Extraction of artefactual MRS patterns from a large database using non‐negative matrix factorization

Despite the success of automated pattern recognition methods in problems of human brain tumor diagnostic classification, limited attention has been paid to the issue of automated data quality assessment in the field of MRS for neuro‐oncology. Beyond some early attempts to address this issue, the cur...

Full description

Saved in:
Bibliographic Details
Published in:NMR in biomedicine Vol. 35; no. 4; pp. e4193 - n/a
Main Authors: Hernández‐Villegas, Yanisleydis, Ortega‐Martorell, Sandra, Arús, Carles, Vellido, Alfredo, Julià‐Sapé, Margarida
Format: Journal Article
Language:English
Published: England Wiley Subscription Services, Inc 01.04.2022
Subjects:
Acquisition Methods
Algorithms
Artifacts and corrections
Automatic control
Automation
Biological products
Brain Neoplasms - pathology
Brain tumors
Data processing
Factorization
Feature extraction
Humans
Methods and Engineering
MR Spectrosocpy (MRS) and Spectroscopic Imaging (MRSI) Methods
Pattern recognition
Pattern Recognition, Automated - methods
Post‐acquisition Processing
Quality assessment
Quality Control
Radiology
Signal processing
Tumors
Acquisition Methods
MR Spectrosocpy (MRS) and Spectroscopic Imaging (MRSI) Methods
Artifacts and corrections
Methods and Engineering
Post-acquisition Processing
ISSN:0952-3480, 1099-1492, 1099-1492
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Despite the success of automated pattern recognition methods in problems of human brain tumor diagnostic classification, limited attention has been paid to the issue of automated data quality assessment in the field of MRS for neuro‐oncology. Beyond some early attempts to address this issue, the current standard in practice is MRS quality control through human (expert‐based) assessment. One aspect of automatic quality control is the problem of detecting artefacts in MRS data. Artefacts, whose variety has already been reviewed in some detail and some of which may even escape human quality control, have a negative influence in pattern recognition methods attempting to assist tumor characterization. The automatic detection of MRS artefacts should be beneficial for radiology as it guarantees more reliable tumor characterizations, as well as the development of more robust pattern recognition‐based tumor classifiers and more trustable MRS data processing and analysis pipelines. Feature extraction methods have previously been used to help distinguishing between good and bad quality spectra to apply subsequent supervised pattern recognition techniques. In this study, we apply feature extraction differently and use a variant of a method for blind source separation, namely Convex Non‐Negative Matrix Factorization, to unveil MRS signal sources in a completely unsupervised way. We hypothesize that, while most sources will correspond to the different tumor patterns, some of them will reflect signal artefacts. The experimental work reported in this paper, analyzing a combined short and long echo time 1H‐MRS database of more than 2000 spectra acquired at 1.5T and corresponding to different tumor types and other anomalous masses, provides a first proof of concept that points to the possible validity of this approach. We used a blind source separation (BSS) method, namely convex non‐negative matrix factorization (CNMF), to extract characteristic spectral pattern sources from a large multi‐center, multi‐project dataset of SV MRS data at 1.5T of brain tumors. We hypothesized that, in addition to different tumoral patterns, we would be able to extract and single out the patterns for the most common artefacts. The correlation and distances to the means of the different classes, as well as the mixing matrix, can be used as metrics for automatic, non‐supervised artefact detection. (85 words).
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0952-3480
1099-1492
1099-1492
DOI:10.1002/nbm.4193