The invention relates to a PET-CT multimodality nasopharyngeal carcinoma image segmentation method based on a hypergraph model. The PET-CT multimodality nasopharyngeal carcinoma image segmentation method comprises the steps of: extracting gray scale information and location information of pixel points in a nasopharyngeal tumor image to construct a data set, constructing a sparse representation model according to the data set, solving the sparse representation model to obtain a reconstruction coefficient matrix and constructing hyperedges, calculating a similarity degree of data samples by utilizing a Gaussian kernel model, regarding the similarity degree as a weight value of the hyperedges, and solving a hyperedge order and a vertex order to construct a hypergraph Laplacian matrix; and marking the nasopharyngeal tumor image to obtain mark vectors, constructing a semi-supervised learning model based on the mark vectors, solving a least square problem to obtain an optimal tangent vector, and finally returning a classification result to the pixel level, namely, completing the segmentation of the tumor image. The PET-CT multimodality nasopharyngeal carcinoma image segmentation method is higher in segmentation precision when compared with a single-modality method, and the hypergraph model based on the combination of sparse representation and Gaussian kernel has higher segmentation precision for nasopharyngeal tumor image data when compared with other simple graph model or hypergraph model.