■我们先前的研究表明,拉曼光谱可以以良好的灵敏度和特异性用于皮肤癌检测。这项研究的目的是确定是否可以通过结合深度神经网络和拉曼光谱来进一步改善皮肤癌检测。
■本研究包括731个皮肤病变的拉曼光谱,包含340个癌性和癌前病变(黑色素瘤,基底细胞癌,鳞状细胞癌和光化性角化病)和391个良性病变(黑素细胞痣和脂溢性角化病)。开发了一维卷积神经网络(1D-CNN)用于拉曼光谱分类。分层抽样随机分为训练(70%),验证(10%)和测试集(20%),并使用并行计算重复56次。对训练数据集实施了不同的数据增强策略,包括增加的随机噪声,光谱位移,使用一维生成对抗网络(1D-GAN)的光谱组合和人工合成拉曼光谱。使用接受者工作特征曲线下面积(ROCAUC)作为诊断性能的量度。传统的机器学习方法,包括用于判别分析的偏最小二乘(PLS-DA),主成分和线性判别分析(PC-LDA),支持向量机(SVM),和逻辑回归(LR)进行了评估,以与1D-CNN相同的数据拆分方案进行比较。
■基于原始训练光谱的测试数据集的ROCAUC为0.886±0.022(1D-CNN),0.870±0.028(PLS-DA),0.875±0.033(PC-LDA),0.864±0.027(SVM),和0.525±0.045(LR),改进为0.909±0.021(1D-CNN),0.899±0.022(PLS-DA),0.895±0.022(PC-LDA),0.901±0.020(SVM),训练数据集扩增后分别为0.897±0.021(LR)(p<0.0001,Wilcoxon检验)。1D-CNN与传统机器学习方法的配对分析表明,1D-CNN有1-3%的改善(p<0.001,Wilcoxon检验)。
■数据增强不仅使深度神经网络和传统机器学习技术的性能提高了2-4%,而且还提高了模型在具有较高噪声或光谱偏移的光谱上的性能。卷积神经网络在通过拉曼光谱检测皮肤癌方面略微优于传统的机器学习方法。
UNASSIGNED: Our previous studies have demonstrated that Raman spectroscopy could be used for skin cancer detection with good sensitivity and specificity. The objective of this study is to determine if skin cancer detection can be further improved by combining deep neural networks and Raman spectroscopy.
UNASSIGNED: Raman spectra of 731 skin lesions were included in this study, containing 340 cancerous and precancerous lesions (melanoma, basal cell carcinoma, squamous cell carcinoma and actinic keratosis) and 391 benign lesions (melanocytic nevus and seborrheic keratosis). One-dimensional convolutional neural networks (1D-CNN) were developed for Raman spectral classification. The stratified samples were divided randomly into training (70%), validation (10%) and test set (20%), and were repeated 56 times using parallel computing. Different data augmentation strategies were implemented for the training dataset, including added random noise, spectral shift, spectral combination and artificially synthesized Raman spectra using one-dimensional generative adversarial networks (1D-GAN). The area under the receiver operating characteristic curve (ROC AUC) was used as a measure of the diagnostic performance. Conventional machine learning approaches, including partial least squares for discriminant analysis (PLS-DA), principal component and linear discriminant analysis (PC-LDA), support vector machine (SVM), and logistic regression (LR) were evaluated for comparison with the same data splitting scheme as the 1D-CNN.
UNASSIGNED: The ROC AUC of the test dataset based on the original training spectra were 0.886±0.022 (1D-CNN), 0.870±0.028 (PLS-DA), 0.875±0.033 (PC-LDA), 0.864±0.027 (SVM), and 0.525±0.045 (LR), which were improved to 0.909±0.021 (1D-CNN), 0.899±0.022 (PLS-DA), 0.895±0.022 (PC-LDA), 0.901±0.020 (SVM), and 0.897±0.021 (LR) respectively after augmentation of the training dataset (p<0.0001, Wilcoxon test). Paired analyses of 1D-CNN with conventional machine learning approaches showed that 1D-CNN had a 1-3% improvement (p<0.001, Wilcoxon test).
UNASSIGNED: Data augmentation not only improved the performance of both deep neural networks and conventional machine learning techniques by 2-4%, but also improved the performance of the models on spectra with higher noise or spectral shifting. Convolutional neural networks slightly outperformed conventional machine learning approaches for skin cancer detection by Raman spectroscopy.