公开(公告)号：US11170502B2

公开(公告)日：2021-11-09

申请号：US16649650

申请日：2019-01-07

Applicant: Dalian University of Technology

Inventor： Rui Xu ,  Xinchen Ye ,  Lin Lin ,  Haojie Li ,  Xin Fan ,  Zhongxuan Luo

IPC: G06T7/41 ,  G06N3/08 ,  G06T7/00 ,  G06N3/04

Abstract: Provided is a method based on deep neural network to extract appearance and geometry features for pulmonary textures classification, which belongs to the technical fields of medical image processing and computer vision. Taking 217 pulmonary computed tomography images as original data, several groups of datasets are generated through a preprocessing procedure. Each group includes a CT image patch, a corresponding image patch containing geometry information and a ground-truth label. A dual-branch residual network is constructed, including two branches separately takes CT image patches and corresponding image patches containing geometry information as input. Appearance and geometry information of pulmonary textures are learnt by the dual-branch residual network, and then they are fused to achieve high accuracy for pulmonary texture classification. Besides, the proposed network architecture is clear, easy to be constructed and implemented.

公开(公告)号：US11501435B2

公开(公告)日：2022-11-15

申请号：US17112623

申请日：2020-12-04

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Rui Xu ,  Xinchen Ye ,  Haojie Li ,  Lin Lin

IPC: G06T7/40 ,  G06T7/00

Abstract: The invention discloses an unsupervised content-preserved domain adaptation method for multiple CT lung texture recognition, which belongs to the field of image processing and computer vision. This method enables the deep network model of lung texture recognition trained in advance on one type of CT data (on the source domain), when applied to another CT image (on the target domain), under the premise of only obtaining target domain CT image and not requiring manually label the typical lung texture, the adversarial learning mechanism and the specially designed content consistency network module can be used to fine-tune the deep network model to maintain high performance in lung texture recognition on the target domain. This method not only saves development labor and time costs, but also is easy to implement and has high practicability.

公开(公告)号：US11551029B2

公开(公告)日：2023-01-10

申请号：US17112367

申请日：2020-12-04

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Rui Xu ,  Xinchen Ye ,  Haojie Li ,  Lin Lin

IPC: G06K9/00 ,  G06K9/62 ,  G16H50/20 ,  G16H30/40 ,  G06N3/08 ,  G06V10/30

Abstract: The invention discloses a deep network lung texture recognition method combined with multi-scale attention, which belongs to the field of image processing and computer vision. In order to accurately recognize the typical texture of diffuse lung disease in computed tomography (CT) images of the lung, a unique attention mechanism module and multi-scale feature fusion module were designed to construct a deep convolutional neural network combing multi-scale and attention, which achieves high-precision automatic recognition of typical textures of diffuse lung diseases. In addition, the proposed network structure is clear, easy to construct, and easy to implement.

公开(公告)号：US11295168B2

公开(公告)日：2022-04-05

申请号：US17112499

申请日：2020-12-04

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Xinchen Ye ,  Rui Xu ,  Xin Fan

IPC: G06K9/62 ,  G06T7/55 ,  H04N1/60

Abstract: The invention discloses a depth estimation and color correction method for monocular underwater images based on deep neural network, which belongs to the field of image processing and computer vision. The framework consists of two parts: style transfer subnetwork and task subnetwork. The style transfer subnetwork is constructed based on generative adversarial network, which is used to transfer the apparent information of underwater images to land images and obtain abundant and effective synthetic labeled data, while the task subnetwork combines the underwater depth estimation and color correction tasks with the stack network structure, carries out collaborative learning to improve their respective accuracies, and reduces the gap between the synthetic underwater image and the real underwater image through the domain adaptation strategy, so as to improve the network's ability to process the real underwater image.