We propose a radiomics approach to identify prognostic biomarkers of HCC and provide patients with some reasonable advice for their therapies.
Radiomics is emerging fields that is based on quantitative analysis of medical images. Tri-phasic CT images are currently the standard imaging modality for the management of HCC. Our goal is to improve treatment decisions of HCC patients through better understanding of their prognosis based on radiomics modeling of HCC. Radiomics is defined as the extraction of quantitative image features from medical images. We will use triphasic CT data of at least 200 patients and develop a robust strategy to extract imaging features from CT. We will use deep learning in the form of a Convolutional Neural Network to segment HCC lesions and use image feature extraction algorithms with supervised classification to predict prognosis.
Study Type
OBSERVATIONAL
Enrollment
1,200
Key Laboratory of Molecular Imaging, Chinese Academy of Sciences
Beijing, Beijing Municipality, China
quantitative image features extracted from CT images can be used as imaging marker for prognosis
Time frame: five(year)
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.