Huang Wei, Xu Yue, Li Zhao, Li Jun, Chen Qing, Huang Qiang, Wu Yaping, Chen Hongtan
Department of Gastroenterology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Research Center for Data Hub and Security, Zhejiang Lab, Hangzhou, China.
Sci Rep. 2025 May 12;15(1):16398. doi: 10.1038/s41598-025-01502-4.
Pancreatic cystic neoplasms (PCNs) are a complex group of lesions with a spectrum of malignancy. Accurate differentiation of PCN types is crucial for patient management, as misdiagnosis can result in unnecessary surgeries or treatment delays, affecting the quality of life. The significance of developing a non-invasive, accurate diagnostic model is underscored by the need to improve patient outcomes and reduce the impact of these conditions. We developed a machine learning model capable of accurately identifying different types of PCNs in a non-invasive manner, by using a dataset comprising 449 MRI and 568 CT scans from adult patients, spanning from 2009 to 2022. The study's results indicate that our multimodal machine learning algorithm, which integrates both clinical and imaging data, significantly outperforms single-source data algorithms. Specifically, it demonstrated state-of-the-art performance in classifying PCN types, achieving an average accuracy of 91.2%, precision of 91.7%, sensitivity of 88.9%, and specificity of 96.5%. Remarkably, for patients with mucinous cystic neoplasms (MCNs), regardless of undergoing MRI or CT imaging, the model achieved a 100% prediction accuracy rate. It indicates that our non-invasive multimodal machine learning model offers strong support for the early screening of MCNs, and represents a significant advancement in PCN diagnosis for improving clinical practice and patient outcomes. We also achieved the best results on an additional pancreatic cancer dataset, which further proves the generality of our model.
胰腺囊性肿瘤（PCNs）是一组具有不同恶性程度的复杂病变。准确区分PCN类型对于患者管理至关重要，因为误诊可能导致不必要的手术或治疗延误，影响生活质量。开发一种非侵入性、准确的诊断模型的重要性因改善患者预后和减少这些疾病影响的需求而得到凸显。我们开发了一种机器学习模型，通过使用包含2009年至2022年成年患者的449份MRI和568份CT扫描的数据集，能够以非侵入性方式准确识别不同类型的PCNs。该研究结果表明，我们整合临床和影像数据的多模态机器学习算法明显优于单源数据算法。具体而言，它在PCN类型分类方面表现出了领先水平，平均准确率达到91.2%，精确率为91.7%，灵敏度为88.9%，特异性为96.5%。值得注意的是，对于黏液性囊性肿瘤（MCNs）患者，无论接受MRI还是CT成像，该模型的预测准确率均达到100%。这表明我们的非侵入性多模态机器学习模型为MCNs的早期筛查提供了有力支持，代表了PCN诊断在改善临床实践和患者预后方面的重大进展。我们在另一个胰腺癌数据集上也取得了最佳结果，这进一步证明了我们模型的通用性。
