公开(公告)号：US11847547B2

公开(公告)日：2023-12-19

申请号：US17692337

申请日：2022-03-11

Applicant: SHENZHEN KEYA MEDICAL TECHNOLOGY CORPORATION

Inventor： Xin Wang ,  Youbing Yin ,  Qi Song ,  Junjie Bai ,  Yi Lu ,  Yi Wu ,  Feng Gao ,  Kunlin Cao

IPC: G06T15/00 ,  G06N3/006 ,  G06N3/08 ,  G06T19/00 ,  G06V10/42 ,  G06F18/21 ,  G06V10/776

CPC classification number: G06N3/006 ,  G06F18/217 ,  G06N3/08 ,  G06T19/00 ,  G06V10/42 ,  G06V10/776

Abstract: Methods and Systems for generating a centerline for an object in an image and computer readable medium are provided. The method includes receiving an image containing the object. The method also includes generating the centerline of the object, by a processor, using a reinforcement learning network configured to predict movement of a virtual agent that traces the centerline in the image. The reinforcement learning network is further configured to perform at least one auxiliary task that detects a bifurcation in a trajectory of the object. The reinforcement learning network is trained by maximizing a cumulative reward and minimizing an auxiliary loss of the at least one auxiliary task. Additionally, the method includes displaying the centerline of the object.

公开(公告)号：US20220198226A1

公开(公告)日：2022-06-23

申请号：US17692337

申请日：2022-03-11

Applicant: SHENZHEN KEYA MEDICAL TECHNOLOGY CORPORATION

Inventor： Xin Wang ,  Youbing Yin ,  Qi Song ,  Junjie Bai ,  Yi Lu ,  Yi Wu ,  Feng Gao ,  Kunlin Cao

IPC: G06K9/62 ,  G06N3/08 ,  G06T19/00 ,  G06V10/42

Abstract: Methods and Systems for generating a centerline for an object in an image and computer readable medium are provided. The method includes receiving an image containing the object. The method also includes generating the centerline of the object, by a processor, using a reinforcement learning network configured to predict movement of a virtual agent that traces the centerline in the image. The reinforcement learning network is further configured to perform at least one auxiliary task that detects a bifurcation in a trajectory of the object. The reinforcement learning network is trained by maximizing a cumulative reward and minimizing an auxiliary loss of the at least one auxiliary task. Additionally, the method includes displaying the centerline of the object.

公开(公告)号：US11308362B2

公开(公告)日：2022-04-19

申请号：US16827613

申请日：2020-03-23

Applicant: SHENZHEN KEYA MEDICAL TECHNOLOGY CORPORATION

Inventor： Xin Wang ,  Youbing Yin ,  Qi Song ,  Junjie Bai ,  Yi Lu ,  Yi Wu ,  Feng Gao ,  Kunlin Cao

IPC: G06T15/00 ,  G06K9/62 ,  G06N3/08 ,  G06T19/00 ,  G06V10/42

Abstract: Methods and Systems for generating a centerline for an object in an image and computer readable medium are provided. The method includes receiving an image containing the object. The method also includes generating the centerline of the object by tracing a sequence of patches with a virtual agent. For each patch other than the initial patch, the method determines a current patch based on the position and action of the virtual agent at a previous patch. The method further determines a policy function and a value function based on the current patch using a trained learning network, which includes an encoder followed by a first learning network and a second learning network. The learning network is trained by maximizing a cumulative reward. The method also determines the action of the virtual agent at the current patch. Additionally, the method displays the centerline of the object.

公开(公告)号：US20200311485A1

公开(公告)日：2020-10-01

申请号：US16827613

申请日：2020-03-23

Applicant: SHENZHEN KEYA MEDICAL TECHNOLOGY CORPORATION

Inventor： Xin Wang ,  Youbing Yin ,  Qi Song ,  Junjie Bai ,  Yi Lu ,  Yi Wu ,  Feng Gao ,  Kunlin Cao

IPC: G06K9/62 ,  G06K9/52 ,  G06T19/00 ,  G06N3/08

Abstract: Methods and Systems for generating a centerline for an object in an image and computer readable medium are provided. The method includes receiving an image containing the object. The method also includes generating the centerline of the object by tracing a sequence of patches with a virtual agent. For each patch other than the initial patch, the method determines a current patch based on the position and action of the virtual agent at a previous patch. The method further determines a policy function and a value function based on the current patch using a trained learning network, which includes an encoder followed by a first learning network and a second learning network. The learning network is trained by maximizing a cumulative reward. The method also determines the action of the virtual agent at the current patch. Additionally, the method displays the centerline of the object.