基于深度学习的MVIT-MLKA模型用于胰腺病变准确分类:一项多中心回顾性队列研究
本研究基于三个医疗中心864例经组织病理学确诊的胰腺病变患者基线CT图像,开发并验证了一种新型深度学习网络MVIT-MLKA,用于区分良恶性胰腺病变。模型在训练集、内部测试集和外部验证集的AUC分别为0.974、0.935和0.924,优于传统机器学习和其他深度学习模型(P<0.05)。放射科医生在模型辅助下诊断准确度和敏感度显著提高(P<0.05),Grad-CAM可视化可有效突出关键病变区域。
要点
- MVIT-MLKA模型在外部验证集分类良恶性胰腺病变的AUC为0.924(95%CI 0.902-0.945)。
- 放射科医生借助该模型后诊断准确度和敏感度较无辅助时显著提高(P<0.05)。
- Grad-CAM可视化可有效突出关键病变区域,增强模型可解释性。
核心结论
- MVIT-MLKA模型能有效区分良恶性胰腺病变,性能优于传统方法和其他深度学习模型,并显著提高放射科医生的诊断表现,作者认为将其整合入临床实践有潜力减少诊断错误并优化治疗策略。
研究设计与样本
- 多中心回顾性队列研究,纳入三个医疗中心864例(男422例、女442例)经组织病理学确诊的胰腺病变患者,构建训练队列、内部测试队列和外部验证队列,基于基线CT图像开发整合CNN与Transformer架构的MVIT-MLKA模型,并与传统机器学习方法及先进深度学习模型比较。
关键影像表现/征象
- Grad-CAM可视化显示模型能有效突出关键病变区域,增强可解释性。
诊断标准与关键数值
- MVIT-MLKA模型分类胰腺病变的AUC在训练集为0.974(95%CI 0.967-0.980)。
- MVIT-MLKA模型分类胰腺病变的AUC在内部测试集为0.935(95%CI 0.915-0.954)。
- MVIT-MLKA模型分类胰腺病变的AUC在外部验证集为0.924(95%CI 0.902-0.945)。
- MVIT-MLKA模型性能优于传统模型和其他深度学习模型(P<0.05)。
- 放射科医生在MVIT-MLKA模型辅助下诊断准确度和敏感度较无辅助时显著提高(P<0.05)。
临床应用与阅片要点
- 作者认为将该深度学习模型整合入临床实践有潜力减少诊断错误并优化治疗策略。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Accurate differentiation between benign and malignant pancreatic lesions is critical for effective patient management. This study aimed to develop and validate a novel deep learning network using baseline computed tomography (CT) images to predict the classification of pancreatic lesions.
METHODS: This retrospective study included 864 patients (422 men, 442 women) with confirmed histopathological results across three medical centers, forming a training cohort, internal testing cohort, and external validation cohort. A novel hybrid model, Multi-Scale Large Kernel Attention with Mobile Vision Transformer (MVIT-MLKA), was developed, integrating CNN and Transformer architectures to classify pancreatic lesions. The model's performance was compared with traditional machine learning methods and advanced deep learning models. We also evaluated the diagnostic accuracy of radiologists with and without the assistance of the optimal model. Model performance was assessed through discrimination, calibration, and clinical applicability.
RESULTS: The MVIT-MLKA model demonstrated superior performance in classifying pancreatic lesions, achieving an AUC of 0.974 (95% CI 0.967-0.980) in the training set, 0.935 (95% CI 0.915-0.954) in the internal testing set, and 0.924 (95% CI 0.902-0.945) in the external validation set, outperforming traditional models and other deep learning models (P < 0.05). Radiologists aided by the MVIT-MLKA model showed significant improvements in diagnostic accuracy and sensitivity compared to those without model assistance (P < 0.05). Grad-CAM visualization enhanced model interpretability by effectively highlighting key lesion areas.
CONCLUSION: The MVIT-MLKA model efficiently differentiates between benign and malignant pancreatic lesions, surpassing traditional methods and significantly improving radiologists' diagnostic performance. The integration of this advanced deep learning model into clinical practice has the potential to reduce diagnostic errors and optimize treatment strategies.
引用
- Liao H, Huang C, Liu C, et al. Deep learning-based MVIT-MLKA model for accurate classification of pancreatic lesions: a multicenter retrospective cohort study. Radiol Med. 2025. PMID: 39832039. doi:10.1007/s11547-025-01949-5
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。