Abstract：
BACKGROUND: Accurate determination of human epidermal growth factor receptor 2 (HER2) is important for choosing optimal HER2 targeting treatment strategies. HER2-low is currently considered HER2-negative, but patients may be eligible to receive new anti-HER2 drug conjugates.
OBJECTIVE: To use breast MRI BI-RADS features for classifying three HER2 levels, first to distinguish HER2-zero from HER2-low/positive (Task-1), and then to distinguish HER2-low from HER2-positive (Task-2).
METHODS: Retrospective.
METHODS: 621 invasive ductal cancer, 245 HER2-zero, 191 HER2-low, and 185 HER2-positive. For Task-1, 488 cases for training and 133 for testing. For Task-2, 294 cases for training and 82 for testing.
UNASSIGNED: 3.0 T; 3D T1-weighted DCE, short time inversion recovery T2, and single-shot EPI DWI.
RESULTS: Pathological information and BI-RADS features were compared. Random Forest was used to select MRI features, and then four machine learning (ML) algorithms: decision tree (DT), support vector machine (SVM), k-nearest neighbors (k-NN), and artificial neural nets (ANN), were applied to build models.
METHODS: Chi-square test, one-way analysis of variance, and Kruskal-Wallis test were performed. The P values <0.05 were considered statistically significant. For ML models, the generated probability was used to construct the ROC curves.
RESULTS: Peritumoral edema, the presence of multiple lesions and non-mass enhancement (NME) showed significant differences. For distinguishing HER2-zero from non-zero (low + positive), multiple lesions, edema, margin, and tumor size were selected, and the k-NN model achieved the highest AUC of 0.86 in the training set and 0.79 in the testing set. For differentiating HER2-low from HER2-positive, multiple lesions, edema, and margin were selected, and the DT model achieved the highest AUC of 0.79 in the training set and 0.69 in the testing set.
CONCLUSIONS: BI-RADS features read by radiologists from preoperative MRI can be analyzed using more sophisticated feature selection and ML algorithms to build models for the classification of HER2 status and identify HER2-low.
METHODS:
UNASSIGNED: Stage 2.
OBJECTIVE: To use breast MRI BI-RADS features for classifying three HER2 levels, first to distinguish HER2-zero from HER2-low/positive (Task-1), and then to distinguish HER2-low from HER2-positive (Task-2).
METHODS: Retrospective.
METHODS: 621 invasive ductal cancer, 245 HER2-zero, 191 HER2-low, and 185 HER2-positive. For Task-1, 488 cases for training and 133 for testing. For Task-2, 294 cases for training and 82 for testing.
UNASSIGNED: 3.0 T; 3D T1-weighted DCE, short time inversion recovery T2, and single-shot EPI DWI.
RESULTS: Pathological information and BI-RADS features were compared. Random Forest was used to select MRI features, and then four machine learning (ML) algorithms: decision tree (DT), support vector machine (SVM), k-nearest neighbors (k-NN), and artificial neural nets (ANN), were applied to build models.
METHODS: Chi-square test, one-way analysis of variance, and Kruskal-Wallis test were performed. The P values <0.05 were considered statistically significant. For ML models, the generated probability was used to construct the ROC curves.
RESULTS: Peritumoral edema, the presence of multiple lesions and non-mass enhancement (NME) showed significant differences. For distinguishing HER2-zero from non-zero (low + positive), multiple lesions, edema, margin, and tumor size were selected, and the k-NN model achieved the highest AUC of 0.86 in the training set and 0.79 in the testing set. For differentiating HER2-low from HER2-positive, multiple lesions, edema, and margin were selected, and the DT model achieved the highest AUC of 0.79 in the training set and 0.69 in the testing set.
CONCLUSIONS: BI-RADS features read by radiologists from preoperative MRI can be analyzed using more sophisticated feature selection and ML algorithms to build models for the classification of HER2 status and identify HER2-low.
METHODS:
UNASSIGNED: Stage 2.
摘要：
背景：准确测定人表皮生长因子受体2（HER2）对于选择最佳HER2靶向治疗策略很重要。HER2低目前被认为是HER2阴性，但患者可能有资格接受新的抗HER2药物偶联物.
目的：使用乳腺MRIBI-RADS特征对三种HER2水平进行分类，首先区分HER2-零和HER2-低/正（任务-1），然后区分HER2低和HER2阳性（任务2）。
方法：回顾性。
方法：621浸润性导管癌，245HER2-零，191HER2低，和185个HER2阳性。对于Task-1，488个案例用于培训，133个案例用于测试。对于任务2，有294个案例用于培训，82个案例用于测试。
■3.0T；3DT1加权DCE，短时反演恢复T2和单发EPIDWI。
结果：比较了病理信息和BI-RADS特征。随机森林用于选择MRI特征，然后是四种机器学习(ML)算法：决策树(DT)，支持向量机(SVM)，k-最近邻(k-NN)，和人工神经网络(ANN)，用于构建模型。
方法：卡方检验，单向方差分析，并进行了Kruskal-Wallis试验。P值<0.05被认为具有统计学意义。对于ML模型，生成的概率用于构建ROC曲线.
结果：瘤周水肿，多病灶和非肿块强化(NME)的存在存在显著差异.为了区分HER2-零与非零（低+正），多发性病变,水肿,margin,选择肿瘤大小，并且k-NN模型在训练集中达到了0.86的最高AUC，在测试集中达到了0.79。为了区分低HER2和阳性HER2，多发性病变,水肿,并选择了保证金，DT模型在训练集中达到0.79的最高AUC，在测试集中达到0.69。
结论：放射科医师从术前MRI读取的BI-RADS特征可以使用更复杂的特征选择和ML算法进行分析，以建立HER2状态分类模型并识别HER2低。
方法：
■阶段2.
目的：使用乳腺MRIBI-RADS特征对三种HER2水平进行分类，首先区分HER2-零和HER2-低/正（任务-1），然后区分HER2低和HER2阳性（任务2）。
方法：回顾性。
方法：621浸润性导管癌，245HER2-零，191HER2低，和185个HER2阳性。对于Task-1，488个案例用于培训，133个案例用于测试。对于任务2，有294个案例用于培训，82个案例用于测试。
■3.0T；3DT1加权DCE，短时反演恢复T2和单发EPIDWI。
结果：比较了病理信息和BI-RADS特征。随机森林用于选择MRI特征，然后是四种机器学习(ML)算法：决策树(DT)，支持向量机(SVM)，k-最近邻(k-NN)，和人工神经网络(ANN)，用于构建模型。
方法：卡方检验，单向方差分析，并进行了Kruskal-Wallis试验。P值<0.05被认为具有统计学意义。对于ML模型，生成的概率用于构建ROC曲线.
结果：瘤周水肿，多病灶和非肿块强化(NME)的存在存在显著差异.为了区分HER2-零与非零（低+正），多发性病变,水肿,margin,选择肿瘤大小，并且k-NN模型在训练集中达到了0.86的最高AUC，在测试集中达到了0.79。为了区分低HER2和阳性HER2，多发性病变,水肿,并选择了保证金，DT模型在训练集中达到0.79的最高AUC，在测试集中达到0.69。
结论：放射科医师从术前MRI读取的BI-RADS特征可以使用更复杂的特征选择和ML算法进行分析，以建立HER2状态分类模型并识别HER2低。
方法：
■阶段2.
