Department of Radiology, Suzhou Ninth People's Hospital, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, PR China.
Department of Gastroenterology, Suzhou Ninth People's Hospital, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, PR China.
Acta Radiol. 2024 Jun;65(6):554-564. doi: 10.1177/02841851241245970. Epub 2024 Apr 16.
Computed tomography (CT) radiomics combined with deep transfer learning was used to identify cholesterol and adenomatous gallbladder polyps that have not been well evaluated before surgery.
To investigate the potential of various machine learning models, incorporating radiomics and deep transfer learning, in predicting the nature of cholesterol and adenomatous gallbladder polyps.
A retrospective analysis was conducted on clinical and imaging data from 100 patients with cholesterol or adenomatous polyps confirmed by surgery and pathology at our hospital between September 2015 and February 2023. Preoperative contrast-enhanced CT radiomics combined with deep learning features were utilized, and -tests and least absolute shrinkage and selection operator (LASSO) cross-validation were employed for feature selection. Subsequently, 11 machine learning algorithms were utilized to construct prediction models, and the area under the ROC curve (AUC), accuracy, and F1 measure were used to assess model performance, which was validated in a validation group.
The Logistic algorithm demonstrated the most effective prediction in identifying polyp properties based on 10 radiomics combined with deep learning features, achieving the highest AUC (0.85 in the validation group, 95% confidence interval = 0.68-1.0). In addition, the accuracy (0.83 in the validation group) and F1 measure (0.76 in the validation group) also indicated strong performance.
The machine learning radiomics combined with deep learning model based on enhanced CT proves valuable in predicting the characteristics of cholesterol and adenomatous gallbladder polyps. This approach provides a more reliable basis for preoperative diagnosis and treatment of these conditions.
计算机断层扫描（CT）放射组学结合深度迁移学习用于识别术前未得到充分评估的胆固醇和腺瘤性胆囊息肉。
探讨各种机器学习模型，包括放射组学和深度迁移学习，在预测胆固醇和腺瘤性胆囊息肉性质方面的潜力。
对 2015 年 9 月至 2023 年 2 月我院经手术和病理证实的 100 例胆固醇或腺瘤性息肉患者的临床和影像学资料进行回顾性分析。利用术前增强 CT 放射组学结合深度学习特征，并进行 t 检验和最小绝对收缩和选择算子（LASSO）交叉验证进行特征选择。然后，利用 11 种机器学习算法构建预测模型，采用 ROC 曲线下面积（AUC）、准确性和 F1 度量评估模型性能，并在验证组中进行验证。
基于 10 个放射组学结合深度学习特征的 Logistic 算法在识别息肉性质方面表现出最有效的预测，在验证组中获得最高 AUC（0.85，95%置信区间=0.68-1.0）。此外，准确性（验证组 0.83）和 F1 度量（验证组 0.76）也表现出较强的性能。
增强 CT 联合机器学习放射组学和深度学习模型在预测胆固醇和腺瘤性胆囊息肉的特征方面具有较高的应用价值。这种方法为术前诊断和治疗这些疾病提供了更可靠的依据。
