Abstract #2391

Applying Radiomics and Convolutional Neural Network Analysis to distinguish Lymph Node Invasion in Prostate Cancer using Multi-parametric MRI

Yang Song¹, Ying Hou², Min-xiong Zhou³, Xu Yan⁴, Ye-feng Yao¹, Yu-dong Zhang², and Guang Yang¹

¹Shanghai Key Laboratory of Magnetic Resonance, East China Normal Univeristy, Shanghai, China, ²Department of Radiology, the First Affiliated Hospital with Nanjing Medical University, Nanjing, China, ³Shanghai University of Medicine & Health Sciences, Shanghai, China, ⁴MR Scientific Marketing, Siemens Healthcare, Shanghai, China

We compared a radiomics model and a convolutional neural network (CNN) model to distinguish lymph node invasion (LNI) in prostate cancer (PCa) using multi-parametric magnetic resonance images (mp-MRI). We trained the models in 281 patients and evaluated them in another 71 cases. The radiomics/CNN model produced an AUC 0.741/0.722, sensitivity 0.769/0.692, specificity 0.690/0.845 for the differentiation of LNI, which showed potential for the diagnosis of LNI in PCa.

This abstract and the presentation materials are available to members only; a login is required.

Join Here