Deep learning for tumor classification in imaging mass spectrometry

Abstract

Motivation: Tumor classification using Imaging Mass Spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Deep learning offers an approach to learn feature extraction and classification combined in a single model. Commonly these steps are handled separately in IMS data analysis, hence deep learning offers an alternative strategy worthwhile to explore. Results: Methodologically, we propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. The proposed methods are evaluated on two challenging tumor classification tasks and compared to a baseline approach. Competitiveness of the proposed methods are shown on both tasks by studying the performance via cross-validation. Moreover, the learned models are analyzed by the proposed sensitivity analysis revealing biologically plausible effects as well as confounding factors of the considered task. Thus, this study may serve as a starting point for further development of deep learning approaches in IMS classification tasks. Source Code: https://gitlab.informatik.uni-bremen.de/digipath/Deep Learning for Tumor Classification in IMS Data: https://seafile.zfn.uni-bremen.de/d/85c915784e/

Identification of Proteomic Markers in Head and Neck Cancer Using MALDI–MS Imaging, LC–MS/MS, and Immunohistochemistry

“…Our results are the basis for further statistical validation of the found markers. By combining these findings with the new deep learning approach, a new classification model can be developed …”

“…By combining these findings with the new deep learning approach, a new classification model can be developed. [40] The bias problem between data from FFPE and fresh frozen tissue is an often-discussed issue. In our study, the absence of keratin type II peaks in fresh frozen tissue underlines the importance of using both kinds of tissues for marker discovery.…”

MALDI‐Imaging for Classification of Epithelial Ovarian Cancer Histotypes from a Tissue Microarray Using Machine Learning Methods

“…Using deep learning approaches, discrimination between head and neck cancer and noncancerous epithelium based on nonlinear microscopic images could be successfully performed . Other studies propose that CNN enables to integrate mass spectrometry data and to determine challenging tumor classification tasks …”

“…In the area of image processing, deep learning methods typically implement convolutional neural networks (CNNs) in order to exploit spatial relations and retrieve high-level abstractions for the final classification stage of the network. [25] In Behrmann et al (2018) [26] the authors propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. In Inglese et al (2017) [27] the authors found linear methods for unsupervised dimensionality reduction to be inadequate for tumor classification based on IMS datasets.…”

“…In Behrmann et al. (2018) the authors propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. In Inglese et al.…”