Choi Seoyun, Lee Youngmi, Lee Minwoo, Byon Jung Hee, Choi Eun Jung
Department of Radiology, Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research Institute of Jeonbuk National University Hospital, Jeonbuk National University Medical School, Jeonju 54907, Republic of Korea.
Department of Statistics, Institute of Applied Statistics, Jeonbuk National University, Jeonju 54896, Republic of Korea.
Diagnostics (Basel). 2025 Jul 29;15(15):1895. doi: 10.3390/diagnostics15151895.
To develop a DL-based model predicting recurrence risk in HER2-low breast cancer patients and to compare performance of the MRI-alone, clinicopathologic-alone, and combined models. We analyzed 453 patients with HER2-low breast cancer who underwent surgery and preoperative breast MRI between May 2018 and April 2022. Patients were randomly assigned to either a training cohort ( = 331) or a test cohort ( = 122). Imaging features were extracted from DCE-MRI and ADC maps, with regions of interest manually annotated by radiologists. Clinicopathological features included tumor size, nodal status, histological grade, and hormone receptor status. Three DL prediction models were developed: a CNN-based MRI-alone model, a clinicopathologic-alone model based on a multi-layer perceptron (MLP) and a combined model integrating CNN-extracted MRI features with clinicopathological data via MLP. Model performance was evaluated using AUC, sensitivity, specificity, and F1-score. The MRI-alone model achieved an AUC of 0.69 (95% CI, 0.68-0.69), with a sensitivity of 37.6% (95% CI, 35.7-39.4), specificity of 87.5% (95% CI, 86.9-88.2), and F1-score of 0.34 (95% CI, 0.33-0.35). The clinicopathologic-alone model yielded the highest AUC of 0.92 (95% CI, 0.92-0.92) and sensitivity of 93.6% (95% CI, 93.4-93.8), but showed the lowest specificity (72.3%, 95% CI, 71.8-72.8) and F1-score of 0.50 (95% CI, 0.49-0.50). The combined model demonstrated the most balanced performance, achieving an AUC of 0.90 (95% CI, 0.89-0.91), sensitivity of 80.0% (95% CI, 78.7-81.3), specificity of 83.2% (95% CI: 82.7-83.6), and the highest F1-score of 0.55 (95% CI, 0.54-0.57). The DL-based model combining MRI and clinicopathological features showed superior performance in predicting recurrence in HER2-low breast cancer. This multimodal approach offers a framework for individualized risk assessment and may aid in refining follow-up strategies.
开发一种基于深度学习的模型来预测HER2低表达乳腺癌患者的复发风险，并比较仅使用MRI、仅使用临床病理特征以及两者结合的模型的性能。我们分析了2018年5月至2022年4月期间接受手术和术前乳腺MRI检查的453例HER2低表达乳腺癌患者。患者被随机分配到训练队列（n = 331）或测试队列（n = 122）。从动态对比增强MRI（DCE-MRI）和表观扩散系数（ADC）图中提取影像特征，感兴趣区域由放射科医生手动标注。临床病理特征包括肿瘤大小、淋巴结状态、组织学分级和激素受体状态。开发了三种深度学习预测模型：基于卷积神经网络（CNN）的仅MRI模型、基于多层感知器（MLP）的仅临床病理模型以及通过MLP将CNN提取的MRI特征与临床病理数据相结合的联合模型。使用曲线下面积（AUC）、灵敏度、特异度和F1分数评估模型性能。仅MRI模型的AUC为0.69（95%置信区间，0.68 - 0.69），灵敏度为37.6%（95%置信区间，35.7 - 39.4），特异度为87.5%（95%置信区间，86.9 - 88.2），F1分数为0.34（95%置信区间，0.33 - 0.35）。仅临床病理模型的AUC最高，为0.92（95%置信区间，0.92 - 0.92），灵敏度为93.6%（95%置信区间，93.4 - 93.8），但特异度最低（72.3%，95%置信区间，71.8 - 72.8），F1分数为0.50（95%置信区间，0.49 - 0.50）。联合模型表现出最平衡的性能，AUC为0.90（95%置信区间，0.89 - 0.91），灵敏度为80.0%（95%置信区间，78.7 - 81.3），特异度为83.2%（95%置信区间：82.7 - 83.6），F1分数最高，为0.55（95%置信区间，0.54 - 0.57）。基于深度学习的结合MRI和临床病理特征的模型在预测HER2低表达乳腺癌复发方面表现出卓越性能。这种多模态方法为个性化风险评估提供了一个框架，并可能有助于优化随访策略。
