PO.BCS02.04 · 生物信息与计算
利用治疗前MRI评估乳腺癌复发风险：一项基于多中心数据的迁移学习研究
Assessing the risk of breast cancer recurrence with pre-treatment MRI: A transfer learning study on multicenter data
作者与单位 Authors & Affiliations
摘要 Abstract
中文摘要
背景：MRI特征在预测未来乳腺癌复发方面已显示出预后价值。然而，深度学习相关研究仍然有限，尤其是在大型多中心数据集中评估其在不同肿瘤亚型和不同时间跨度下表现的研究。
材料与方法：我们使用来自多中心MAMA-MIA数据集的治疗前DCE-MRI检查（433例接受新辅助治疗（NAT）的乳腺癌患者；其中115例发生复发事件，318例无复发），以评估一个基于DenseNet121（在ImageNet上预训练）的迁移学习框架。含肿瘤的中间层面图像经过偏置场校正、重采样、裁剪至肿瘤区域，并调整尺寸至224×224像素。解冻DenseNet121顶部10%的层，用于模型微调以进行复发预测。五折分层交叉验证在各数据划分中保留了中心分布。模型性能采用Harrell's C-index以及3年和5年时间跨度的时间依赖性AUC进行评估。相关C-index之间的比较采用双侧Kang等人检验。我们还评估了深度学习风险评分相对于基于既定临床因素HR和HER2的基线预后模型所增加的价值。此外，还评估了模型在不同肿瘤亚型中的表现。
结果：我们的深度学习模型取得了0.67±0.03的C-index，3年和5年AUC分别为0.69±0.04和0.67±0.10。将深度学习风险评分加入基线模型后，性能从0.64显著提升至0.71（p=0.007）。亚型特异性评估（表1）显示表现不一，其中在HER2-pure和TNBC患者中表现最佳。
结论：我们的研究结果凸显了基于迁移学习的DenseNet121 MRI模型预测乳腺癌患者3年和5年复发的潜力，其价值超越了标准临床因素。未来的优化将着眼于在大型多中心数据集中改善亚型特异性表现。表1. 多中心MAMA-MIA数据集（N = 433）无复发生存分析结果。我们的深度学习模型所增加的预后价值：模型 C-index p值* DL模型 0.67 ± 0.03 0.01 基线模型（HR、HER2）0.64 ± 0.05 不适用 基线 + DL 0.71 ± 0.05 0.007 * p值为相对于基线模型的C-index差异。我们的深度学习模型按时间跨度的表现：3年AUC 0.69 ± 0.04 5年AUC 0.67 ± 0.10 我们的深度学习模型按乳腺癌亚型的表现：C-index 3年AUC 5年AUC Luminal A（N = 121）0.61±0.02 0.61±0.11 0.64±0.08 Luminal B（N = 50）0.67±0.13 0.62±0.09 0.57±0.07 TNBC（N = 120）0.70±0.04 0.72±0.03 0.72±0.15 HER2-enriched（N = 65）0.65±0.16 0.59±0.19 0.68±0.28 HER2-pure（N = 56）0.82±0.11 0.86±0.13 0.90±0.20
查看英文原文 English abstract
Background: MRI features have demonstrated prognostic value in predicting future breast cancer recurrence. However, deep learning studies remain limited particularly those evaluating performance across tumor subtypes and different time horizons in large multicenter datasets.
Materials and Methods: We used pretreatment DCE-MRI exams from the multicenter MAMA-MIA dataset (433 breast cancer patients who underwent NAT; 115 with recurrence events, 318 recurrence-free) to evaluate a transfer-learning framework based on DenseNet121 pretrained on ImageNet. Middle tumor-containing slices were bias-field corrected, resampled, cropped to the tumor regions, and resized to 224×224 pixels. The top 10% of DenseNet121 layers were unfrozen for model fine-tuning for recurrence prediction. Five-fold stratified cross-validation preserved site distribution across data splits. Model performance was evaluated using Harrell's C-index and time-dependent AUCs at 3 and 5 year horizons. Correlated C-indices were compared using the two-sided Kang et al. test. We also assessed the added value by our deep-learning risk score to a baseline prognostic model based on the established clinical factors HR and HER2. Model performance was also assessed across tumor subtypes.
Results: Our deep learning model achieved a C-index of 0.67±0.03 with 3 and 5 year AUCs of 0.69±0.04 and 0.67±0.10, respectively. Adding our deep-learning risk score to the baseline model significantly improved performance from 0.64 to 0.71 (p=0.007). Subtype-specific evaluations (Table 1) showed variable performances with the highest performance in HER2-pure and TNBC patients.
Conclusion: Our findings highlight the potential of a transfer-learning-based DenseNet121 MRI model to predict 3 and 5 year recurrences in breast cancer patients, providing added value beyond standard clinical factors. Future optimizations will aim at improving subtype-specific performance in large multicenter datasets. Table 1. Recurrence-free survival analysis results in multi-center MAMA-MIA dataset (N = 433). Added prognostic value by our deep learning model Model C-index p-value* DL model 0.67 ± 0.03 0.01 Baseline model (HR, HER2) 0.64 ± 0.05 N/A Baseline + DL 0.71 ± 0.05 0.007 * p-value for C-index differences with respect to the baseline model. Performance of our deep learning model by time horizon 3-year AUC 0.69 ± 0.04 5-year AUC 0.67 ± 0.10 Performance of our deep learning model by breast cancer subtype C-index 3-year AUC 5-year AUC Luminal A (N = 121) 0.61±0.02 0.61±0.11 0.64±0.08 Luminal B (N = 50) 0.67±0.13 0.62±0.09 0.57±0.07 TNBC (N = 120) 0.70±0.04 0.72±0.03 0.72±0.15 HER2-enriched (N = 65) 0.65±0.16 0.59±0.19 0.68±0.28 Her2-pure (N = 56) 0.82±0.11 0.86±0.13 0.90±0.20
利益披露 Disclosure
K. Bhalla, None..
A. Sanchez, None..
J. M. Luna, None..
T. Ahmad, None..
D. L. Bennett, None..
A. A. Davis, None..
A. Gastounioti, None.