卷积神经网络利用乳腺 MRI 肿瘤数据集可预测 OncotypeDx 复发评分。
Convolutional Neural Network Using a Breast MRI Tumor Dataset Can Predict Oncotype Dx Recurrence Score.
机构信息
Breast Imaging Section, Department of Radiology, Columbia University Medical Center, New York, New York, USA.
Department of Radiology, Columbia University Medical Center, New York, New York, USA.
出版信息
J Magn Reson Imaging. 2019 Feb;49(2):518-524. doi: 10.1002/jmri.26244. Epub 2018 Aug 21.
BACKGROUND
Oncotype Dx is a validated genetic analysis that provides a recurrence score (RS) to quantitatively predict outcomes in patients who meet the criteria of estrogen receptor positive / human epidermal growth factor receptor-2 negative (ER+/HER2-)/node negative invasive breast carcinoma. Although effective, the test is invasive and expensive, which has motivated this investigation to determine the potential role of radiomics.
HYPOTHESIS
We hypothesized that convolutional neural network (CNN) can be used to predict Oncotype Dx RS using an MRI dataset.
STUDY TYPE
Institutional Review Board (IRB)-approved retrospective study from January 2010 to June 2016.
POPULATION
In all, 134 patients with ER+/HER2- invasive ductal carcinoma who underwent both breast MRI and Oncotype Dx RS evaluation. Patients were classified into three groups: low risk (group 1, RS <18), intermediate risk (group 2, RS 18-30), and high risk (group 3, RS >30).
FIELD STRENGTH/SEQUENCE: 1.5T and 3.0T. Breast MRI, T postcontrast.
ASSESSMENT
Each breast tumor underwent 3D segmentation. In all, 1649 volumetric slices in 134 tumors (mean 12.3 slices/tumor) were evaluated. A CNN consisted of four convolutional layers and max-pooling layers. Dropout at 50% was applied to the second to last fully connected layer to prevent overfitting. Three-class prediction (group 1 vs. group 2 vs. group 3) and two-class prediction (group 1 vs. group 2/3) models were performed.
STATISTICAL TESTS
A 5-fold crossvalidation test was performed using 80% training and 20% testing. Diagnostic accuracy, sensitivity, specificity, and receiver operating characteristic (ROC) area under the curve (AUC) were evaluated.
RESULTS
The CNN achieved an overall accuracy of 81% (95% confidence interval [CI] ± 4%) in three-class prediction with specificity 90% (95% CI ± 5%), sensitivity 60% (95% CI ± 6%), and the area under the ROC curve was 0.92 (SD, 0.01). The CNN achieved an overall accuracy of 84% (95% CI ± 5%) in two-class prediction with specificity 81% (95% CI ± 4%), sensitivity 87% (95% CI ± 5%), and the area under the ROC curve was 0.92 (SD, 0.01).
DATA CONCLUSION
It is feasible for current deep CNN architecture to be trained to predict Oncotype DX RS.
LEVEL OF EVIDENCE
4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:518-524.
背景
Oncotype DX 是一种经过验证的基因分析方法，可提供复发评分（RS），定量预测符合雌激素受体阳性/人表皮生长因子受体-2 阴性（ER+/HER2-）/淋巴结阴性浸润性乳腺癌标准的患者的结局。虽然有效，但该检测具有侵袭性且昂贵，这促使我们进行了这项研究，以确定放射组学的潜在作用。
假设
我们假设卷积神经网络（CNN）可用于使用 MRI 数据集预测 Oncotype DX RS。
研究类型
2010 年 1 月至 2016 年 6 月，经机构审查委员会（IRB）批准的回顾性研究。
人群
共有 134 名接受过乳腺 MRI 和 Oncotype DX RS 评估的 ER+/HER2-浸润性导管癌患者。患者分为三组：低风险（组 1，RS <18）、中风险（组 2，RS 18-30）和高风险（组 3，RS >30）。
场强/序列：1.5T 和 3.0T。乳腺 MRI，T 造影后。
评估
对每个乳腺肿瘤进行 3D 分割。总共评估了 134 个肿瘤的 1649 个容积切片（平均每个肿瘤 12.3 个切片）。CNN 由四个卷积层和最大池化层组成。在倒数第二层的全连接层中应用 50%的辍学率以防止过拟合。进行了三分类预测（组 1 与组 2 与组 3）和二分类预测（组 1 与组 2/3）。
统计检验
使用 80%的训练数据和 20%的测试数据进行了 5 折交叉验证测试。评估了诊断准确性、敏感性、特异性和接收器工作特征（ROC）曲线下面积（AUC）。
结果
CNN 在三分类预测中的总体准确率为 81%（95%置信区间[CI]±4%），特异性为 90%（95%CI±5%），灵敏度为 60%（95%CI±6%），ROC 曲线下面积为 0.92（SD，0.01）。CNN 在二分类预测中的总体准确率为 84%（95%CI±5%），特异性为 81%（95%CI±4%），灵敏度为 87%（95%CI±5%），ROC 曲线下面积为 0.92（SD，0.01）。
数据结论
目前的深层 CNN 架构可以进行训练，以预测 Oncotype DX RS。
证据水平
4 级技术功效：第 2 阶段 J. Magn. Reson. Imaging 2019;49:518-524.
Zotero 插件