Support vector machine for breast cancer classification using diffusion-weighted MRI histogram features: Preliminary study
Support vector machine for breast cancer classification using diffusion-weighted MRI histogram features: Preliminary study
复制标题
DOI：
10.1002/jmri.25873
复制
发表时间：
2018-05-01
影响因子：
4.4
通讯作者：
Goa, Pal Erik
中科院分区：
文献类型：
--
作者：
Vidic, Igor;Egnell, Liv;Goa, Pal Erik
背景磁共振弥散加权成像（DWI）是目前发展最快的肿瘤MRI技术之一。DWI模型拟合的直方图特性是区分病变的有用特征，机器学习可能会改善分类。目的使用支持向量机（SVM）评估恶性和良性肿瘤以及乳腺癌亚型的分类。研究类型前瞻性研究对象51例良性（n=23）和恶性（n=28）乳腺肿瘤患者（26例ER+，其中6例为HER 2+）。场强/序列患者用DW-MRI（3 T）成像，使用两次重聚焦自旋回波回波回波平面成像，回波时间/重复时间（TR/TE）=9000/86毫秒，90 × 90矩阵大小，2 × 2 mm平面内分辨率，2.5mm切片厚度，计算表观扩散系数（ADC）、相对增强扩散系数（RED）和体素内非相干运动（IVIM）参数扩散系数（D）、伪扩散系数（D*）和灌注分数（f）。直方图的属性（中位数，平均值，标准差，偏度，峰度）被用作SVM（10倍交叉验证）的特征，用于区分病变和亚型。统计测试SVM分类的准确性被计算，以找到具有最高预测准确性的特征组合。Mann-Whitney检验进行单变量comparison.ResultsFor良性与恶性肿瘤，单变量分析发现11直方图属性是显着的差异。使用SVM，从单个特征（RED的平均值）或从IVIM或ADC的三个特征组合实现最高准确度（0.96）。结合所有模型的特征，得到完美的分类。没有单一特征预测ER+肿瘤的HER 2状态（单变量或SVM），尽管SVM结合几个特征实现了高准确度（0.90）。重要的是，这些功能必须包括高阶统计量（峰度和偏度），说明占heterogeneity.Data ConclusionOur的研究结果表明，SVM，使用功能的组合扩散模型，提高预测准确性的良性与恶性乳腺肿瘤的分化，并可能进一步协助分型的乳腺癌。证据等级：3技术有效性：3期J. Magn. Reson。成像2018;47：1205-1216。
BackgroundDiffusion-weighted MRI (DWI) is currently one of the fastest developing MRI-based techniques in oncology. Histogram properties from model fitting of DWI are useful features for differentiation of lesions, and classification can potentially be improved by machine learning.PurposeTo evaluate classification of malignant and benign tumors and breast cancer subtypes using support vector machine (SVM).Study TypeProspective.SUBJECTSFifty-one patients with benign (n=23) and malignant (n=28) breast tumors (26 ER+, whereof six were HER2+).Field Strength/SequencePatients were imaged with DW-MRI (3T) using twice refocused spin-echo echo-planar imaging with echo time / repetition time (TR/TE)=9000/86 msec, 90 x 90 matrix size, 2 x 2mm in-plane resolution, 2.5mm slice thickness, and 13 b-values.AssessmentApparent diffusion coefficient (ADC), relative enhanced diffusivity (RED), and the intravoxel incoherent motion (IVIM) parameters diffusivity (D), pseudo-diffusivity (D*), and perfusion fraction (f) were calculated. The histogram properties (median, mean, standard deviation, skewness, kurtosis) were used as features in SVM (10-fold cross-validation) for differentiation of lesions and subtyping.Statistical TestsAccuracies of the SVM classifications were calculated to find the combination of features with highest prediction accuracy. Mann-Whitney tests were performed for univariate comparisons.ResultsFor benign versus malignant tumors, univariate analysis found 11 histogram properties to be significant differentiators. Using SVM, the highest accuracy (0.96) was achieved from a single feature (mean of RED), or from three feature combinations of IVIM or ADC. Combining features from all models gave perfect classification. No single feature predicted HER2 status of ER+tumors (univariate or SVM), although high accuracy (0.90) was achieved with SVM combining several features. Importantly, these features had to include higher-order statistics (kurtosis and skewness), indicating the importance to account for heterogeneity.Data ConclusionOur findings suggest that SVM, using features from a combination of diffusion models, improves prediction accuracy for differentiation of benign versus malignant breast tumors, and may further assist in subtyping of breast cancer. Level of Evidence: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:1205-1216.