2023-09-19

申请号：US17394554

申请日：2021-08-05

Applicant: Panasonic Corporation

Inventor： Kazuki Kozuka ,  Kazutoyo Takata ,  Kenji Kondo ,  Hirohiko Kimura ,  Toyohiko Sakai

IPC: G06F3/04845 ,  G06F3/0488 ,  G06F16/58 ,  G16H50/70 ,  G06F3/0485 ,  G16H30/20 ,  G16H30/40

CPC classification number: G06F3/04845 ,  G06F3/0485 ,  G06F3/0488 ,  G06F16/5866 ,  G16H30/20 ,  G16H30/40 ,  G16H50/70 ,  G06F2203/04104 ,  G06F2203/04803 ,  G06F2203/04806 ,  G06V2201/03

Abstract: A method for controlling an information terminal causes a computer of the information terminal to receive, from a case retrieval system, a plurality of similar medical images having a feature quantity of a region of interest and a certain degree of similarity in accordance with the region of interest included in a target medical image, displays a display screen displaying the plurality of received similar medical images on a touch panel display, the display screen including a display region in which at least some of the plurality of received similar medical images are displayed, displays, if selection of a first similar medical image from among the at least some of the plurality of received similar medical images displayed in the display region is detected, the first similar medical image across the display region, and displays, if a swipe operation performed on the first similar medical image is detected, a second similar medical image, which has second highest similarity next to the first similar medical image among the plurality of similar medical images, in the display region such that a corresponding region of interest included in the second similar medical image is located at a certain position in the display region.

公开(公告)号：US20230290120A1

公开(公告)日：2023-09-14

申请号：US18198165

申请日：2023-05-16

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Yu ZHAO ,  Zhenyu LIN ,  Jianhua YAO

IPC: G06V10/764 ,  G06V10/44 ,  G06V10/26

CPC classification number: G06V10/764 ,  G06V10/44 ,  G06V10/26 ,  G06V2201/03

Abstract: Disclosed are an image classification method performed by a computer device. The method includes: acquiring an image feature of a pathological image; extracting, for each scale in multiple scales, a local feature corresponding to the scale from the image feature; splicing the local features respectively corresponding to the scales to obtain a spliced image feature; and classifying the spliced image feature to obtain a category to which the pathological image belongs. According to the method provided in the embodiments of this application, the local features corresponding to different scales contain different information, so that the finally obtained spliced image feature contains feature information corresponding to different scales, and the feature information of the spliced image feature is enriched. The category to which the pathological image belongs is determined based on the spliced image feature, so that the accuracy of the category is ensured.

公开(公告)号：US11751834B2

公开(公告)日：2023-09-12

申请号：US17715196

申请日：2022-04-07

Applicant: Rakuten Group, Inc.

Inventor： Joji Kimizuka

IPC: A61B6/00 ,  G06T11/00 ,  G06V40/10 ,  G06V10/44 ,  A61B6/03

CPC classification number: A61B6/5217 ,  G06T11/008 ,  G06V10/443 ,  G06V40/10 ,  A61B6/032 ,  G06V2201/03

Abstract: A measurement image acquisition unit 72 acquires a measurement image indicating a measurement value of a predetermined physical quantity for a measurement target including a plurality of types of body tissues. A body tissue image generation unit 74 generates a body tissue image associated with each of the plurality of types of body tissues by executing, for the each of the plurality of types of body tissues, a filtering process corresponding to the each of the plurality of types of body tissues with respect to the measurement image. A masked body tissue image generation unit 78 generates a masked body tissue image associated with a specific type of body tissue by executing, with respect to the body tissue image associated with the specific type of body tissue, a masking process which is based on the body tissue image associated with a different type of body tissue.

公开(公告)号：US20230281971A1

公开(公告)日：2023-09-07

申请号：US18178233

申请日：2023-03-03

Applicant: Lunit Inc.

Inventor： Dong Geun YOO ,  Sang Hoon SONG ,  Chan Young OCK ,  Won Kyung JUNG ,  Soo Ick CHO ,  Kyung Hyun PAENG

IPC: G06V10/774 ,  G06V20/69 ,  G06T7/00

CPC classification number: G06V10/774 ,  G06V20/698 ,  G06T7/0012 ,  G06V2201/03 ,  G06T2207/30024 ,  G06T2207/20081

Abstract: Provided is a computing device including at least one memory, and at least one processor configured to obtain a first pathological slide image one of a first object and biological information of the first object, generate training data by using at least one first patch included in the first pathological slide image, and the biological information, train a first machine learning model based on the training data, and analyze a second pathological slide image of a second object by using the trained first machine learning model.

公开(公告)号：US11748677B2

公开(公告)日：2023-09-05

申请号：US17393726

申请日：2021-08-04

Applicant: Enlitic, Inc.

Inventor： Jordan Prosky ,  Li Yao ,  Eric C. Poblenz ,  Kevin Lyman ,  Ben Covington ,  Anthony Upton

IPC: G06T5/50 ,  G06F9/54 ,  G06N5/04 ,  G06Q10/0631 ,  G16H10/60 ,  G16H30/40 ,  G16H15/00 ,  G06T5/00 ,  G06T7/00 ,  G06T11/00 ,  G16H30/20 ,  G06N20/00 ,  G06T7/187 ,  G06T7/11 ,  G06F3/0482 ,  G06T3/40 ,  A61B5/00 ,  G16H50/20 ,  G06F21/62 ,  G06Q20/14 ,  G16H40/20 ,  G06F3/0484 ,  G16H10/20 ,  G06N5/045 ,  G06T7/10 ,  G06T11/20 ,  G06F16/245 ,  G06T7/44 ,  G06N20/20 ,  H04L67/12 ,  H04L67/01 ,  G06V10/82 ,  G06F18/40 ,  G06F18/214 ,  G06F18/21 ,  G06F18/2115 ,  G06F18/2415 ,  G06V10/25 ,  G06V30/19 ,  G06V10/764 ,  G06V40/16 ,  G06V10/22 ,  G16H50/70 ,  G06T7/70 ,  G16H50/30 ,  A61B5/055 ,  A61B6/03 ,  A61B8/00 ,  A61B6/00 ,  G06Q50/22 ,  G06F40/295 ,  G06F18/24 ,  G06F18/2111 ,  G06V30/194

CPC classification number: G06Q10/06315 ,  A61B5/7264 ,  G06F3/0482 ,  G06F3/0484 ,  G06F9/542 ,  G06F16/245 ,  G06F18/214 ,  G06F18/217 ,  G06F18/2115 ,  G06F18/2415 ,  G06F18/41 ,  G06F21/6254 ,  G06N5/04 ,  G06N5/045 ,  G06N20/00 ,  G06N20/20 ,  G06Q20/14 ,  G06T3/40 ,  G06T5/002 ,  G06T5/008 ,  G06T5/50 ,  G06T7/0012 ,  G06T7/0014 ,  G06T7/10 ,  G06T7/11 ,  G06T7/187 ,  G06T7/44 ,  G06T7/97 ,  G06T11/001 ,  G06T11/006 ,  G06T11/206 ,  G06V10/225 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82 ,  G06V30/19173 ,  G06V40/171 ,  G16H10/20 ,  G16H10/60 ,  G16H15/00 ,  G16H30/20 ,  G16H30/40 ,  G16H40/20 ,  G16H50/20 ,  H04L67/01 ,  H04L67/12 ,  A61B5/055 ,  A61B6/032 ,  A61B6/5217 ,  A61B8/4416 ,  G06F18/2111 ,  G06F18/24 ,  G06F40/295 ,  G06Q50/22 ,  G06T7/70 ,  G06T2200/24 ,  G06T2207/10048 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10116 ,  G06T2207/10132 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06T2207/30008 ,  G06T2207/30016 ,  G06T2207/30061 ,  G06V30/194 ,  G06V2201/03 ,  G16H50/30 ,  G16H50/70

Abstract: A multi-model medical scan analysis system is operable to generate a generic model by performing a training step on image data of a plurality of medical scans and corresponding labeling data. A plurality of fine-tuned models are generated by performing a fine-tuning step on the generic model. Abnormality detection data is generated for a new medical scan by utilizing the generic model. A first one of the plurality of abnormality types that is detected in the new medical scan is determined based on a corresponding one of the plurality of probability values. Additional abnormality data is generated by performing a fine-tuned inference function on the image data of the new medical scan that utilizes one of the plurality of fine-tuned models that corresponds to the first one of the plurality of abnormality types. The additional abnormality data is transmitted for display.

公开(公告)号：US20230274534A1

公开(公告)日：2023-08-31

申请号：US18173330

申请日：2023-02-23

Applicant: Siemens Healthcare GmbH

Inventor： Andre AICHERT ,  Marvin TEICHMANN ,  Birgi TAMERSOY ,  Martin KRAUS ,  Arnaud Arindra ADIYOSO

IPC: G06V10/774 ,  G06T7/11 ,  G06T7/00 ,  G06V20/70 ,  G06V10/77 ,  G06V10/56 ,  G06V10/26 ,  G06V10/764

CPC classification number: G06V10/774 ,  G06T7/11 ,  G06T7/0012 ,  G06V20/70 ,  G06V10/7715 ,  G06V10/56 ,  G06V10/26 ,  G06V10/764 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/30096 ,  G06V2201/03

Abstract: Various disclosed examples pertain to digital pathology, more specifically to training of a segmentation algorithm for segmenting whole-slide images depicting tissue of multiple types. An initial annotation of a whole-slide image is refined to yield a refined annotation based on which parameters of the segmentation algorithm can be set. Techniques of patch-wise weak supervision can be employed for such refinement.

公开(公告)号：US11742082B2

公开(公告)日：2023-08-29

申请号：US17209360

申请日：2021-03-23

Applicant: Becton, Dickinson and Company

Inventor： Jonathan Karl Burkholz ,  Jeff O'Bryan

IPC: G16H40/67 ,  G16H20/17 ,  A61M5/14 ,  A61M5/315 ,  A61M5/42 ,  A61B5/15 ,  A61B5/154 ,  G16H10/60 ,  G16H10/40 ,  G16H40/63 ,  G16H30/20 ,  G16Z99/00 ,  G06V20/52 ,  H04N23/51 ,  A61M5/142 ,  A61M5/168 ,  A61M5/172 ,  A61B5/157 ,  A61B10/00 ,  A61B10/02 ,  H04N5/44 ,  H04N7/18 ,  A61B90/96 ,  A61B90/90 ,  A61M5/20 ,  A61M5/28 ,  A61M5/145 ,  A61M5/158 ,  G16H30/40 ,  G16H10/65 ,  G06Q50/22

CPC classification number: G16H40/67 ,  A61B5/15003 ,  A61B5/154 ,  A61B5/157 ,  A61B5/150748 ,  A61B5/150786 ,  A61B5/150992 ,  A61B10/0096 ,  A61B10/02 ,  A61M5/14 ,  A61M5/142 ,  A61M5/16831 ,  A61M5/172 ,  A61M5/315 ,  A61M5/31525 ,  A61M5/427 ,  G06V20/52 ,  G16H10/40 ,  G16H10/60 ,  G16H20/17 ,  G16H30/20 ,  G16H40/63 ,  G16Z99/00 ,  H04N5/44 ,  H04N7/18 ,  H04N23/51 ,  A61B5/150732 ,  A61B5/150847 ,  A61B90/90 ,  A61B90/96 ,  A61M5/1452 ,  A61M5/20 ,  A61M5/28 ,  A61M2005/1588 ,  A61M2205/3306 ,  A61M2205/3389 ,  A61M2205/3561 ,  A61M2205/3569 ,  A61M2205/3576 ,  A61M2205/52 ,  A61M2205/583 ,  A61M2205/6009 ,  A61M2205/6054 ,  A61M2205/6063 ,  A61M2205/6072 ,  G06Q50/22 ,  G06V2201/03 ,  G16H10/65 ,  G16H30/40

Abstract: A system for confirmation of fluid delivery to a patient at the clinical point of use is provided. The system includes a wearable electronic device. The wearable electronic device has a housing; at least one imaging sensor associated with the housing; a data transmission interface; a data reporting accessory for providing data to the user; a microprocessor for managing the at least one imaging sensor, the data transmission interface, and the data reporting accessory; and a program for acquiring and processing images from the at least one imaging sensor. The system further includes a fluid delivery apparatus; and one or more identification tags attached to or integrally formed with the fluid delivery apparatus. The program processes an image captured by the at least one imaging sensor to identify the one or more identification tags and acquires fluid delivery apparatus information from the one or more identification tags.

公开(公告)号：US11742076B2

公开(公告)日：2023-08-29

申请号：US17960755

申请日：2022-10-05

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada

IPC: G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G16H30/40 ,  G06V10/77 ,  G06V10/82 ,  G06V10/774 ,  G06T7/00 ,  G06N20/00

CPC classification number: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G06N20/00 ,  G06T2207/10088 ,  G06T2207/10104 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06T2207/30104 ,  G06V2201/03

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating multi-modal data archetypes. In one aspect, a method comprises obtaining a plurality of training examples, wherein each training example corresponds to a respective patient and includes multi-modal data, having a plurality of feature dimensions, that characterizes the patient; jointly training an encoder neural network and a decoder neural network on the plurality of training examples; and generating a plurality of multi-modal data archetypes that each correspond to a respective dimension of a latent space, comprising, for each multi-modal data archetype: processing a predefined embedding that represents the corresponding dimension of the latent space using the decoder neural network to generate multi-modal data, having the plurality of feature dimensions, that defines the multi-modal data archetype.

公开(公告)号：US11734820B2

公开(公告)日：2023-08-22

申请号：US17543654

申请日：2021-12-06

Applicant: FUJIFILM Corporation

Inventor： Masaaki Oosake

IPC: G06T7/00 ,  G06T7/70 ,  G06F18/21 ,  G06V10/25 ,  G06V10/764 ,  G06V10/776 ,  G06V10/80 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06T7/0012 ,  G06F18/217 ,  G06T7/70 ,  G06V10/25 ,  G06V10/454 ,  G06V10/764 ,  G06V10/776 ,  G06V10/80 ,  G06V10/82 ,  G06T2207/20084 ,  G06T2207/30096 ,  G06V2201/03

Abstract: A medical image processing device having a processor configured to: acquire a medical image including an image of a subject; perform a first recognition of the medical image using a first recognizer; determine a confidence level for a recognition result of a first recognition by the first recognition; and perform a second recognition of the medical image using a second recognizer according to the confidence level for the recognition result of the first recognition, the second recognition having higher recognition accuracy than the first recognition.