影像组学和深度学习在胰腺癌诊疗和评估中的研究进展

Research Progress of Radiomics and Deep Learning in Pancreatic Cancer

胰腺癌的术前准确诊断和评估是影像学检查的主要目的,可指导临床决策和预后评价。影像组学和深度学习为胰腺癌的精准诊疗和疗效评估提供了新的技术手段。综述影像组学和深度学习在胰腺癌研究中的现状和进展,介绍影像组学和深度学习在胰腺癌前驱病变恶性潜能预测、诊断与鉴别诊断、疗效评估、预后预测以及基因表达方面的应用;阐述未来通过标准化质量控制和多中心大数据库建立等方面的努力,使影像组学和深度学习技术为临床治疗决策提供更全面更准确的信息,促进胰腺癌的精准诊疗。

Imaging examinations are used for preoperative diagnosis and evaluation of pancreatic cancer,which play great role in clinical decision-making and prognosis prediction.Radiomics and deep learning provide new means for accurate diagnosis and treatment of pancreatic cancer.In this paper,the developments of radiomics and deep learning in pancreatic cancer were reviewed.The paper reviewed the application of radiomics and deep learning in predicting malignant potential of precursor lesions,diagnosis and differentiating diagnosis,therapeutic effect evaluation,prognosis prediction,and gene expression status.Radiomics and deep learning may provide comprehensive information for clinical decision-making and provide help for precise diagnosis and treatment of pancreatic cancer,with standardized quality control and multi-center database establishment.