基于活动轮廓模型和影像组学的乳腺癌LVI状态预测

针对乳腺癌患者术前LVI状态预测问题，提出了活动轮廓模型和影像组学相结合的计算机辅助分析方法.首先，提出一种基于后验概率和模糊速度函数的活动轮廓模型方法来完成乳腺癌DCE-MRI图像分割.通过在小波域下构建基于后验概率的活动轮廓模型的区域项，同时利用模糊速度函数构建活动轮廓模型的边界项，可以提高乳腺癌病灶分割的准确性.其次，提取形态、灰度、纹理等图像特征，利用集成分类器随机森林方法构造LVI状态的预测模型.实验结果表明，所构建的模型对乳腺癌患者LVI状态具有较好的预测能力.

Breast Cancer Related LVI Status Prediction Based on Active Contour Model and Radiomics

To predict preoperative lymphovascular invasion(LVI)status of breast cancer patients， a computer-aided analysis method which combines an active contour model and radiomics is proposed. First， the image from dynamic contrast enhanced magnetic resonance imaging(DCE-MRI)of breast cancer is segmented by an active contour model(ACM)based on post probability and fuzzy velocity function. By constructing the region term of the active contour model based on post probability in the wavelet domain and the edge stop term of the active contour model by using the fuzzy velocity function， the accuracy of breast cancer lesion segmentation can be improved. Second， the image features such as morphology， grayscale and texture are extracted. Finally， a model for predicting LVI status is developed by the random forest classifier and its predictive ability is verified by experimental results.