| 11 | 0 | 38 |
| 下载次数 | 被引频次 | 阅读次数 |
目的 开发基于治疗前多参数MRI、超声以及MRI联合超声的影像组学模型，尝试无创预测乳腺癌患者新辅助化疗（NAC）的病理完全缓解（pCR）。方法 回顾性分析219例行NAC的乳腺癌患者。根据病理结果分为pCR组和非pCR组。提取MRI和超声影像组学特征，通过最小绝对收缩与选择算子（LASSO）回归进行特征选择。在训练集（n=159）中构建四种影像组学模型（MRI影像组学模型、超声影像组学模型、MRI联合超声影像组学模型、MRI影像组学联合临床特征模型），并在验证集（n=60）中进行测试。通过逻辑回归分析筛选独立的临床病理预测因子。采用受试者工作特征（ROC）分析和DeLong检验评估模型性能。结果 MRI影像组学模型的曲线下面积（AUC）值显著高于超声影像组学模型（训练集：0.785比0.642,P=0.006；验证集：0.851比0.594,P=0.021）。MRI联合超声影像组学模型与单独MRI影像组学模型性能相当（训练集：0.808比0.785,P=0.674；验证集：0.810比0.851,P=0.646）。与单独MRI影像组学模型相比，MRI影像组学联合临床特征模型在训练集（0.848比0.785,P=0.254）、验证集（0.846比0.851,P=0.953）中均未表现出显著差异的AUC值。结论 多参数MRI影像组学模型在无创预测乳腺癌NAC pCR方面优于超声影像组学模型。与单独使用MRI影像组学模型相比，超声影像组学特征和临床病理特征对NAC疗效的预测并无显著附加价值。
Abstract：Objective To develop radiomics models based on pre-treatment multiparametric MRI, ultrasound(US), and the combination of MRI and US for non-invasive prediction of pathological complete response(pCR)to neoadjuvant chemotherapy(NAC)in patients with breast cancer. Methods A retrospective analysis was conducted on 219 patients, who underwent NAC for breast cancer in our hospital. According to the pathological results, they were divided into the pCR group and the non-PCR group. The radiomics features of MRI and US were extracted and selected through the least absolute shrinkage and selection operator(LASSO)regression technique. The MRI, US, combined MRI and US, and combined MRI and clinical radiomics models were constructed in the training set(n=159)and tested in the independent validation set(n=60). Independent clinicopathological predictors were screened through logistic regression analysis. The performance of the model was evaluated by receiver operating characteristic(ROC) curve analysis and DeLong test. Results The area under the ROC curve(AUC) value of the MRI radiomics model(training set: 0.785,validation set: 0.851) was significantly(P =0.006, P =0.021) higher than that of the US radiomics model(0.642, 0.594). The performance of the combined MRI and US radiomics model(training set: 0.808, validation set: 0.810)was comparable(P=0.674, P=0.646)to that of the MRI radiomics model alone(0.785, 0.851). There were no significant differences(P=0.254, P=0.953)in AUCs of the model combining MRI radiomics features and clinicopathological features(training set: 0.848, validation set 0.846)from that of MRI radiomics model alone(0.785, 0.851). Conclusion Multiparametric MRI radiomics model outperformed US radiomics model for noninvasive prediction of pCR to NAC in breast cancer. The US radiomics features and clinicopathologic features had no significant added value in predicting the treatment effect of NAC compared with the MRI radiomics model alone.
[1]Li Q R, Xia C F, Li H, et al. Disparities in 36 cancers across185 countries:secondary analysis of global cancer statistics[J].Front Med, 2024,18(5):911-920.
[2]Siegel R L, Giaquinto A N, Jemal A. Cancer statistics, 2024[J].CA Cancer J Clin, 2024,74(1):12-49.
[3]中华人民共和国国家卫生健康委员会.乳腺癌诊疗指南（2022年版）[J].中国合理用药探索, 2022,19(10):1-26.
[4]Wankhade D, Gharde P, Dutta S. The current role of neoadjuvant chemotherapy in the management of HER2-positive,triple-negative, and micropapillary breast cancer:a narrative review[J]. Cureus, 2023,15(11):e49742.
[5]Zheng Y Y, Zhang H, Chen H J, et al. Combined morphology and radiomics of intravoxel incoherent movement as a predictive model for the pathologic complete response before neoadjuvant chemotherapy in patients with breast cancer[J]. Front Oncol,2025,15:1452128.
[6]Villacampa G, Navarro V, Matikas A, et al. Neoadjuvant immune checkpoint inhibitors plus chemotherapy in early breast cancer:a systematic review and meta-analysis[J]. JAMA Oncol, 2024, 10(10):1331-1341.
[7]Ji L, Chen X, Qian X Y, et al. Major pathologic response and long-term clinical benefit in hormone receptor-positive, human epidermal growth factor receptor 2-negative breast cancer after neoadjuvant chemotherapy[J]. Breast, 2024,78:103792.
[8]Caracciolo M, Castello A, Urso L, et al. Comparison of MRI vs.[18F]FDG PET/CT for treatment response evaluation of primary breast cancer after neoadjuvant chemotherapy:literature review and future perspectives[J]. J Clin Med, 2023,12(16):5355.
[9]Pesapane F, De Marco P, Rapino A, et al. How radiomics can improve breast cancer diagnosis and treatment[J]. J Clin Med,2023,12(4):1372.
[10]Liu H Q, Lin S Y, Song Y D, et al. Machine learning on MRI radiomic features:identification of molecular subtype alteration in breast cancer after neoadjuvant therapy[J]. Eur Radiol,2023,33(4):2965-2974.
[11]李鸿恩,陈江玲,唐大为,等. ER与HER2状态联合MRI评估乳腺癌新辅助化疗病理完全缓解[J].影像诊断与介入放射学, 2025,34(6):404-412.
[12]Li X, Yan F H. Predictive value of background parenchymal enhancement on breast magnetic resonance imaging for pathological tumor response to neoadjuvant chemotherapy in breast cancers:a systematic review[J]. Cancer Imaging, 2024,24(1):35.
[13]Zhang J, Zhan C A, Zhang C X, et al. Fully automatic classification of breast lesions on multi-parameter MRI using a radiomics model with minimal number of stable, interpretable features[J]. Radiol Med, 2023,128(2):160-170.
[14]Choudhery S, Gomez-Cardona D, Favazza C P, et al. MRI radiomics for assessment of molecular subtype, pathological complete response, and residual cancer burden in breast cancer patients treated with neoadjuvant chemotherapy[J]. Acad Radiol,2022,29(Suppl 1):S145-S154.
[15]James J, Law M, Sengupta S, et al. Assessment of the axilla in women with early-stage breast cancer undergoing primary surgery:a review[J]. World J Surg Oncol, 2024,22(1):127.
[16]Reginelli A, Nardone V, Giacobbe G, et al. Radiomics as a new frontier of imaging for cancer prognosis:a narrative review[J].Diagnostics, 2021,11(10):1796.
[17]Granzier R W Y, Ibrahim A, Primakov S P, et al. MRI-based radiomics analysis for the pretreatment prediction of pathologic complete tumor response to neoadjuvant systemic therapy in breast cancer patients:a multicenter study[J]. Cancers, 2021,13(10):2447.
[18]陈鑫,陈小波,梁演婷,等.基于MRI影像组学的可解释性机器学习模型预测乳腺癌新辅助治疗病理完全缓解[J].临床放射学杂志, 2024,43(10):1666-1672.
[19]G radishar W J, Moran M S, Abraham J, et al. NCCN Guidelines Insights:breast cancer, version 4.2021[J]. J Natl Compr Canc Netw, 2021,19(5):484-493.
[20]Zhang H N, Peng Y. Current biological, pathological and clinical landscape of HER2-low breast cancer[J]. Cancers,2022,15(1):126.
[21]Ogston K N, Miller I D, Payne S, et al. A new histological grading system to assess response of breast cancers to primary chemotherapy:prognostic significance and survival[J]. Breast,2003,12(5):320-327.
[22]Mercado C L. BI-RADS update[J]. Radiol Clin North Am,2014,52(3):481-487.
[23]Peng S Y, Chen L Q, Tao J, et al. Radiomics analysis of multi-phase DCE-MRI in predicting tumor response to neoadjuvant therapy in breast cancer[J]. Diagnostics, 2021, 11(11):2086.
[24]Ponsiglione A M, Angelone F, Amato F, et al. A statistical approach to assess the robustness of radiomics features in the discrimination of mammographic lesions[J]. J Pers Med, 2023,13(7):1104.
[25]张恒,赵彤,张赛,等.基于超声深度学习影像组学的乳腺癌新辅助化疗疗效预测[J].中国医疗设备, 2024,39(4):122-129.
[26]Pesapane F, Rotili A, Botta F, et al. Radiomics of MRI for the prediction of the pathological response to neoadjuvant chemotherapy in breast cancer patients:a single referral centre analysis[J]. Cancers, 2021,13(17):4271.
[27]Shin J, Seo N, Baek S E, et al. MRI radiomics model predicts pathologic complete response of rectal cancer following chemoradiotherapy[J]. Radiology, 2022,303(2):351-358.
[28]Cao Y, Wang X X, Li L, et al. Early prediction of pathologic complete response of breast cancer after neoadjuvant chemotherapy using longitudinal ultrafast dynamic contrastenhanced MRI[J]. Diagn Interv Imaging, 2023, 104(12):605-614.
[29]He C W, Yu T H, Yang L, et al. Clinical prediction of pathological complete response in breast cancer:a machine learning study[J]. BMC Cancer, 2025,25(1):933.
基本信息:
中图分类号:R737.9;R445
引用信息:
[1]张奕伟,郑少燕,汪丹凤,等.多参数MRI和超声影像组学模型在预测乳腺癌新辅助化疗病理完全缓解中的应用[J].影像诊断与介入放射学,2026,35(03):202-210.
基金信息:
广东省医学科研基金立项项目（B2023426）
2026-06-25
2026-06-25