Department of Radiotherapy Oncology, Changzhou No. 2 People's Hospital, Nanjing Medical University, Changzhou, China.
Jiangsu Province Engineering Research Center of Medical Physics, Changzhou, China.
Biomed Eng Online. 2024 Nov 21;23(1):117. doi: 10.1186/s12938-024-01315-y.
This study aimed to develop and validate an ultrasound radiomics model for distinguishing invasive ductal carcinoma (IDC) from ductal carcinoma in situ (DCIS) by combining intratumoral and peritumoral features.
Retrospective analysis was performed on 454 patients from Chengzhong Hospital. The patients were randomly divided in accordance with a ratio of 8:2 into a training group (363 cases) and validation group (91 cases). In addition, 175 patients from Yanghu Hospital were used as the external test group. The peritumoral ranges were set to 2, 4, 6, 8, and 10 mm. Mann-Whitney U-test, recursive feature elimination, and a least absolute shrinkage and selection operator were used to in the dimension reduction of the radiomics features and clinical knowledge, and machine learning logistic regression classifiers were utilized to construct the diagnostic model. The area under the curve (AUC) of the receiver operating characteristics, accuracy, sensitivity, and specificity were used to evaluate the model performance.
By combining peritumoral features of different ranges, the AUC of the radiomics model was improved in the validation and test groups. In the validation group, the maximum increase in AUC was 9.7% (P = 0.031, AUC = 0.803) when the peritumoral range was 8 mm. Similarly, when the peritumoral range was only 8 mm in the test group, the maximum increase in AUC was 4.9% (P = 0.005, AUC = 0.770). In this study, the best prediction performance was achieved when the peritumoral range was only 8 mm.
The ultrasound-based radiomics model that combined intratumoral and peritumoral features exhibits good ability to distinguish between IDC and DCIS. The selection of peritumoral range size exerts an important effect on the prediction performance of the radiomics model.
本研究旨在通过联合肿瘤内和肿瘤旁特征，建立并验证一种超声放射组学模型，用于鉴别浸润性导管癌（IDC）与导管原位癌（DCIS）。
回顾性分析来自城中医院的 454 例患者。患者按照 8:2 的比例随机分为训练组（363 例）和验证组（91 例）。此外，来自阳湖医院的 175 例患者被用作外部测试组。肿瘤旁范围设定为 2、4、6、8 和 10mm。采用 Mann-Whitney U 检验、递归特征消除和最小绝对收缩和选择算子对放射组学特征和临床知识进行降维，使用机器学习逻辑回归分类器构建诊断模型。采用受试者工作特征曲线下面积（AUC）、准确性、敏感度和特异度评估模型性能。
通过联合不同范围的肿瘤旁特征，放射组学模型在验证组和测试组中的 AUC 得到提高。在验证组中，当肿瘤旁范围为 8mm 时，AUC 的最大增幅为 9.7%（P=0.031，AUC=0.803）。同样，当测试组中仅肿瘤旁范围为 8mm 时，AUC 的最大增幅为 4.9%（P=0.005，AUC=0.770）。在本研究中，当肿瘤旁范围仅为 8mm 时，达到了最佳预测性能。
联合肿瘤内和肿瘤旁特征的基于超声的放射组学模型具有良好的鉴别 IDC 和 DCIS 的能力。肿瘤旁范围大小的选择对放射组学模型的预测性能有重要影响。
