Department of Pathomorphology, Jagiellonian University Medical College, Grzegorzecka 16, 31-531, Cracow, Poland.
Department of Pathomorphology, University Hospital, Cracow, Poland.
Eur J Nucl Med Mol Imaging. 2023 May;50(6):1792-1810. doi: 10.1007/s00259-023-06121-7. Epub 2023 Feb 9.
Knowledge about pancreatic cancer (PC) biology has been growing rapidly in recent decades. Nevertheless, the survival of PC patients has not greatly improved. The development of a novel methodology suitable for deep investigation of the nature of PC tumors is of great importance. Molecular imaging techniques, such as Fourier transform infrared (FTIR) spectroscopy and Raman hyperspectral mapping (RHM) combined with advanced multivariate data analysis, were useful in studying the biochemical composition of PC tissue.
Here, we evaluated the potential of molecular imaging in differentiating three groups of PC tumors, which originate from different precursor lesions. Specifically, we comprehensively investigated adenocarcinomas (ACs): conventional ductal AC, intraductal papillary mucinous carcinoma, and ampulla of Vater AC. FTIR microspectroscopy and RHM maps of 24 PC tissue slides were obtained, and comprehensive advanced statistical analyses, such as hierarchical clustering and nonnegative matrix factorization, were performed on a total of 211,355 Raman spectra. Additionally, we employed deep learning technology for the same task of PC subtyping to enable automation. The so-called convolutional neural network (CNN) was trained to recognize spectra specific to each PC group and then employed to generate CNN-prediction-based tissue maps. To identify the DNA methylation spectral markers, we used differently methylated, isolated DNA and compared the observed spectral differences with the results obtained from cellular nuclei regions of PC tissues.
The results showed significant differences among cancer tissues of the studied PC groups. The main findings are the varying content of β-sheet-rich proteins within the PC cells and alterations in the relative DNA methylation level. Our CNN model efficiently differentiated PC groups with 94% accuracy. The usage of CNN in the classification task did not require Raman spectral data preprocessing and eliminated the need for extensive knowledge of statistical methodologies.
Molecular spectroscopy combined with CNN technology is a powerful tool for PC detection and subtyping. The molecular fingerprint of DNA methylation and β-sheet cytoplasmic proteins established by our results is different for the main PC groups and allowed the subtyping of pancreatic tumors, which can improve patient management and increase their survival. Our observations are of key importance in understanding the variability of PC and allow translation of the methodology into clinical practice by utilizing liquid biopsy testing.
近几十年来，人们对胰腺癌（PC）生物学的认识迅速增长。然而，PC 患者的生存率并没有显著提高。开发一种适用于深入研究 PC 肿瘤本质的新方法学具有重要意义。分子成像技术，如傅里叶变换红外（FTIR）光谱和拉曼高光谱映射（RHM）结合先进的多元数据分析，在研究 PC 组织的生化组成方面非常有用。
在这里，我们评估了分子成像在区分源自不同前体病变的三组 PC 肿瘤的潜力。具体来说，我们全面研究了腺癌（AC）：传统导管 AC、导管内乳头状黏液性癌和 Vater 壶腹 AC。获得了 24 个 PC 组织切片的 FTIR 微光谱和 RHM 图谱，并对总共 211355 个拉曼光谱进行了综合的高级统计分析，如层次聚类和非负矩阵分解。此外，我们还使用深度学习技术来实现 PC 分型的自动化。所训练的卷积神经网络（CNN）用于识别每个 PC 组特有的光谱，然后用于生成基于 CNN 预测的组织图谱。为了识别 DNA 甲基化光谱标记物，我们使用了不同甲基化的、分离的 DNA，并将观察到的光谱差异与从 PC 组织的细胞核区域获得的结果进行比较。
研究结果表明，所研究的 PC 组的癌症组织之间存在显著差异。主要发现是 PC 细胞中富含β-折叠的蛋白质含量不同，以及相对 DNA 甲基化水平的改变。我们的 CNN 模型能够以 94%的准确率有效地区分 PC 组。在分类任务中使用 CNN 不需要对拉曼光谱数据进行预处理，并且不需要广泛的统计方法学知识。
分子光谱学结合 CNN 技术是 PC 检测和分型的有力工具。我们的结果建立的 DNA 甲基化和细胞质β-折叠蛋白的分子指纹在主要 PC 组中是不同的，并且允许对胰腺肿瘤进行分型，这可以改善患者的管理并提高他们的生存率。我们的观察结果对于理解 PC 的可变性具有重要意义，并允许通过利用液体活检测试将该方法学转化为临床实践。
