公开(公告)号：US20240265693A1

公开(公告)日：2024-08-08

申请号：US18565413

申请日：2022-02-07

Applicant: Hitachi Astemo, Ltd.

Inventor： Kota IRIE ,  Hirotomo SAI ,  Takakiyo YASUKAWA

IPC: G06V10/70 ,  G06V10/94 ,  G06V20/56 ,  G06V20/58 ,  H04N17/00 ,  H04N23/90

CPC classification number: G06V10/87 ,  G06V10/94 ,  G06V20/58 ,  H04N17/002 ,  G06V20/588 ,  G06V2201/03 ,  H04N23/90

Abstract: Provided are an image processing apparatus and an image processing system capable of performing control in a state where redundancy is secured even when an imaging device itself has failed or is malfunctioning. The image processing apparatus 3 recognizes a recognition target based on image data obtained by imaging an outside world using a first imaging device 2a and a second imaging device 2b installed to be spaced apart from the first imaging device 2a in a vertical direction from an interior of a vehicle via a window glass 6, and includes: a first image processing unit 3a that recognizes a first recognition target based on image data of the first imaging device 2a; and a second image processing unit 3b that recognizes a second recognition target different from the first recognition target based on image data of the first imaging device 2a and the second imaging device 2b. When a predetermined condition is satisfied, the second image processing unit 3b recognizes the first recognition target.

公开(公告)号：US20240265645A1

公开(公告)日：2024-08-08

申请号：US18433236

申请日：2024-02-05

Applicant: Rayhan Papar

Inventor： Rayhan Papar

IPC: G06T19/00 ,  G06T5/50 ,  G06V20/70 ,  G16H30/20 ,  G16H30/40

CPC classification number: G06T19/006 ,  G06K15/1276 ,  G06T5/50 ,  G06V20/695 ,  G06V20/70 ,  G16H30/20 ,  G16H30/40 ,  G06T2207/20221 ,  G06T2207/30096 ,  G06T2207/30101 ,  G06V2201/03 ,  G06V2201/07

Abstract: An augmented reality system and method, comprising: a memory configured to store 3D medical scans comprising an image of a tumor and an angiogram; an output port configured to present a signal for presentation of an augmented reality display to a user; at least one camera, configured to capture images of a physiological object from a perspective; at least one processor, configured to: implement a first neural network trained to automatically segment the tumor; implement a second neural network to segment vasculature in proximity to the tumor; implement a third neural network to recognize a physiological object in the captured images; and generate an augmented reality display of the physiological object, tumor and vasculature based on the captured images, the segmented tumor and the segmented vasculature, compensated for changes in the perspective.

公开(公告)号：US12057234B2

公开(公告)日：2024-08-06

申请号：US18385405

申请日：2023-10-31

Applicant: CANCER HOSPITAL, CHINESE ACADEMY OF MEDICAL SCIENCES

Inventor： Qing Zhao ,  Xu Guan ,  Enrui Liu ,  Ran Wei ,  Xiaoxiao Song

IPC: G16H50/70 ,  G06T11/20 ,  G06V10/22 ,  G06V10/25 ,  G06V10/44 ,  G06V10/54 ,  G06V10/766 ,  G06V10/774 ,  G06V20/70 ,  G16H10/60 ,  G16H30/20

CPC classification number: G16H50/70 ,  G06T11/206 ,  G06V10/225 ,  G06V10/25 ,  G06V10/44 ,  G06V10/54 ,  G06V10/766 ,  G06V10/774 ,  G06V20/70 ,  G16H10/60 ,  G16H30/20 ,  G06V2201/03

Abstract: A system for predicting therapy resistance and its molecular mechanisms in rectal cancer before treatment is provided. The system includes a feature extraction device, a collection device, a signature construction device and a prediction device. The system can predict responses to neoadjuvant therapy in patients before treatment, analyze patients who are resistant to rectal cancer therapy and their underlying molecular mechanism, thereby enabling personalized therapy for patients who are resistant to rectal cancer therapy. The system has important clinical significance in improving the overall survival of rectal cancer patients.

公开(公告)号：US20240249541A1

公开(公告)日：2024-07-25

申请号：US18566374

申请日：2021-06-04

Applicant: Toru NAGASAKA

Inventor： Toru NAGASAKA

IPC: G06V20/69 ,  G06T7/70 ,  G06V10/82

CPC classification number: G06V20/698 ,  G06T7/70 ,  G06V10/82 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06V2201/03

Abstract: An image analysis method includes a calculation unit that calculates a colocalization value indicating colocalization between two target cell objects among a plurality of target cell objects and an output unit that outputs output data acquired by using the colocalization value to an external, wherein the calculation unit calculates the colocalization value by using a first calculation that includes multiplying a first matching rate specified for a first target cell object and a second matching rate specified for a second target cell object and a second calculation that includes dividing a calculated value acquired by the first calculation by first distance squared, the first distance being a distance between the first target cell object and the second target cell object.

公开(公告)号：US12042320B2

公开(公告)日：2024-07-23

申请号：US17264048

申请日：2019-07-30

Applicant: MEMORIAL SLOAN KETTERING CANCER CENTER

Inventor： Joseph O. Deasy ,  Harini Veeraraghavan ,  Yu-Chi Hu ,  Gig Mageras ,  Jue Jiang

IPC: G06K9/00 ,  A61B6/00 ,  G06T3/4053 ,  G06T5/50 ,  G06T7/00 ,  G06T7/11 ,  G06T7/187 ,  A61B6/03

CPC classification number: A61B6/5211 ,  G06T3/4053 ,  G06T5/50 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/187 ,  A61B6/03 ,  A61B6/5229 ,  G06T2207/10072 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V2201/03

Abstract: Systems and methods for multi-modal, multi-resolution deep learning neural networks for segmentation, outcomes prediction and longitudinal response monitoring to immunotherapy and radiotherapy are detailed herein. A structure-specific Generational Adversarial Network (SSGAN) is used to synthesize realistic and structure-preserving images not produced using state-of-the art GANs and simultaneously incorporate constraints to produce synthetic images. A deeply supervised, Multi-modality, Multi-Resolution Residual Networks (DeepMMRRN) for tumor and organs-at-risk (OAR) segmentation may be used for tumor and OAR segmentation. The DeepMMRRN may combine multiple modalities for tumor and OAR segmentation. Accurate segmentation is may be realized by maximizing network capacity by simultaneously using features at multiple scales and resolutions and feature selection through deep supervision. DeepMMRRN Radiomics may be used for predicting and longitudinal monitoring response to immunotherapy. Auto-segmentations may be combined with radiomics analysis for predicting response prior to treatment initiation. Quantification of entire tumor burden may be used for automatic response assessment.

公开(公告)号：US20240233347A1

公开(公告)日：2024-07-11

申请号：US18610209

申请日：2024-03-19

Applicant: Ventana Medical Systems, Inc.

Inventor： Qinle Ba ,  Jim F. Martin ,  Karel J. Zuiderveld ,  Uwe Horchner

IPC: G06V10/776 ,  G06T7/00 ,  G06V10/77 ,  G06V10/774 ,  G06V20/69 ,  G06V20/70

CPC classification number: G06V10/776 ,  G06T7/0012 ,  G06V10/7715 ,  G06V10/774 ,  G06V20/695 ,  G06V20/70 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06V20/698 ,  G06V2201/03

Abstract: Method and systems for of using a machine-learning model to detect predicted artifacts at a target image resolution are provided. A machine-learning model trained to detect artifact pixels in images at a target image resolution is accessed. An image depicting at least part of the biological sample at an initial image resolution can be converted at the target image resolution. The machine-learning model is applied to the converted image to identify one or more artifact pixels from the converted image. Method and systems for training the machine-learning model to detect predicted artifacts at the target image resolution are also provided.

公开(公告)号：US12026875B2

公开(公告)日：2024-07-02

申请号：US17431334

申请日：2020-03-26

Applicant: HOFFMANN-LA ROCHE INC.

Inventor： Eldad Klaiman ,  Jacob Gildenblat

IPC: G06T7/00 ,  G06N3/045 ,  G06V10/44 ,  G06V10/74 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V20/69 ,  G16H30/40

CPC classification number: G06T7/0012 ,  G06N3/045 ,  G06V10/454 ,  G06V10/761 ,  G06V10/764 ,  G06V10/7747 ,  G06V10/82 ,  G06V20/695 ,  G06V20/698 ,  G16H30/40 ,  G06T2207/30024 ,  G06V2201/03

Abstract: The method includes receiving a plurality of digital images each depicting a tissue sample; splitting each of the received images into a plurality of tiles; automatically generating tile pairs, each tile pair having assigned a label 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 of the two tiles in the pair, wherein the distance positively correlates with dissimilarity; and training a machine learning module—MLM—using the labeled tile pairs as training data to generate a trained MLM, the trained MLM being configured for performing an image analysis of digital histopathology images.

公开(公告)号：US20240203105A1

公开(公告)日：2024-06-20

申请号：US18539348

申请日：2023-12-14

Applicant: Leica Microsystems CMS GmbH

Inventor： Constantin KAPPEL

IPC: G06V10/776 ,  G06N3/0475 ,  G06N3/092 ,  G06V10/774 ,  G06V10/778 ,  G06V20/50

CPC classification number: G06V10/776 ,  G06N3/0475 ,  G06N3/092 ,  G06V10/774 ,  G06V10/7784 ,  G06V20/50 ,  G06V10/82 ,  G06V2201/03

Abstract: Examples relate to methods, systems, and computer systems for training a machine-learning model, for generating a training corpus, and for using a machine-learning model for use in a scientific or surgical imaging system, and to a scientific or surgical imaging system comprising such a system. A method for training a machine-learning model for use in a scientific or surgical imaging system comprises obtaining a plurality of images of a scientific or surgical imaging system, for use as training input images. The method comprises obtaining a plurality of training outputs that are based on the plurality of training input images and that are based on an image processing workflow of the scientific or surgical imaging system, the image processing workflow comprising a plurality of image processing steps. The method comprises training the machine-learning model using the plurality of training input images and the plurality of training outputs.

公开(公告)号：US20240203098A1

公开(公告)日：2024-06-20

申请号：US18084152

申请日：2022-12-19

Applicant: Mohamed bin Zayed University of Artificial Intelligence

Inventor： Maryam SULTANA ,  Muhammad Muzammal NASEER ,  Muhammad Haris KHAN ,  Salman KHAN ,  Fahad Shahbaz KHAN

IPC: G06V10/774 ,  G06V10/764 ,  G06V10/77 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V10/774 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/776 ,  G06V10/82 ,  G06V2201/03

Abstract: An apparatus and method for a machine learning engine for domain generalization which trains a vision transformer neural network using a training dataset including at least two domains for diagnosis of a medical condition. Image patches and class tokens are processed through a sequence of feature extraction transformer blocks to obtain a predicted class token. In parallel, intermediate class tokens are extracted as outputs of each of the feature extraction transformer blocks, where each transformer block is a sub-model. One sub-model is randomly sampled from the sub-models to obtain a sampled intermediate class token. The intermediate class token is used to make a sub-model prediction. The vision transformer neural network is optimized based on a difference between the predicted class token and the sub-model prediction. Inferencing is performed for a target medical image in a target domain that is different from the at least two domains.

公开(公告)号：US20240188799A1

公开(公告)日：2024-06-13

申请号：US18582650

申请日：2024-02-21

Applicant: FUJIFILM Corporation

Inventor： Yuya KIMURA ,  Yuma HORI ,  Tatsuya KOBAYASHI ,  Yuichi SAKAGUCHI ,  Kenichi HARADA ,  Takeru SUGIYAMA

IPC: A61B1/00 ,  G06T7/00 ,  G06V10/70 ,  G10L15/08 ,  G10L15/22

CPC classification number: A61B1/0004 ,  A61B1/000096 ,  G06T7/0012 ,  G06V10/70 ,  G10L15/08 ,  G10L15/22 ,  G06T2207/10068 ,  G06T2207/20081 ,  G06T2207/30096 ,  G06V2201/03 ,  G10L2015/088

Abstract: An embodiment according to the technique of the present disclosure is to provide an endoscope system, a medical information processing apparatus, a medical information processing method, a medical information processing program, and a recording medium capable of improving recognition accuracy of an audio input. The endoscope system according to an aspect of the present invention includes an audio input device; an image sensor that images a subject; and a processor, in which the processor acquires a plurality of medical images by causing the image sensor to image the subject in chronological order, accepts an input of an audio input trigger during capturing of the plurality of medical images, sets, in a case where the audio input trigger is input, an audio recognition dictionary according to the audio input trigger, and performs audio recognition on audio input to the audio input device after the setting, using the set audio recognition dictionary.