Computerized Consensus Diagnosis: A Classification Strategy for the Robust Analysis of MR Spectra. I. Application to <sup>1</sup>H Spectra of Thyroid Neoplasms

Somorjai, Ray L.; Nikulin, A; Pizzi, Nic; Jackson, Dick; Scarth, Gordon B.; Dolenko, Brion; Gordon, Heather L.; Russell, Peter; Lean, Cynthia L.; Delbridge, Leigh; Mountford, Carolyn E.; Smith, Ian C. P.

doi:10.1002/mrm.1910330217

Cited by 93 publications

(48 citation statements)

References 11 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Good overviews of preprocessing and feature reduction/selection methods for the classification of MRS data have been published. 7,8,28,29 We were mainly interested in the effect on classification when MRI information was added. However, a broad range of feature-reduction methods was compared in the study, to investigate whether the effect of a specific feature reduction method was more significant than the addition of MRI information.…”

Section: Discussionmentioning

confidence: 99%

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

et al. 2005

View full text Add to dashboard Cite

The purpose of this paper is to evaluate the effect of the combination of magnetic resonance spectroscopic imaging (MRSI) data and magnetic resonance imaging (MRI) data on the classification result of four brain tumor classes. Suppressed and unsuppressed short echo time MRSI and MRI were performed on 24 patients with a brain tumor and four volunteers. Four different feature reduction procedures were applied to the MRSI data: simple quantitation, principal component analysis, independent component analysis and LCModel. Water intensities were calculated from the unsuppressed MRSI data. Features were extracted from the MR images which were acquired with four different contrasts to comply with the spatial resolution of the MRSI. Evaluation was performed by investigating different combinations of the MRSI features, the MRI features and the water intensities. For each data set, the isolation in feature space of the tumor classes, healthy brain tissue and cerebrospinal fluid was calculated and visualized. A test set was used to calculate classification results for each data set. Finally, the effect of the selected feature reduction procedures on the MRSI data was investigated to ascertain whether it was more important than the addition of MRI information. Conclusions are that the combination of features from MRSI data and MRI data improves the classification result considerably when compared with features obtained from MRSI data alone. This effect is larger than the effect of specific feature reduction procedures on the MRSI data. The addition of water intensities to the data set also increases the classification result, although not significantly. We show that the combination of data from different MR investigations can be very important for brain tumor classification, particularly if a large number of tumors are to be classified simultaneously.

show abstract

Section: Discussionmentioning

confidence: 99%

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

et al. 2005

View full text Add to dashboard Cite

show abstract

“…Another example demonstrates the method of consensus analysis (Somorjai et al 1995(Somorjai et al , 2004a. This involves analysis of the 1 H spectra of thyroid tissue biopsies by use of different classifier approaches and then combining the resultant classifier outcomes to form a consensus result.…”

Section: Thyroid Cancermentioning

confidence: 99%

Deriving biomedical diagnostics from NMR spectroscopic data

Smith

Somorjai

2011

Biophys Rev

Self Cite

View full text Add to dashboard Cite

Biomedical spectroscopic experiments generate large volumes of data. For accurate, robust diagnostic tools the data must be analyzed for only a few characteristic observations per subject, and a large number of subjects must be studied. We describe here two of the current data analytic approaches applied to this problem: SIMCA (principal component analysis, partial least squares), and the statistical classification strategy (SCS). We demonstrate the application of the SCS by three examples of its use in analyzing 1 H NMR spectra: screening for colon cancer, characterization of thyroid cancer, and distinguishing cancer from cholangitis in the biliary tract.

show abstract

“…The GA_ORS approach has been very successful [for its application to the classification of biomedical MR and IR spectra, see Somorjai et al (1995), and the review of Lean et al (2002) …”

Section: Feature Selection/extraction/generationmentioning

confidence: 99%

Creating robust, reliable, clinically relevant classifiers from spectroscopic data

Somorjai

2009

Biophys Rev

View full text Add to dashboard Cite

I describe in detail the intimately connected feature extraction and classifier development stages of the data-driven Statistical Classification Strategy (SCS) and compare them with current practice used in MR spectroscopy. We initially created the SCS for the analysis of MR and IR spectra of biofluids and tissues, and subsequently extended it to analyze biomedical data in general. I focus on explaining how to extract discriminatory spectral features and create robust classifiers that can reliably discriminate diseases and disease states. I discuss our approach to identifying features that retain spectral identity and provisionally relate these features, averaged subregions of the spectra, to specific chemical entities ("metabolites"). Particular emphasis is placed on describing the steps required to help create classifiers whose accuracy doesn't deteriorate significantly when presented with new, unknown samples. A simple but powerful extension of the discovered features to detect metabolite-metabolite (feature-feature) interactions is also sketched. I contrast the advantages and disadvantages of using either spectral signatures or explicit metabolite concentrations derived from the spectra as sets of discriminatory features. At present, no clearcut preference is obvious and more objective comparisons will be needed. Finally, I argue that clinical requirements and exigencies strongly suggest adopting a two-phase approach to diagnosis/prognosis. In the first phase the emphasis ought to be on providing as accurate a diagnosis as possible, without any attempt to identify "biomarkers." That should be the goal of the second, research phase, with a view of providing prognosis on disease progression.

show abstract

Computerized Consensus Diagnosis: A Classification Strategy for the Robust Analysis of MR Spectra. I. Application to ¹H Spectra of Thyroid Neoplasms

Cited by 93 publications

References 11 publications

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

Deriving biomedical diagnostics from NMR spectroscopic data

Creating robust, reliable, clinically relevant classifiers from spectroscopic data

Contact Info

Product

Resources

About

Computerized Consensus Diagnosis: A Classification Strategy for the Robust Analysis of MR Spectra. I. Application to 1H Spectra of Thyroid Neoplasms

Cited by 93 publications

References 11 publications

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

Deriving biomedical diagnostics from NMR spectroscopic data

Creating robust, reliable, clinically relevant classifiers from spectroscopic data

Contact Info

Product

Resources

About

Computerized Consensus Diagnosis: A Classification Strategy for the Robust Analysis of MR Spectra. I. Application to ¹H Spectra of Thyroid Neoplasms