Liu Jun, Wu Huanhua, Ren Dabin, Huang Hao, Chen Xinyue, Liu Liqiu, Wang Yongtao, Wang Guoyu
Taizhou Central Hospital, Taizhou, China.
The Affiliated Shunde Hospital of Jinan University, Foshan, China.
Abdom Radiol (NY). 2025 Apr 3. doi: 10.1007/s00261-025-04921-z.
This study aimed to preoperatively predict Ki-67 proliferation levels in patients with pancreatic solid pseudopapillary neoplasm (pSPN) using radiomics features extracted from arterial phase helical CT images.
We retrospectively analyzed 92 patients (Ningbo Medical Center Lihuili Hospital: n = 64, Taizhou Central Hospital: n = 28) with pathologically confirmed pSPN from June 2015 to June 2023. Ki-67 positivity > 3% was considered high. Radiomics features were extracted using PyRadiomics, with patients from training cohort (n = 64) and validation cohort (n = 28). A radiomics signature was constructed, and a CT radiomics score (CTscore) was calculated. Deep learning models were employed for prediction, with early stopping to prevent overfitting.
Seven key radiomics features were selected via LASSO regression with cross-validation. The deep learning model demonstrated improved accuracy with demographics and CTscore, with key features such as Morphology and CTscore contributing significantly to predictive accuracy. The best-performing models, including GBM and deep learning algorithms, achieved high predictive performance with an AUC of up to 0.946 in the training cohort.
We developed a robust deep learning-based radiomics model using arterial phase CT images to predict Ki-67 levels in pSPN patients, identifying CTscore and Morphology as key predictors. This non-invasive approach has potential utility in guiding personalized preoperative treatment strategies.
Not applicable.
本研究旨在利用从动脉期螺旋CT图像中提取的放射组学特征，术前预测胰腺实性假乳头状瘤（pSPN）患者的Ki-67增殖水平。
我们回顾性分析了2015年6月至2023年6月期间92例经病理证实的pSPN患者（宁波医疗中心李惠利医院：n = 64，台州中心医院：n = 28）。Ki-67阳性>3%被视为高表达。使用PyRadiomics从训练队列（n = 64）和验证队列（n = 28）的患者中提取放射组学特征。构建放射组学特征，并计算CT放射组学评分（CTscore）。采用深度学习模型进行预测，并采用早期停止法防止过拟合。
通过LASSO回归和交叉验证选择了7个关键放射组学特征。深度学习模型在纳入人口统计学数据和CTscore后显示出更高的准确性，其中形态学和CTscore等关键特征对预测准确性有显著贡献。包括GBM和深度学习算法在内的表现最佳的模型在训练队列中实现了高达0.946的AUC，具有较高的预测性能。
我们开发了一种基于深度学习的强大放射组学模型，利用动脉期CT图像预测pSPN患者的Ki-67水平，确定CTscore和形态学为关键预测因素。这种非侵入性方法在指导个性化术前治疗策略方面具有潜在应用价值。
不适用。
