AUTHOR=Dong Zhenglin , Chen Xiahan , Cheng Zhaorui , Luo Yuanbo , He Min , Chen Tao , Zhang Zijie , Qian Xiaohua , Chen Wei 

TITLE=Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.941744

DOI=10.3389/fonc.2022.941744

ISSN=2234-943X

ABSTRACT=Pancreatic cystic neoplasms (PCNs) are a group of heterogenous diseases with distinct prognosis. Existing differential diagnosis methods require invasive biopsy or prolonged monitoring. We sought to develop an inexpensive, non-invasive differential diagnosis system for PCNs based on radiomics features and clinical characteristics for higher total PCN screening rate. We retrospectively analyzed CT images and clinical data from 129 patients with PCN, including 47 patients with intraductal papillary mucinous neoplasms (IPMNs), 49 patients with serous cystadenomas (SCNs), and 33 patients with mucous cystic neoplasms (MCNs). 6 clinical characteristics and 944 radiomics features were tested, and 9 features were finally selected for model construction using DXscore algorithm. 5-fold cross-validation algorithm and test group were applied to verify the results. In 5-fold cross-validation section, the AUC of our model was 0.8687 and the total accuracy was 74.23%, where the accuracy of IPMNs, SCNs and MCNs were 74.26%, 78.37% and 68.00%, respectively. In test group, the AUC was 0.8462 and the total accuracy was 73.61%. In conclusion，our research constructed an end-to-end powerful PCN differential diagnosis system based on radiomics method, which could assist decision-making in clinical practice.