Toward Digital Staining using Imaging Mass Spectrometry and Random Forests

• Published in: Journal of proteome research Vol. 8; no. 7; pp. 3558 - 3567
• Main Authors: Hanselmann, Michael, Köthe, Ullrich, Kirchner, Marc, Renard, Bernhard Y, Amstalden, Erika R, Glunde, Kristine, Heeren, Ron M. A, Hamprecht, Fred A
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 01.07.2009
• Subjects: Algorithms; Computational Biology - methods; Data Interpretation, Statistical; Gene Expression Profiling - methods; Humans; Image Processing, Computer-Assisted; Markov Chains; Mass Spectrometry - methods; Models, Statistical; Neoplasms - pathology; Oligonucleotide Array Sequence Analysis - methods; Pattern Recognition, Automated; Proteomics - methods; Software; imaging mass spectrometry; Markov Random Fields; Random Forest classification; spectral images; bioinformatics; smoothing; hyperspectral images
• ISSN: 1535-3893; 1535-3907
• DOI: 10.1021/pr900253y

We show on imaging mass spectrometry (IMS) data that the Random Forest classifier can be used for automated tissue classification and that it results in predictions with high sensitivities and positive predictive values, even when intersample variability is present in the data. We further demonstrate how Markov Random Fields and vector-valued median filtering can be applied to reduce noise effects to further improve the classification results in a posthoc smoothing step. Our study gives clear evidence that digital staining by means of IMS constitutes a promising complement to chemical staining techniques.