Deep Learning Applied to Raman Spectroscopy for the Detection of Microsatellite Instability/MMR Deficient Colorectal Cancer.
Deep Learning Applied to Raman Spectroscopy for the Detection of Microsatellite Instability/MMR Deficient Colorectal Cancer.
复制标题
作者：
结直肠癌有几种疾病途径，对患者的监测和治疗方式有影响。一个重要的途径是由负责修复癌前细胞的基因缺陷引起的。检测这些缺陷的方法是存在的，但没有像建议的那样经常实施，可以改进。拉曼光谱是一种可以提供这种改进的技术，在癌症研究的其他领域已经显示出潜力。拉曼数据集的全部潜力可以通过利用现代机器学习模型来实现。我们评估了一个小型结直肠组织数据集，以评估一些常见机器学习技术检测不同结直肠癌途径的可行性。我们发现，拉曼光谱与机器学习相结合可能是一种可行的方法，可以改善筛查和潜在的诊断工具，并保证进一步研究更大的样本量。DNA错配修复缺陷是结直肠癌的致病途径之一。其特征在于微卫星不稳定性，这为其检测提供了分子生物标志物。由于资源限制，这种生物标志物的通用检测的临床指南没有得到满足;因此，人们有兴趣开发新的检测方法。拉曼光谱（RS）是一种分析工具，能够询问样品的分子振动，以提供独特的生化指纹。由此产生的数据集复杂且高维，使其成为深度学习的理想候选者，尽管这可能受到样本量小的限制。这项研究调查了使用RS区分人类结直肠样本中正常微卫星稳定（MSS）和微卫星不稳定（MSI-H）腺癌的潜力，以及深度学习是否比传统机器学习模型更有利于实现这一目标。开发了一种1D卷积神经网络（CNN）来区分人体组织中的健康、MSI-H和MSS，并与主成分分析-线性判别分析（PCA-LDA）和支持向量机（SVM）模型进行了比较。使用嵌套交叉验证策略训练30个样品，每组10个，总共1490个拉曼光谱。与PCA-LDA相比，CNN的灵敏度和特异性分别为83%和45%，PCA-LDA的灵敏度和特异性分别为82%和51%。尽管样本量较低，但这些与现有指南相比具有竞争力，这说明了RS与深度学习相结合的分子鉴别能力。负责这种歧视的生化前因的数量也进行了探讨，与核酸和胶原蛋白相关的拉曼峰被牵连。
Colorectal cancer has several disease pathways which have implications for how patients are monitored and treated. One important pathway is caused by deficiencies to genes responsible for repairing pre-cancerous cells. Methods to detect these deficiencies exist, but are not implemented as often as recommended and could be improved. Raman spectroscopy is a technique that could provide such an improvement, having shown potential in other areas of cancer research. The full potential of Raman datasets may be achieved by exploiting modern machine learning models. We evaluated a small colorectal tissue dataset to assess the viability of some common machine learning techniques to detect different colorectal cancer pathways. We find that Raman spectroscopy in conjunction with machine learning could be a viable means of improving screening and potentially diagnostic tools and warrants further research with larger sample sizes. Defective DNA mismatch repair is one pathogenic pathway to colorectal cancer. It is characterised by microsatellite instability which provides a molecular biomarker for its detection. Clinical guidelines for universal testing of this biomarker are not met due to resource limitations; thus, there is interest in developing novel methods for its detection. Raman spectroscopy (RS) is an analytical tool able to interrogate the molecular vibrations of a sample to provide a unique biochemical fingerprint. The resulting datasets are complex and high-dimensional, making them an ideal candidate for deep learning, though this may be limited by small sample sizes. This study investigates the potential of using RS to distinguish between normal, microsatellite stable (MSS) and microsatellite unstable (MSI-H) adenocarcinoma in human colorectal samples and whether deep learning provides any benefit to this end over traditional machine learning models. A 1D convolutional neural network (CNN) was developed to discriminate between healthy, MSI-H and MSS in human tissue and compared to a principal component analysis–linear discriminant analysis (PCA–LDA) and a support vector machine (SVM) model. A nested cross-validation strategy was used to train 30 samples, 10 from each group, with a total of 1490 Raman spectra. The CNN achieved a sensitivity and specificity of 83% and 45% compared to PCA–LDA, which achieved a sensitivity and specificity of 82% and 51%, respectively. These are competitive with existing guidelines, despite the low sample size, speaking to the molecular discriminative power of RS combined with deep learning. A number of biochemical antecedents responsible for this discrimination are also explored, with Raman peaks associated with nucleic acids and collagen being implicated.
登录
查看更多内容
影响因子：
3
作者：
Gaifulina R;Maher AT;Kendall C;Nelson J;Rodriguez-Justo M;Lau K;Thomas GM
通讯作者：
Thomas GM
基于组织学的人工智能检测微卫星不稳定性和对结直肠癌免疫疗法反应的预测。
影响因子：
5.2
作者：
Hildebrand LA;Pierce CJ;Dennis M;Paracha M;Maoz A
通讯作者：
Maoz A
DOI：
10.1007/s10552-021-01543-w
发表时间：
2022-04
期刊：
Cancer causes & control : CCC
影响因子：
--
作者：
Li H;Sun L;Zhuang Y;Tian C;Yan F;Zhang Z;Hu Y;Liu P
通讯作者：
Liu P
影响因子：
3.6
作者：
Snowsill, Tristan;Coelho, Helen;Hyde, Chris
通讯作者：
Hyde, Chris
影响因子：
78.8
作者：
Bera, Kaustav;Schalper, Kurt A.;Madabhushi, Anant
通讯作者：
Madabhushi, Anant