Bruker Daltonics GmbH & Co KG, Fahrenheitstrasse 4, 28359 Bremen, Germany.
Institute of Pathology, School of Medicine, Technical University of Munich, Trogerstrasse 18, 81675 München, Germany.
Anal Chem. 2022 Jun 14;94(23):8194-8201. doi: 10.1021/acs.analchem.2c00097. Epub 2022 Jun 6.
Many studies have demonstrated that tissue phenotyping (tissue typing) based on mass spectrometric imaging data is possible; however, comprehensive studies assessing variation and classifier transferability are largely lacking. This study evaluated the generalization of tissue classification based on Matrix Assisted Laser Desorption/Ionization (MALDI) mass spectrometric imaging (MSI) across measurements performed at different sites. Sections of a tissue microarray (TMA) consisting of different formalin-fixed and paraffin-embedded (FFPE) human tissue samples from different tumor entities (leiomyoma, seminoma, mantle cell lymphoma, melanoma, breast cancer, and squamous cell carcinoma of the lung) were prepared and measured by MALDI-MSI at different sites using a standard protocol (SOP). Technical variation was deliberately introduced on two separate measurements via a different sample preparation protocol and a MALDI Time of Flight mass spectrometer that was not tuned to optimal performance. Using standard data preprocessing, a classification accuracy of 91.4% per pixel was achieved for intrasite classifications. When applying a leave-one-site-out cross-validation strategy, accuracy per pixel over sites was 78.6% for the SOP-compliant data sets and as low as 36.1% for the mistuned instrument data set. Data preprocessing designed to remove technical variation while retaining biological information substantially increased classification accuracy for all data sets with SOP-compliant data sets improved to 94.3%. In particular, classification accuracy of the mistuned instrument data set improved to 81.3% and from 67.0% to 87.8% per pixel for the non-SOP-compliant data set. We demonstrate that MALDI-MSI-based tissue classification is possible across sites when applying histological annotation and an optimized data preprocessing pipeline to improve generalization of classifications over technical variation and increasing overall robustness.
许多研究表明，基于质谱成像数据的组织表型（组织分型）是可行的；然而，全面评估变异性和分类器可转移性的研究还很少。本研究评估了基于基质辅助激光解吸/电离（MALDI）质谱成像（MSI）的组织分类在不同地点进行测量时的泛化能力。使用标准方案（SOP）在不同地点通过 MALDI-MSI 对由不同肿瘤实体（平滑肌瘤、精原细胞瘤、套细胞淋巴瘤、黑色素瘤、乳腺癌和肺鳞状细胞癌）的不同福尔马林固定和石蜡包埋（FFPE）人组织样本组成的组织微阵列（TMA）的切片进行制备和测量。通过使用不同的样品制备方案和未调谐至最佳性能的 MALDI 飞行时间质谱仪，在两次单独测量中故意引入技术变异性。使用标准数据预处理，在内部站点分类中，每个像素的分类准确率达到 91.4%。当应用一种离开一个站点的交叉验证策略时，符合 SOP 的数据集的每个像素的准确率为 78.6%，而调谐不当仪器数据集的准确率低至 36.1%。旨在消除技术变异性而同时保留生物信息的数据预处理极大地提高了所有符合 SOP 的数据集的分类准确性，使符合 SOP 的数据集的分类准确性提高到 94.3%。特别是，调谐不当仪器数据集的分类准确性提高到 81.3%，而非符合 SOP 的数据集的分类准确性从 67.0%提高到 87.8%。我们证明，当应用组织学注释和优化的数据预处理管道以提高分类的泛化能力，克服技术变异性并提高整体稳健性时，基于 MALDI-MSI 的组织分类是可以在不同站点进行的。
