公开(公告)号：US11195052B2

公开(公告)日：2021-12-07

申请号：US16833451

申请日：2020-03-27

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06K9/00 ,  G06K9/62 ,  A61B1/00 ,  A61B1/273 ,  G06N3/08 ,  G06T7/00 ,  G16H50/20 ,  G16H30/40 ,  A61B1/31 ,  G06N3/04

Abstract: The present disclosure relates to computer-implemented systems and methods for training and using generative adversarial networks to detect abnormalities in images of a human organ. In one implementation, a method is provided for training a neural network system, the method may include applying a perception branch of an object detection network to frames of a first subset of a plurality of videos to produce a first plurality of detections of abnormalities. Further, the method may include using the first plurality of detections and frames from a second subset of the plurality of videos to train a generator network to generate a plurality of artificial representations of polyps, and training an adversarial branch of the discriminator network to differentiate between artificial representations of the abnormalities and true representations of abnormalities. Additionally, the method may include retraining the perception branch based on difference indicators between the artificial representations of abnormalities and true representations of abnormalities included in frames of the second subset of plurality of videos and a second plurality of detections.

公开(公告)号：US12158924B2

公开(公告)日：2024-12-03

申请号：US17251773

申请日：2019-06-11

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06F18/2413 ,  A61B1/00 ,  A61B1/273 ,  A61B1/31 ,  G06F18/21 ,  G06F18/214 ,  G06F18/40 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  G06T7/00 ,  G16H30/40 ,  G16H50/20

Abstract: The present disclosure relates to computer-implemented systems and methods for training and using generative adversarial networks. In one implementation, a system for training a generative adversarial network may include at least one processor that may provide a first plurality of images including representations of a feature-of-interest and indicators of locations of the feature-of-interest and use the first plurality and indicators to train an object detection network. Further, the processor(s) may provide a second plurality of images including representations of the feature-of-interest, and apply the trained object detection network to the second plurality to produce a plurality of detections of the feature-of-interest. Additionally, the processor(s) may provide manually set verifications of true positives and false positives with respect to the plurality of detections, use the verifications to train a generative adversarial network, and retrain the generative adversarial network using at least one further set of images, further detections, and further manually set verifications.

公开(公告)号：US11574403B2

公开(公告)日：2023-02-07

申请号：US17379902

申请日：2021-07-19

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06K9/62 ,  G06T7/00 ,  G06T7/70 ,  G16H30/20 ,  G06N3/08 ,  G06T11/00 ,  G06T11/60 ,  G06T11/20 ,  A61B1/00 ,  A61B5/00 ,  G06V10/25 ,  G06V10/20 ,  G06V20/40 ,  G06N3/04 ,  G06V10/82

Abstract: The present disclosure relates to computer-implemented systems and methods for detecting a feature-of-interest in a video. In one implementation, a computer-implemented system may include a discriminator network and a generative network. The discriminator network may include a perception branch and an adversarial branch, the perception branch being configured to output detections of the feature-of-interest in the video. The generative network may be configured to receive detections of the feature-of-interest from the perception branch of the discriminator network and generate artificial representations of the feature-of-interest based on the detections from the perception branch. Further, the adversarial branch may be configured to provide an output identifying differences between the false representations and true representations of the feature-of-interest, and the perception branch may be further configured to be trained by the output of the adversarial branch so that false representations are not detected by the perception branch as true representations.

公开(公告)号：US12089820B2

公开(公告)日：2024-09-17

申请号：US17251768

申请日：2019-06-11

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06K9/00 ,  A61B1/00 ,  A61B1/31 ,  A61B5/00 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06T7/00 ,  G06T7/70 ,  G06T11/00 ,  G06T11/20 ,  G06T11/60 ,  G06V10/20 ,  G06V10/25 ,  G06V10/82 ,  G06V20/40 ,  G16H30/20

CPC classification number: A61B1/31 ,  A61B1/000094 ,  A61B1/000095 ,  A61B1/000096 ,  A61B1/00055 ,  A61B5/7264 ,  A61B5/7267 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0012 ,  G06T7/70 ,  G06T11/001 ,  G06T11/203 ,  G06T11/60 ,  G06V10/25 ,  G06V10/255 ,  G06V10/82 ,  G06V20/40 ,  G06V20/49 ,  G16H30/20 ,  G06T2207/10016 ,  G06T2207/10068 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06T2207/30032 ,  G06T2207/30064 ,  G06T2207/30096 ,  G06V2201/03 ,  G06V2201/032

Abstract: The present disclosure relates to systems and methods for processing real-time video and detecting objects in the video. In one implementation, a system is provided that includes an input port for receiving real-time video obtained from a medical image device, a first bus for transferring the received real-time video, and at least one processor configured to receive the real-time video from the first bus, perform object detection by applying a trained neural network on frames of the received real-time video, and overlay a border indicating a location of at least one detected object in the frames. The system also includes a second bus for receiving the video with the overlaid border, an output port for outputting the video with the overlaid border from the second bus to an external display, and a third bus for directly transmitting the received real-time video to the output port.

公开(公告)号：US11100633B2

公开(公告)日：2021-08-24

申请号：US16008015

申请日：2018-06-13

Applicant: Cosmo Artificial Intelligence—AI Limited

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/70 ,  G16H30/20 ,  G06N3/08 ,  G06T11/00 ,  G06T11/60 ,  G06K9/32 ,  G06T11/20 ,  A61B1/00 ,  A61B5/00

Abstract: The present disclosure relates to systems and methods for processing real-time video and detecting objects in the video. In one implementation, a system is provided that includes an input port for receiving real-time video obtained from a medical image device, a first bus for transferring the received real-time video, and at least one processor configured to receive the real-time video from the first bus, perform object detection by applying a trained neural network on frames of the received real-time video, and overlay a border indicating a location of at least one detected object in the frames. The system also includes a second bus for receiving the video with the overlaid border, an output port for outputting the video with the overlaid border from the second bus to an external display, and a third bus for directly transmitting the received real-time video to the output port.

公开(公告)号：US12207798B2

公开(公告)日：2025-01-28

申请号：US18525800

申请日：2023-11-30

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06K9/62 ,  A61B1/00 ,  A61B1/31 ,  A61B5/00 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06T7/00 ,  G06T7/70 ,  G06T11/00 ,  G06T11/20 ,  G06T11/60 ,  G06V10/20 ,  G06V10/25 ,  G06V10/82 ,  G06V20/40 ,  G16H30/20

Abstract: The present disclosure relates to systems and methods for processing real-time video and detecting objects in the video. In one implementation, a system is provided that includes an input port for receiving real-time video obtained from a medical image device, a first bus for transferring the received real-time video, and at least one processor configured to receive the real-time video from the first bus, perform object detection by applying a trained neural network on frames of the received real-time video, and overlay a border indicating a location of at least one detected object in the frames. The system also includes a second bus for receiving the video with the overlaid border, an output port for outputting the video with the overlaid border from the second bus to an external display, and a third bus for directly transmitting the received real-time video to the output port.

公开(公告)号：US20210343013A1

公开(公告)日：2021-11-04

申请号：US17379902

申请日：2021-07-19

Applicant: COSMO ARTIFICIAL INTELLIGENCE - AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06T7/00 ,  G06T7/70 ,  G16H30/20 ,  G06N3/08 ,  G06T11/00 ,  G06T11/60 ,  G06K9/00 ,  G06K9/32 ,  G06T11/20 ,  A61B1/00 ,  A61B5/00

Abstract: The present disclosure relates to computer-implemented systems and methods for detecting a feature-of-interest in a video. In one implementation, a computer-implemented system may include a discriminator network and a generative network. The discriminator network may include a perception branch and an adversarial branch, the perception branch being configured to output detections of the feature-of-interest in the video. The generative network may be configured to receive detections of the feature-of-interest from the perception branch of the discriminator network and generate artificial representations of the feature-of-interest based on the detections from the perception branch. Further, the adversarial branch may be configured to provide an output identifying differences between the false representations and true representations of the feature-of-interest, and the perception branch may be further configured to be trained by the output of the adversarial branch so that false representations are not detected by the perception branch as true representations.

公开(公告)号：US12161305B2

公开(公告)日：2024-12-10

申请号：US18165180

申请日：2023-02-06

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06K9/00 ,  A61B1/00 ,  A61B1/31 ,  A61B5/00 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06T7/00 ,  G06T7/70 ,  G06T11/00 ,  G06T11/20 ,  G06T11/60 ,  G06V10/20 ,  G06V10/25 ,  G06V10/82 ,  G06V20/40 ,  G16H30/20

Abstract: The present disclosure relates to systems and methods for processing real-time video and detecting objects in the video. In one implementation, a system is provided that includes an input port for receiving real-time video obtained from a medical image device, a first bus for transferring the received real-time video, and at least one processor configured to receive the real-time video from the first bus, perform object detection by applying a trained neural network on frames of the received real-time video, and overlay a border indicating a location of at least one detected object in the frames. The system also includes a second bus for receiving the video with the overlaid border, an output port for outputting the video with the overlaid border from the second bus to an external display, and a third bus for directly transmitting the received real-time video to the output port.

公开(公告)号：US12026234B2

公开(公告)日：2024-07-02

申请号：US17251773

申请日：2019-06-11

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06F18/2413 ,  A61B1/00 ,  A61B1/273 ,  A61B1/31 ,  G06F18/21 ,  G06F18/214 ,  G06F18/40 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  G06T7/00 ,  G16H30/40 ,  G16H50/20

CPC classification number: G06F18/2413 ,  A61B1/000096 ,  A61B1/273 ,  A61B1/2736 ,  A61B1/31 ,  G06F18/214 ,  G06F18/2148 ,  G06F18/217 ,  G06F18/41 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  G06T7/0012 ,  G16H30/40 ,  G16H50/20 ,  G06T2207/10016 ,  G06T2207/10068 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30032 ,  G06T2207/30096 ,  G06V2201/032

Abstract: The present disclosure relates to computer-implemented systems and methods for training and using generative adversarial networks. In one implementation, a system for training a generative adversarial network may include at least one processor that may provide a first plurality of images including representations of a feature-of-interest and indicators of locations of the feature-of-interest and use the first plurality and indicators to train an object detection network. Further, the processor(s) may provide a second plurality of images including representations of the feature-of-interest, and apply the trained object detection network to the second plurality to produce a plurality of detections of the feature-of-interest. Additionally, the processor(s) may provide manually set verifications of true positives and false positives with respect to the plurality of detections, use the verifications to train a generative adversarial network, and retrain the generative adversarial network using at least one further set of images, further detections, and further manually set verifications.

公开(公告)号：US11844499B2

公开(公告)日：2023-12-19

申请号：US18165232

申请日：2023-02-06

Applicant: COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED

Inventor： Nhan Ngo Dinh ,  Giulio Evangelisti ,  Flavio Navari

IPC: G06K9/62 ,  A61B1/31 ,  G06T7/70 ,  G16H30/20 ,  G06N3/08 ,  G06T7/00 ,  G06T11/00 ,  G06T11/60 ,  G06T11/20 ,  A61B1/00 ,  A61B5/00 ,  G06V20/40 ,  G06V10/82 ,  G06F18/214 ,  G06N3/045 ,  G06V10/25 ,  G06V10/20

CPC classification number: A61B1/31 ,  A61B1/00055 ,  A61B1/000094 ,  A61B1/000095 ,  A61B1/000096 ,  A61B5/7264 ,  A61B5/7267 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0012 ,  G06T7/70 ,  G06T11/001 ,  G06T11/203 ,  G06T11/60 ,  G06V10/25 ,  G06V10/255 ,  G06V10/82 ,  G06V20/40 ,  G06V20/49 ,  G16H30/20 ,  G06T2207/10016 ,  G06T2207/10068 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06T2207/30032 ,  G06T2207/30064 ,  G06T2207/30096 ,  G06V2201/03 ,  G06V2201/032

Abstract: The present disclosure relates to systems and methods for processing real-time video and detecting objects in the video. In one implementation, a system is provided that includes an input port for receiving real-time video obtained from a medical image device, a first bus for transferring the received real-time video, and at least one processor configured to receive the real-time video from the first bus, perform object detection by applying a trained neural network on frames of the received real-time video, and overlay a border indicating a location of at least one detected object in the frames. The system also includes a second bus for receiving the video with the overlaid border, an output port for outputting the video with the overlaid border from the second bus to an external display, and a third bus for directly transmitting the received real-time video to the output port.