Imaging Center, Harbin Medical University Cancer Hospital, Harbin, China.
Division of Respiratory Disease, Fourth Affiliated Hospital of Harbin Medical University, Harbin, China.
J Magn Reson Imaging. 2024 Apr;59(4):1425-1435. doi: 10.1002/jmri.28895. Epub 2023 Jul 5.
Dynamic contrast-enhanced (DCE) MRI commonly outperforms diffusion-weighted (DW) MRI in breast cancer discrimination. However, the side effects of contrast agents limit the use of DCE-MRI, particularly in patients with chronic kidney disease.
To develop a novel deep learning model to fully exploit the potential of overall b-value DW-MRI without the need for a contrast agent in predicting breast cancer molecular subtypes and to evaluate its performance in comparison with DCE-MRI.
Prospective.
486 female breast cancer patients (training/validation/test: 64%/16%/20%).
FIELD STRENGTH/SEQUENCE: 3.0 T/DW-MRI (13 b-values) and DCE-MRI (one precontrast and five postcontrast phases).
The breast cancers were divided into four subtypes: luminal A, luminal B, HER2+, and triple negative. A channel-dimensional feature-reconstructed (CDFR) deep neural network (DNN) was proposed to predict these subtypes using pathological diagnosis as the reference standard. Additionally, a non-CDFR DNN (NCDFR-DNN) was built for comparative purposes. A mixture ensemble DNN (ME-DNN) integrating two CDFR-DNNs was constructed to identify subtypes on multiparametric MRI (MP-MRI) combing DW-MRI and DCE-MRI.
Model performance was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Model comparisons were performed using the one-way analysis of variance with least significant difference post hoc test and the DeLong test. P < 0.05 was considered significant.
The CDFR-DNN (accuracies, 0.79 ~ 0.80; AUCs, 0.93 ~ 0.94) demonstrated significantly improved predictive performance than the NCDFR-DNN (accuracies, 0.76 ~ 0.78; AUCs, 0.92 ~ 0.93) on DW-MRI. Utilizing the CDFR-DNN, DW-MRI attained the predictive performance equal (P = 0.065 ~ 1.000) to DCE-MRI (accuracies, 0.79 ~ 0.80; AUCs, 0.93 ~ 0.95). The predictive performance of the ME-DNN on MP-MRI (accuracies, 0.85 ~ 0.87; AUCs, 0.96 ~ 0.97) was superior to those of both the CDFR-DNN and NCDFR-DNN on either DW-MRI or DCE-MRI.
The CDFR-DNN enabled overall b-value DW-MRI to achieve the predictive performance comparable to DCE-MRI. MP-MRI outperformed DW-MRI and DCE-MRI in subtype prediction.
2 TECHNICAL EFFICACY STAGE: 1.
动态对比增强（DCE）MRI 在乳腺癌鉴别方面通常优于弥散加权（DW）MRI。然而，造影剂的副作用限制了 DCE-MRI 的使用，特别是在慢性肾病患者中。
开发一种新的深度学习模型，充分利用整体 b 值 DW-MRI 的潜力，无需造影剂即可预测乳腺癌分子亚型，并评估其与 DCE-MRI 相比的性能。
前瞻性。
486 名女性乳腺癌患者（训练/验证/测试：64%/16%/20%）。
磁场强度/序列：3.0T/DW-MRI（13 个 b 值）和 DCE-MRI（一个预对比和五个后对比相）。
将乳腺癌分为四种亚型：管腔 A、管腔 B、HER2+和三阴性。提出了一种通道维度特征重建（CDFR）深度神经网络（DNN），使用病理诊断作为参考标准来预测这些亚型。此外，还构建了一个非 CDFR-DNN（NCDFR-DNN）进行比较。构建了一个混合集成 DNN（ME-DNN），将 DW-MRI 和 DCE-MRI 结合起来，对多参数 MRI（MP-MRI）进行亚型识别。
使用准确性、敏感度、特异性和接收器工作特征曲线下的面积（AUC）评估模型性能。使用单向方差分析和最小显著差异事后检验以及 DeLong 检验进行模型比较。P<0.05 被认为具有统计学意义。
CDFR-DNN（准确率，0.790.80；AUC，0.930.94）在 DW-MRI 上表现出比 NCDFR-DNN（准确率，0.760.78；AUC，0.920.93）显著改善的预测性能。利用 CDFR-DNN，DW-MRI 达到了与 DCE-MRI 相当的预测性能（P=0.0651.000）（准确率，0.790.80；AUC，0.930.95）。ME-DNN 在 MP-MRI 上的预测性能（准确率，0.850.87；AUC，0.96~0.97）优于 CDFR-DNN 和 NCDFR-DNN 在 DW-MRI 或 DCE-MRI 上的预测性能。
CDFR-DNN 使整体 b 值 DW-MRI 能够实现与 DCE-MRI 相当的预测性能。MP-MRI 在亚型预测方面优于 DW-MRI 和 DCE-MRI。
2 技术功效阶段：1。
