Retrospectively analyzed radiomics features of pancreatic ductal adenocarcinoma to predict staging and prognosis

Pancreatic cancer is the most malignant tumor of the digestive system and the seventh leading cause of cancer-related death worldwide.The rate of lymph node metastasis in pancreatic cancer is as high as 59%.Lymph node metastasis is an important prognostic factor, which is closely associated with poor prognosis of pancreatic cancer patients.Preoperative accurate prediction of lymph node status has important clinical value.At present, the preoperative LN status of pancreatic cancer patients is mainly evaluated by conventional imaging methods such as CT and MRI.The accuracy of evaluating LN state only from the perspective of morphology is poor.Ductal adenocarcinoma of the pancreas is highly malignant, has a median disease-free survival of only about 1 year, and most pancreatic cancer patients eventually relapse.At present, TNM staging system is mainly used for prognosis evaluation.However, even among patients with the same TNM stage, the prognosis is still significantly different, which reflects the lack of prognostic information provided by the TNM stage.Imaging omics extracts a large number of quantitative features from medical images in a high-throughput manner to enable non-invasive analysis of intra-tumor heterogeneity.In this study, we planned to construct a prediction study of preoperative lymph node metastasis and prognosis of pancreatic cancer based on multimodal imaging, so as to provide a basis for clinical treatment decision and prognosis.

Inclusion Criteria:

• radical resection was performed, and histopathologically confirmed pancreatic ductal adenocarcinoma and lymph node status;2) CT and/or MRI enhancement examinations were performed 2 weeks before surgery;3) Patients with complete clinical data

Exclusion Criteria:

• (1)Patients who received radiotherapy or chemotherapy before preoperative imaging examination;2) Poor image quality.

Pancreatic tumor patients