Automatic Tumor Segmentation and Prediction of Therapeutic Response to Gamma Knife Radiosurgery Based on Multi-parametric MRI in Vestibular Schwannoma

Dual-modality imaging of structural ultrasound and functional magnetics for the high-specificity of nano-targeting tumors

Trace

Technical Name	Metastasis Cancer Prediction of Breast Ultrasound Using Deep Convolutional Neural Network
Project Operator	National Taiwan University
Project Host	張瑞峰
Summary	We used the tumor region with different thicknesses of the peritumor (surrounding tissue) to predict the metastasis status of a tumor. This study finds that the peritumor 15 pixels achieved the best performance with an accuracy of 84.8%, a sensitivity of 88.8%, a specificity of 81.3%, and an area under the curve (AUC) of receiver operating characteristic (ROC) of 0.926.
Scientific Breakthrough	Some computer-aided diagnosis (CAD) systems used of primary tumor characteristics (such as tumor size, tumor type and grade, lymphovascular invasion, and hormonal status) to predict metastasis status in breast cancer. But, the performance was not good. We developed a CAD system to determine the metastasis status in breast cancer using the tumor surrounding tissue features in 2D US images.
Industrial Applicability	This study will help physicians to predict the tumor metastasis status in the future and the treatment direction of prognosis. We also need more data and clinical trials to prove the robustness of this method.
Keyword	metastasis status image matting tumor segmentation deep convolution neural network cancer metastasis segmentation convolution neural network neural network CNN

Matchmaking

other people also saw