Combining CNN and Hybrid Active Contours for Head and Neck Tumor Segmentation in CT and PET Images

摘要

Automatic segmentation of head and neck tumor plays an important role for radiomics analysis. In this short paper, we propose an automatic segmentation method for head and neck tumors from PET and CT images based on the combination of convolutional neural networks (CNNs) and hybrid active contours. Specifically, we first introduce a multi-channel 3D U-Net to segment the tumor with the concatenated PET and CT images. Then, we estimate the segmentation uncertainty by model ensembles, and define a segmentation quality score to select the cases with high uncertainties. Finally, we develop a hybrid active contour model to refine the high uncertainty cases. We evaluate the proposed method on the MICCAI 2020 HECKTOR challenge and achieve promising performance with average Dice Similarity Coefficient, precision and recall of 0.7525, 0.8384, 0.7471 respectively.