公开(公告)号：US20230263384A1

公开(公告)日：2023-08-24

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

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

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：US20230255468A1

公开(公告)日：2023-08-17

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

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：US20240013509A1

公开(公告)日：2024-01-11

申请号：US18348785

申请日：2023-07-07

Applicant: COSMO ARTIFICIAL INTELLIGENCE – AI LIMITED

Inventor： ANDREA CHERUBINI ,  NHAN NGO DINH ,  PIETRO SALVAGNINI ,  CARLO BIFFI

IPC: G06V10/62 ,  G06T7/00 ,  G06V10/44 ,  G16H30/20

CPC classification number: G06V10/62 ,  G06T7/0002 ,  G06V10/44 ,  G16H30/20 ,  G06T2207/30168

Abstract: A computer-implemented method for detecting at least one feature of interest in images captured with an imaging device includes: receiving an ordered set of images and analyzing one or more subsets of the ordered set using a local spatio-temporal processing module. The local spatio-temporal processing module determines presence of characteristics related to the feature of interest in each image of each subset of images and annotates the subset of images. The method also includes processing a set of feature vectors of the ordered set of images using a global spatio-temporal processing module to refine the determined characteristics associated with each subset of images, and calculate one or more values for each image using a timeseries analysis module, the values being representative of the feature of interest and calculated using the refined characteristics associated with each subset of images and spatio-temporal information.

公开(公告)号：US20240013383A1

公开(公告)日：2024-01-11

申请号：US18348734

申请日：2023-07-07

Applicant: COSMO ARTIFICIAL INTELLIGENCE – AI LIMITED

Inventor： ANDREA CHERUBINI ,  NHAN NGO DINH ,  PIETRO SALVAGNINI ,  CARLO BIFFI

IPC: G06T7/00 ,  G06V10/44 ,  G06V20/40 ,  G06T7/73 ,  G06T7/11 ,  G06T11/00 ,  G16H30/40 ,  G16H15/00 ,  G16H30/20

CPC classification number: G06T7/0012 ,  G06V10/443 ,  G06V20/47 ,  G06V20/44 ,  G06T7/73 ,  G06T7/11 ,  G06T11/00 ,  G16H30/40 ,  G16H15/00 ,  G16H30/20 ,  G06T2207/10016 ,  G06T2207/30028 ,  G06T2207/30096 ,  G06T2207/10068 ,  G06T2210/41 ,  A61B1/000096

Abstract: A computer-implemented method for detecting at least one feature of interest in images captured with an imaging device includes: receiving an ordered set of images and analyzing one or more subsets of the ordered set using a local spatio-temporal processing module. The local spatio-temporal processing module determines presence of characteristics related to the feature of interest in each image of each subset of images and annotates the subset of images. The method also includes processing a set of feature vectors of the ordered set of images using a global spatio-temporal processing module to refine the determined characteristics associated with each subset of images, and calculate one or more values for each image using a timeseries analysis module, the values being representative of the feature of interest and calculated using the refined characteristics associated with each subset of images and spatio-temporal information.

公开(公告)号：US20240303299A1

公开(公告)日：2024-09-12

申请号：US18652226

申请日：2024-05-01

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 representation 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 tr 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：US20240296560A1

公开(公告)日：2024-09-05

申请号：US18578337

申请日：2022-07-12

Applicant: COSMO ARTIFICIAL INTELLIGENCE – AI LIMITED

Inventor： ANDREA CHERUBINI ,  PIETRO SALVAGNINI ,  CARLO BIFFI ,  NHAN NGO DINH

IPC: G06T7/00 ,  A61B1/00 ,  G06T7/60 ,  G06T7/73 ,  G06V10/764 ,  G06V10/82 ,  G06V20/40 ,  G06V20/50 ,  G16H70/20

CPC classification number: G06T7/0012 ,  A61B1/000094 ,  G06T7/60 ,  G06T7/73 ,  G06V10/764 ,  G06V10/82 ,  G06V20/46 ,  G06V20/50 ,  G16H70/20 ,  G06T2207/10016 ,  G06T2207/10068 ,  G06T2207/20084 ,  G06T2207/30032 ,  G06T2207/30096 ,  G06V2201/032

Abstract: A computer-implemented system is provided that receives a real-time video captured from a medical image device during a medical procedure. The real-time video may include a plurality of frames. The system may be adapted to detect an object of interest in the plurality of frames and apply one or more neural networks configured to identify a plurality of characteristics of the detected object of interest, such as classification, size, and/or location. In some embodiments, the system is adapted to identify, based on one or more of the plurality of characteristics, a medical guideline and present, in real-time on a display device during the medical procedure, information for the medical guideline.

公开(公告)号：US20240108209A1

公开(公告)日：2024-04-04

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: A61B1/31 ,  A61B1/00 ,  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：US20240020835A1

公开(公告)日：2024-01-18

申请号：US18348677

申请日：2023-07-07

Applicant: COSMO ARTIFICIAL INTELLIGENCE – AI LIMITED

Inventor： ANDREA CHERUBINI ,  NHAN NGO DINH ,  PIETRO SALVAGNINI ,  CARLO BIFFI

IPC: G06T7/00 ,  G06V20/40 ,  G06T7/73 ,  G06T7/155 ,  G06T7/11 ,  G06T11/00 ,  G16H15/00 ,  G16H30/40

CPC classification number: G06T7/0012 ,  G06V20/47 ,  G06V20/44 ,  G06T7/73 ,  G06T7/155 ,  G06T7/11 ,  G06T11/00 ,  G16H15/00 ,  G16H30/40 ,  G06T2207/20076 ,  G06T2207/20084 ,  G06T2207/30028 ,  G06T2207/30096 ,  G06T2207/10068 ,  G06T2210/41

Abstract: A computer-implemented method for detecting at least one feature of interest in images captured with an imaging device includes: receiving an ordered set of images and analyzing one or more subsets of the ordered set using a local spatio-temporal processing module. The local spatio-temporal processing module determines presence of characteristics related to the feature of interest in each image of each subset of images and annotates the subset of images. The method also includes processing a set of feature vectors of the ordered set of images using a global spatio-temporal processing module to refine the determined characteristics associated with each subset of images, and calculate one or more values for each image using a timeseries analysis module, the values being representative of the feature of interest and calculated using the refined characteristics associated with each subset of images and spatio-temporal information.