Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
COMPUTER APPARATUS AND METHOD FOR IMPLEMENTING CLASSIFICATION DETECTION OF PULMONARY NODULE IMAGES
Document Type and Number:
WIPO Patent Application WO/2019/238104
Kind Code:
A1
Abstract:
The present invention provides a computer apparatus and a method for implementing classification detection of pulmonary nodule images. The method comprises the following steps: scanning a pulmonary CT image of a patient by means of a CT scanner, and performing adaptive morphology segmentation on the pulmonary CT image to obtain pulmonary nodule images; marking the pulmonary nodule images into different categories and storing the marked pulmonary nodule images in an image database; establishing a pulmonary nodule image unit library on the basis of the pulmonary nodule images in the image database; calculating a distance between each two image units in the pulmonary nodule image unit library to obtain a distance matrix; clustering the distance matrix; calculating pulmonary nodule CT value density distribution features of each of the pulmonary nodule image units; implementing training and classification of the degrees of risk of pulmonary nodules by using the CT value density distribution features on the basis of a supervised machine learning model; removing a false positive pulmonary nodule image according to the CT value density distribution of each of the pulmonary nodule images. The present invention improves the accuracy of classification detection of pulmonary nodule images and has a wide range of applications.

More Like This:
JP6928876Form type learning system and image processing device
JP2011221689LEARNING DEVICE, LEARNING METHOD, RECOGNITION DEVICE, RECOGNITION METHOD, AND PROGRAM
JP3120534DEVICE FOR POSITIONING RECORDING HEAD CHIP
Inventors:
YAO YUDONG (CN)
QIAN WEI (CN)
ZHENG BIN (CN)
MA HE (CN)
QI SHOULIANG (CN)
ZHAO MINGFANG (CN)
Application Number:
PCT/CN2019/091190
Publication Date:
December 19, 2019
Filing Date:
June 14, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ANYCHECK INFORMATION TECH CO LTD (CN)
International Classes:
G06T7/00
Foreign References:
CN106250701A2016-12-21
CN108010013A2018-05-08
Other References:
CAO, LEI: "Analysis and Identification of Pulmonary Nodule Images", INFORMATION & TECHNOLOGY, CHINA DOCTORAL DISSERTATIONS FULL-TEXT DATABASE, 15 January 2010 (2010-01-15), pages 30 - 42
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: PREPARATION METHOD FOR PYRIDINYLAMINOPYRIMIDINE DERIVATIVE AND INTERMEDIATE THEREOF

Next Patent: MEDICAL INSURANCE INTERFACE CODE MATCHING METHOD, COMPUTER DEVICE AND READABLE STORAGE MEDIUM