Cargando…

Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments

Mass spectrometry imaging is a powerful tool for investigating the spatial distribution of chemical compounds in a biological sample such as tissue. Two common goals of these experiments are unsupervised segmentation of images into newly discovered homogeneous segments and supervised classification...

Descripción completa

Detalles Bibliográficos
Autores principales: Bemis, Kyle D., Harry, April, Eberlin, Livia S., Ferreira, Christina R., van de Ven, Stephanie M., Mallick, Parag, Stolowitz, Mark, Vitek, Olga
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The American Society for Biochemistry and Molecular Biology 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4858953/
https://www.ncbi.nlm.nih.gov/pubmed/26796117
http://dx.doi.org/10.1074/mcp.O115.053918
_version_ 1782430886541656064
author Bemis, Kyle D.
Harry, April
Eberlin, Livia S.
Ferreira, Christina R.
van de Ven, Stephanie M.
Mallick, Parag
Stolowitz, Mark
Vitek, Olga
author_facet Bemis, Kyle D.
Harry, April
Eberlin, Livia S.
Ferreira, Christina R.
van de Ven, Stephanie M.
Mallick, Parag
Stolowitz, Mark
Vitek, Olga
author_sort Bemis, Kyle D.
collection PubMed
description Mass spectrometry imaging is a powerful tool for investigating the spatial distribution of chemical compounds in a biological sample such as tissue. Two common goals of these experiments are unsupervised segmentation of images into newly discovered homogeneous segments and supervised classification of images into predefined classes. In both cases, the important secondary goals are to characterize the uncertainty associated with the segmentation and with the classification and to characterize the spectral features that define each segment or class. Recent analysis methods have focused on the spatial structure of the data to improve results. However, they either do not address these secondary goals or do this with separate post hoc procedures. We introduce spatial shrunken centroids, a statistical model-based framework for both supervised classification and unsupervised segmentation. It takes as input sets of previously detected, aligned, quantified, and normalized spectral features and expresses both spatial and multivariate nature of the data using probabilistic modeling. It selects informative subsets of spectral features that define each unsupervised segment or supervised class and quantifies and visualizes the uncertainty in spatial segmentations and in tissue classification. In the unsupervised setting, it also guides the choice of an appropriate number of segments. We demonstrate the usefulness of this framework in a supervised human renal cell carcinoma experimental dataset and several unsupervised experimental datasets, including a pig fetus cross-section, three rodent brains, and a controlled image with known ground truth. This framework is available for use within the open-source R package Cardinal as part of a full pipeline for the processing, visualization, and statistical analysis of mass spectrometry imaging experiments.
format Online
Article
Text
id pubmed-4858953
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher The American Society for Biochemistry and Molecular Biology
record_format MEDLINE/PubMed
spelling pubmed-48589532017-05-01 Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments Bemis, Kyle D. Harry, April Eberlin, Livia S. Ferreira, Christina R. van de Ven, Stephanie M. Mallick, Parag Stolowitz, Mark Vitek, Olga Mol Cell Proteomics Technological Innovation and Resources Mass spectrometry imaging is a powerful tool for investigating the spatial distribution of chemical compounds in a biological sample such as tissue. Two common goals of these experiments are unsupervised segmentation of images into newly discovered homogeneous segments and supervised classification of images into predefined classes. In both cases, the important secondary goals are to characterize the uncertainty associated with the segmentation and with the classification and to characterize the spectral features that define each segment or class. Recent analysis methods have focused on the spatial structure of the data to improve results. However, they either do not address these secondary goals or do this with separate post hoc procedures. We introduce spatial shrunken centroids, a statistical model-based framework for both supervised classification and unsupervised segmentation. It takes as input sets of previously detected, aligned, quantified, and normalized spectral features and expresses both spatial and multivariate nature of the data using probabilistic modeling. It selects informative subsets of spectral features that define each unsupervised segment or supervised class and quantifies and visualizes the uncertainty in spatial segmentations and in tissue classification. In the unsupervised setting, it also guides the choice of an appropriate number of segments. We demonstrate the usefulness of this framework in a supervised human renal cell carcinoma experimental dataset and several unsupervised experimental datasets, including a pig fetus cross-section, three rodent brains, and a controlled image with known ground truth. This framework is available for use within the open-source R package Cardinal as part of a full pipeline for the processing, visualization, and statistical analysis of mass spectrometry imaging experiments. The American Society for Biochemistry and Molecular Biology 2016-05 2016-01-21 /pmc/articles/PMC4858953/ /pubmed/26796117 http://dx.doi.org/10.1074/mcp.O115.053918 Text en © 2016 by The American Society for Biochemistry and Molecular Biology, Inc. Author's Choice—Final version free via Creative Commons CC-BY license (http://creativecommons.org/licenses/by/4.0) .
spellingShingle Technological Innovation and Resources
Bemis, Kyle D.
Harry, April
Eberlin, Livia S.
Ferreira, Christina R.
van de Ven, Stephanie M.
Mallick, Parag
Stolowitz, Mark
Vitek, Olga
Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments
title Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments
title_full Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments
title_fullStr Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments
title_full_unstemmed Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments
title_short Probabilistic Segmentation of Mass Spectrometry (MS) Images Helps Select Important Ions and Characterize Confidence in the Resulting Segments
title_sort probabilistic segmentation of mass spectrometry (ms) images helps select important ions and characterize confidence in the resulting segments
topic Technological Innovation and Resources
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4858953/
https://www.ncbi.nlm.nih.gov/pubmed/26796117
http://dx.doi.org/10.1074/mcp.O115.053918
work_keys_str_mv AT bemiskyled probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments
AT harryapril probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments
AT eberlinlivias probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments
AT ferreirachristinar probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments
AT vandevenstephaniem probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments
AT mallickparag probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments
AT stolowitzmark probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments
AT vitekolga probabilisticsegmentationofmassspectrometrymsimageshelpsselectimportantionsandcharacterizeconfidenceintheresultingsegments