Department of Surgery, City of Hope National Medical Center, 1500 E. Duarte Rd, Furth 1116, Duarte, CA, 91010, USA.
Department of Engineering, Harvey Mudd College, 301 Platt Blvd, Claremont, CA, 91711, USA.
Sci Rep. 2021 Mar 22;11(1):6482. doi: 10.1038/s41598-021-85758-6.
This study addresses the core issue facing a surgical team during breast cancer surgery: quantitative prediction of tumor likelihood including estimates of prediction error. We have previously reported that a molecular probe, Laser Raman spectroscopy (LRS), can distinguish healthy and tumor tissue. We now report that combining LRS with two machine learning algorithms, unsupervised k-means and stochastic nonlinear neural networks (NN), provides rapid, quantitative, probabilistic tumor assessment with real-time error analysis. NNs were first trained on Raman spectra using human expert histopathology diagnostics as gold standard (74 spectra, 5 patients). K-means predictions using spectral data when compared to histopathology produced clustering models with 93.2-94.6% accuracy, 89.8-91.8% sensitivity, and 100% specificity. NNs trained on k-means predictions generated probabilities of correctness for the autonomous classification. Finally, the autonomous system characterized an extended dataset (203 spectra, 8 patients). Our results show that an increase in DNA|RNA signal intensity in the fingerprint region (600-1800 cm) and global loss of high wavenumber signal (2800-3200 cm) are particularly sensitive LRS warning signs of tumor. The stochastic nature of NNs made it possible to rapidly generate multiple models of target tissue classification and calculate the inherent error in the probabilistic estimates for each target.
包括预测误差估计在内的肿瘤可能性的定量预测。我们之前曾报道过，一种分子探针，即激光拉曼光谱（LRS），可以区分健康组织和肿瘤组织。现在我们报告说，将 LRS 与两种机器学习算法，无监督的 k-均值和随机非线性神经网络（NN）相结合，可以快速、定量、概率地评估肿瘤，并实时分析误差。NN 首先使用人类专家组织病理学诊断作为金标准（74 个光谱，5 个患者）对拉曼光谱进行训练。与组织病理学相比，使用光谱数据进行 k-均值预测产生了具有 93.2-94.6%准确率、89.8-91.8%灵敏度和 100%特异性的聚类模型。基于 k-均值预测训练的 NN 生成了自主分类的正确性概率。最后，自主系统对扩展数据集（203 个光谱，8 个患者）进行了特征描述。我们的结果表明，指纹区域（600-1800 cm）中 DNA|RNA 信号强度的增加和高波数信号（2800-3200 cm）的整体损失是 LRS 对肿瘤的特别敏感的预警信号。NN 的随机性使其能够快速生成多个目标组织分类模型，并计算每个目标概率估计的固有误差。
