Skip to Main Content

COVID-19 is an emerging, rapidly evolving situation.

What people with cancer should know: https://www.cancer.gov/coronavirus

Get the latest public health information from CDC: https://www.coronavirus.gov

Get the latest research information from NIH: https://covid19.nih.gov/

Principal Investigator
Name
zhengwen Ma
Degrees
M.S.
Institution
Zhongshan Yangshi Technology Co., Ltd
Position Title
Technician
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-746
Initial CDAS Request Approval
Dec 31, 2020
Title
Lung Nodule Detection and Benign and Malignant Diagnosis Based on Deep Learning
Summary
The prevalence of lung cancer is increasing yearly and with the highest mortality rate among other types of cancer. Early detection of lung cancer and treatment will significantly improve patient survival. CT image is the effective technique for the detection of lung cancer, and pulmonary nodules are the early clinical manifestations of lung cancer, which means that the study on the detection and diagnosis of early pulmonary nodules based on CT images has important scientific and clinical significance. Deep learning technology has been increasingly applied in the field of medical image processing and has achieved good results. We plan to use deep learning technology to detect pulmonary nodules and to diagnose benign/malignant pulmonary nodules. A common difficulty in medical imaging is the lack of sufficient data tagging/annotation to train deep learning models. At present, relatively small LUNA16 and LIDC-IDRI data sets are mainly used for the detection or classification of pulmonary nodules. We plan to use semi-supervised methods to fully utilize LUNA16, LIDC-IDRI and NLST datasets to train our model on more data to improve the accuracy of pulmonary nodules detection and classification.
Aims

1.We will explore semi-supervised methods to train our model on more data to improve the performance of pulmonary nodule detection and classification.
2.We will design and implementation of lung cancer assisted diagnosis system based Artificial Intelligence.

Collaborators

NO