公开(公告)号：US12056880B2

公开(公告)日：2024-08-06

申请号：US17352229

申请日：2021-06-18

Applicant: Korea Advanced Institute of Science and Technology

Inventor： JongChul Ye ,  Sangjoon Park ,  Yujin Oh ,  Gwanghyun Kim

IPC: G06T7/143 ,  G06T7/11

CPC classification number: G06T7/143 ,  G06T7/11 ,  G06T2207/10116 ,  G06T2207/20004 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30061

Abstract: Disclosed are a method of classifying lesions of chest x-ray radiographs based on data normalization and local patches and an apparatus thereof. The method includes converting an input chest x-ray radiograph into a normalized image, segmenting the converted normalized image into an organ area by using a first neural network based on a pre-learned segmentation model, generating local patches for the segmented organ area, and classifying a lesion in the input chest x-ray radiograph by using a second neural network based on a pre-learned classification model for the generated local patches.

公开(公告)号：US12169933B2

公开(公告)日：2024-12-17

申请号：US17704879

申请日：2022-03-25

Applicant: Korea Advanced Institute of Science and Technology

Inventor： JongChul Ye ,  Sangjoon Park ,  Gwanghyun Kim

IPC: G06T7/00 ,  A61B6/00 ,  G06T7/10 ,  G06T7/73 ,  G06V10/32 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82

Abstract: Disclosed is a method and apparatus for quantifying severity of infectious disease based on a vision transformer using a chest X-ray (CXR) image. Here, a method of quantifying severity of infectious disease based on a vision transformer includes receiving an input CXR image; extracting a feature map from the received input CXR image using a pretrained neural network; classifying a lesion in the input CXR image using the vision transformer based on the extracted feature map; and quantifying severity of the input CXR image based on the extracted feature map and the classified lesion.

公开(公告)号：US20220309661A1

公开(公告)日：2022-09-29

申请号：US17704879

申请日：2022-03-25

Applicant: Korea Advanced Institute of Science and Technology

Inventor： JongChul Ye ,  Sangjoon Park ,  Gwanghyun Kim

IPC: G06T7/00 ,  G06V10/764 ,  G06V10/77 ,  G06V10/32 ,  G06T7/73 ,  G06T7/10 ,  G06V10/774 ,  G06V10/82 ,  A61B6/00

Abstract: Disclosed is a method and apparatus for quantifying severity of infectious disease based on a vision transformer using a chest X-ray (CXR) image. Here, a method of quantifying severity of infectious disease based on a vision transformer includes receiving an input CXR image; extracting a feature map from the received input CXR image using a pretrained neural network; classifying a lesion in the input CXR image using the vision transformer based on the extracted feature map; and quantifying severity of the input CXR image based on the extracted feature map and the classified lesion.

公开(公告)号：US20230255581A1

公开(公告)日：2023-08-17

申请号：US18043853

申请日：2021-08-30

Applicant: The General Hospital Corporation ,  Korea Advanced Institute of Science and Technology

Inventor： Ik-Kyung Jang ,  Jong Chul Ye ,  Sangjoon Park

IPC: A61B6/00 ,  A61B6/03 ,  G06N3/084 ,  G06T7/00 ,  G06N3/0499 ,  G16H20/10

CPC classification number: A61B6/504 ,  A61B6/032 ,  G06N3/084 ,  G06T7/0012 ,  G06N3/0499 ,  G16H20/10 ,  G06T2207/20084 ,  G06T2207/10101 ,  G06T2207/10081 ,  G06T2207/10088

Abstract: A method for identifying plaque erosion in a vessel. The method includes: obtaining, using a processor, a sequence of images of the vessel; extracting, using the processor, one or more image features from the sequence of images using a convolutional neural network model; contextually classifying, using the processor, the one or more extracted image features using a cascaded self-attention trained model; and generating, using the processor, one or more diagnostic labels associated with the sequence of images based on contextually classifying the one or more extracted image features, where the one or more diagnostic labels may include an indication of a presence of plaque erosion or an absence of plaque erosion.

公开(公告)号：US20220036564A1

公开(公告)日：2022-02-03

申请号：US17352229

申请日：2021-06-18

Applicant: Korea Advanced Institute of Science and Technology

Inventor： JongChul Ye ,  Sangjoon Park ,  Yujin Oh ,  Gwanghyun Kim

IPC: G06T7/143 ,  G06T7/11

Abstract: Disclosed are a method of classifying lesions of chest x-ray radiographs based on data normalization and local patches and an apparatus thereof. The method includes converting an input chest x-ray radiograph into a normalized image, segmenting the converted normalized image into an organ area by using a first neural network based on a pre-learned segmentation model, generating local patches for the segmented organ area, and classifying a lesion in the input chest x-ray radiograph by using a second neural network based on a pre-learned classification model for the generated local patches.