The investigators aim to investigate the utility of radiomics to differentiate malignant nodules from benign nodules and invasive adenocarcinoma from non-invasive adenocarcinoma.
With the development of computed tomography (CT) equipment and the increasing use of lung cancer screening programs with low-dose CT, a growing number of early-stage lung cancers were detected so that a large number of patients have undergone surgery. Although a number of radiological studies have been used morphological signs so-called semantic features to make a differential diagnosis, it is still hard to apply by clinician because pulmonary nodules especially ground-glass nodules and small size nodules have atypical radiology signs and have strong subjectivity from different observers. Recently, CT-based radiomics, extracting the quantitative high-throughput features from medical images and facilitating clinical decision-making system, showed a good performance to predict diagnosis and prognosis of diverse cancer. Therefore, the proposed project aims to develop and validate radiomics models based on CT images to identify malignant nodules and then to discriminate the different types of lung adenocarcinoma in patients with pulmonary nodules.
Study Type
OBSERVATIONAL
Enrollment
800
The high-throughput extraction of large amounts of quantitative image features from medical images
Affiliated Zhongshan Hospital of Dalian University
Dalian, Liaoning, China
Malignant nodules classifier
Model based on Radiomic that can differentiate malignant nodules from benign nodules.
Time frame: 30 days
Invasive adenocarcinoma classifier
Model based on Radiomic that can differentiate invasive adenocarcinoma from non-invasive adenocarcinoma.
Time frame: 30 days
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.