Wan Cai-Feng, Jiang Zhuo-Yun, Wang Yu-Qun, Wang Lin, Fang Hua, Jin Ye, Dong Qi, Zhang Xue-Qing, Jiang Li-Xin
Department of Ultrasound, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200127, PR China (C-f.W., Y-q.W., L.W., H.F., Y.J., Q.D., L-x.J.).
School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, PR China (Z-y.J.).
Acad Radiol. 2025 Apr;32(4):1861-1873. doi: 10.1016/j.acra.2024.11.012. Epub 2024 Dec 16.
To construct and validate a clinical-radiomics model based on radiomics features extracted from two-stage multimodal ultrasound and clinicopathologic information for early predicting pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer patients treated with NAC.
Consecutive women with biopsy-proven breast cancer undergoing multimodal US pretreatment and after two cycles of NAC and followed by surgery between January 2014 and November 2023 were retrospectively collected for clinical-radiomics model construction (n = 274) and retrospective test (n = 134). The predictive performance of it was further tested in a subsequent prospective internal test set recruited between January 2024 to July 2024 (n = 76). Finally, a total of 484 patients were enrolled. The clinical-radiomics model predictive performance was compared with radiomics model, clinical model and radiologists' visual assessment by area under the receiver operating characteristic curve (AUC) analysis and DeLong test.
The proposed clinical-radiomics model obtained the AUC values of 0.92 (95%CI: 0.88, 0.94) and 0.85 (95%CI: 0.79, 0.89) in retrospective and prospective test sets, respectively, which were significantly higher than that those of the radiomics model (AUCs: 0.75-0.85), clinical model (AUCs: 0.68-0.72) and radiologists' visual assessments (AUCs:0.59-0.68) (all p < 0.05). In addition, the predictive efficacy of the radiologists was improved under the assistance of the clinical-radiomics model significantly.
The clinical-radiomics model developed in this study, which integrated clinicopathologic information and two-stage multimodal ultrasound features, was able to early predict pCR to NAC in breast cancer patients with favorable predictive effectiveness.
构建并验证一种临床放射组学模型，该模型基于从两阶段多模态超声提取的放射组学特征以及临床病理信息，用于早期预测接受新辅助化疗（NAC）的乳腺癌患者对新辅助化疗的病理完全缓解（pCR）情况。
回顾性收集2014年1月至2023年11月期间连续的经活检证实为乳腺癌且在新辅助化疗前接受多模态超声检查、新辅助化疗两个周期后并接受手术的女性患者，用于构建临床放射组学模型（n = 274）和进行回顾性测试（n = 134）。其预测性能在2024年1月至2024年7月招募的后续前瞻性内部测试集（n = 76）中进一步测试。最终，共纳入484例患者。通过受试者操作特征曲线（AUC）分析和德龙检验，将临床放射组学模型的预测性能与放射组学模型、临床模型以及放射科医生的视觉评估进行比较。
所提出的临床放射组学模型在回顾性和前瞻性测试集中分别获得了0.92（95%CI：0.88，0.94）和0.85（95%CI：0.79，0.89）的AUC值，显著高于放射组学模型（AUC值：0.75 - 0.85）、临床模型（AUC值：0.68 - 0.72）和放射科医生的视觉评估（AUC值：0.59 - 0.68）（所有p < 0.05）。此外，在临床放射组学模型的辅助下，放射科医生的预测效能显著提高。
本研究开发的临床放射组学模型整合了临床病理信息和两阶段多模态超声特征，能够早期预测乳腺癌患者对新辅助化疗的pCR情况，预测效果良好。
