Ensemble Learning for Breast Cancer Lesion Classification: A Pilot Validation Using Correlated Spectroscopic Imaging and Diffusion-Weighted Imaging.
Ensemble Learning for Breast Cancer Lesion Classification: A Pilot Validation Using Correlated Spectroscopic Imaging and Diffusion-Weighted Imaging.
复制标题
DOI：
10.3390/metabo13070835
复制
发表时间：
2023-07-11
期刊：
影响因子：
4.1
通讯作者：
中科院分区：
文献类型：
--
作者：
这项工作的主要目的是评估个体和集成机器学习模型的应用，以使用从五维回波平面相关光谱成像（5D EP-COSI）和弥散加权成像（DWI）提取的二维（2D）相关光谱光谱的特征对恶性和良性乳腺肿块进行分类。使用24种不同的代谢物和脂质比率作为特征，所述24种不同的代谢物和脂质比率相对于来自2D光谱的对角脂肪峰（1.4 ppm，5.4 ppm）以及来自一维非水抑制（NWS）光谱的水和脂肪峰（4.7 ppm，1.4 ppm）。此外，还包括来自NWS光谱的水分数、脂肪分数和水脂肪比以及来自DWI的表观扩散系数（ADC）。采用递归特征消除、序贯前向选择和相关分析确定了9个最重要的特征。XGBoost（AUC：93.0%，准确度：85.7%，F1评分：88.9%，精密度：88.2%，灵敏度：90.4%，特异性：84.6%）和AUC：94.3%，准确度：89.3%，F1评分：90.7%，精密度：87.9%，灵敏度：94.2%，特异性：83.4%）是表现最好的模型。常规生物标志物如胆碱、肌醇和甘氨酸是统计学显著的预测因子。对分类有贡献的关键特征是ADC，0.9 ppm、2.1 ppm、3.5 ppm和5.4 ppm处的2D对角峰，1.4和0.9 ppm、4.3和4.1 ppm、2.3和1.6 ppm之间的交叉峰，以及肉豆蔻基脂肪交叉峰。结果突出了2D谱峰对模型的贡献，并且它们证明了5D EP-COSI用于早期乳腺癌检测的潜力。
The main objective of this work was to evaluate the application of individual and ensemble machine learning models to classify malignant and benign breast masses using features from two-dimensional (2D) correlated spectroscopy spectra extracted from five-dimensional echo-planar correlated spectroscopic imaging (5D EP-COSI) and diffusion-weighted imaging (DWI). Twenty-four different metabolite and lipid ratios with respect to diagonal fat peaks (1.4 ppm, 5.4 ppm) from 2D spectra, and water and fat peaks (4.7 ppm, 1.4 ppm) from one-dimensional non-water-suppressed (NWS) spectra were used as the features. Additionally, water fraction, fat fraction and water-to-fat ratios from NWS spectra and apparent diffusion coefficients (ADC) from DWI were included. The nine most important features were identified using recursive feature elimination, sequential forward selection and correlation analysis. XGBoost (AUC: 93.0%, Accuracy: 85.7%, F1-score: 88.9%, Precision: 88.2%, Sensitivity: 90.4%, Specificity: 84.6%) and GradientBoost (AUC: 94.3%, Accuracy: 89.3%, F1-score: 90.7%, Precision: 87.9%, Sensitivity: 94.2%, Specificity: 83.4%) were the best-performing models. Conventional biomarkers like choline, myo-Inositol, and glycine were statistically significant predictors. Key features contributing to the classification were ADC, 2D diagonal peaks at 0.9 ppm, 2.1 ppm, 3.5 ppm, and 5.4 ppm, cross peaks between 1.4 and 0.9 ppm, 4.3 and 4.1 ppm, 2.3 and 1.6 ppm, and the triglyceryl–fat cross peak. The results highlight the contribution of the 2D spectral peaks to the model, and they demonstrate the potential of 5D EP-COSI for early breast cancer detection.
登录
查看更多内容
影响因子：
--
作者：
通讯作者：
--
定量弥散加权磁共振成像在乳腺病变鉴别诊断中的Meta分析
影响因子：
3.8
作者：
Chen X;Li WL;Zhang YL;Wu Q;Guo YM;Bai ZL
通讯作者：
Bai ZL
影响因子：
4.7
作者：
Prvulovic Bunovic N;Sveljo O;Kozic D;Boban J
通讯作者：
Boban J
DOI：
10.1002/jmri.25909
发表时间：
2018-07
期刊：
Journal of magnetic resonance imaging : JMRI
影响因子：
--
作者：
Amornsiripanitch N;Nguyen VT;Rahbar H;Hippe DS;Gadi VK;Rendi MH;Partridge SC
通讯作者：
Partridge SC
影响因子：
4.1
作者：
Haukaas TH;Euceda LR;Giskeødegård GF;Bathen TF
通讯作者：
Bathen TF