基于锥光束乳腺CT图像的放射组学模型对乳腺癌新辅助治疗病理完全缓解性的预测价值  

Predictive value of radiomics model based on cone⁃beam breast CT images for pathological complete response of neoadjuvant therapy in breast cancer

作　　者：阳君[1,2,3] 康巍 钟武宁[4] 赵欣 YANG Jun;KANG Wei;ZHONG Wuning;ZHAO Xin(Medical Imaging Center,Guangxi Medical University Cancer Hospital,Nanning 530021,China;Guangxi Key Clinical Specialty(Medical Imaging Department);Dominant Cultivation Discipline of Guangxi Medical University Cancer Hospital(Medical Imaging Department),Nanning 530021,China;Department of the Breast,Bone and Soft Tissue Oncology,Guangxi Medical University Cancer Hospital,Nanning 530021,China)

机构地区：[1]广西医科大学附属肿瘤医院医学影像中心,南宁530021 [2]广西临床重点专科(医学影像科) [3]广西医科大学附属肿瘤医院优势培育学科(医学影像科),南宁530021 [4]广西医科大学附属肿瘤医院乳腺及骨软组织肿瘤内科,南宁530021

出　　处：《中国癌症防治杂志》2025年第1期103-108,共6页CHINESE JOURNAL OF ONCOLOGY PREVENTION AND TREATMENT

基　　金：广西医疗卫生适宜技术开发与推广应用项目(S2021023);广西自然科学基金青年基金项目联合专项(2023GXNSFBA026247);广西影像医学临床医学研究中心建设项目(桂科AD20238096);广西医科大学附属肿瘤医院院内青年基金项目(YQJ2022-2)。

摘　　要：目的探讨基于锥光束乳腺CT(cone-bean breast CT,CBBCT)图像的放射组学模型对乳腺癌新辅助治疗病理完全缓解(pathological complete response,pCR)的预测价值。方法回顾性分析2022年1月至2023年5月于广西医科大学附属肿瘤医院接受新辅助治疗的106例女性乳腺癌患者的CBBCT图像。将患者按8∶2的比例随机分为训练组和测试组。共提取2264个放射组学特征,采用特征筛选器与机器学习分类器交叉组合的方案建立放射组学模型。使用受试者工作特征(receiver operating characteristic,ROC)曲线评估模型的性能,利用决策曲线分析(decision curve analysis,DCA)比较训练组和测试组不同阈值概率下的净收益。结果L2范数正则化-决策树模型在训练组的曲线下面积(area under the curve,AUC)为0.941(95%CI:0.897~0.984),准确率为86.9%,特异度为94.2%,敏感度为75.0%;在测试组的AUC为0.732(95%CI:0.518~0.947),准确率为72.7%,特异度为85.7%,敏感度为50.0%。无论在训练组还是测试组均有最大净收益。结论基于CBBCT图像的L2范数正则化-决策树预测模型在预测乳腺癌新辅助治疗pCR上有较好的性能表现,可为乳腺癌个体化治疗和及时调整化疗方案提供有价值的信息。Objective To investigate the predictive value of radiomics model based on cone⁃beam breast CT(CBBCT)images for pathological complete response(pCR)of neoadjuvant therapy in breast cancer.Methods CBBCT images from 106 female breast cancer patients who underwent neoadjuvant therapy in Guangxi Medical University Cancer Hospital from January 2022 to May 2023 were retrospectively analyzed.The patients were randomly divided into the training group and the validation group at a ratio of 8∶2.A total of 2,264 radiomics features were extracted,and radiomics models were constructed through a cross⁃combination of feature selectors and machine⁃learning classifiers.The performance of the model was assessed using the receiver operating characteristic(ROC)curve,and decision curve analysis(DCA)was applied to evaluate the net benefits at different threshold probabilities between the training and the validation groups.Results The area under the curve(AUC)of L2 norm regularization⁃decision tree model demonstrated strong perfor⁃mance in the training group was 0.941(95%CI:0.897-0.984),accuracy was 86.9%,specificity was 94.2%,and sensitivity was 75.0%.In the validation group,the model achieved an AUC of 0.732(95%CI:0.518⁃0.947),accuracy of 72.7%,specificity of 85.7%,and sensitiv⁃ity of 50.0%.Both the training and validation groups achieved the most net benefit.Conclusions The L2 norm regularization⁃decision tree prediction model based on CBBCT images demonstrates strong performance in predicting pCR of neoadjuvant therapy in breast cancer,which can provide valuable information for individualized treatment and timely adjustments to chemotherapy regimens.

关 键 词：乳腺癌 锥光束乳腺CT 放射组学 新辅助治疗 病理反应性 

分 类 号：R737.9[医药卫生—肿瘤]