Automated estimation of tumor probability in prostate magnetic resonance spectroscopic imaging: Pattern recognition vs quantification

Abstract

Despite its diagnostic value and technological availability, 1 H NMR spectroscopic imaging (MRSI) has not found its way into clinical routine yet. Prerequisite for the clinical application is an automated and reliable method for the diagnostic evaluation of MRS images. In the present paper, different approaches to the estimation of tumor probability from MRSI in the prostate are assessed. Two approaches to feature extraction are compared: quantification (VARPRO, AMARES, QUEST) and subspace methods on spectral patterns (principal components, independent components, nonnegative matrix factorization, partial least squares). Linear as well as nonlinear classifiers (support vector machines, Gaussian processes, random forests) are applied and discussed. Quantification-based approaches are much more sensitive to the choice and parameterization of the quantification algorithm than to the choice of the classifier. Furthermore, linear methods based on magnitude spectra easily achieve equal performance and also allow for biochemical interpretation in combination with subspace methods. Nonlinear methods operating directly on magnitude spectra achieve the best results but are less transparent than the linear methods. Clinical studies have shown significant diagnostic value of 1 H magnetic resonance spectroscopic imaging (MRSI) for the detection of tumorous tissue in the prostate (1-6). Despite the promising results of these and other studies, the integration of MRSI in the clinical routine remains difficult, mainly because of the complexity and effort associated with the evaluation of the acquired data.Two basic approaches to the evaluation of MRSI can be distinguished: the quantification-based approach and the pattern recognition (PR) approach. Quantification aims at estimating relative metabolite concentrations as accurately as possible. For that purpose, the most likely parameter estimate for a given signal model is usually determined with a nonlinear least squares (NLS) approach. However, quantification may fail for various reasons. In particular, in the presence of artifacts and severe noise the NLS objective can have many local optima and the result becomes very sensitive to the choice of initial values. Prior knowledge about the expected signal shape can help to alleviate these problems (7), but it also leads to an estimation bias and can be harmful in unanticipated cases where the employed prior knowledge is inadequate. A subsequent statistical analysis that gains diagnostic information from the spectral data relies on these parameter estimates and therefore inherits all problems associated with the quantification.Pattern recognition approaches do not require an explicit quantification step. Although the same methods and classifiers (e.g., logistic regression (8), artificial neural networks (8), support vector machines (SVM) (9), etc.) can be used for both quantified signals and spectral patterns, only methods applied to the latter will be referred to as pattern recognition approaches in accordance with, for example,...

A hierarchical spectral clustering and nonlinear dimensionality reduction scheme for detection of prostate cancer from magnetic resonance spectroscopy (MRS)

“…However, the performance of these quantification models is usually dependent on ͑i͒ the choice of correct number of model components, ͑ii͒ optimal choice of prior knowledge ͑model function͒, ͑iii͒ presence of noise and contributions from nonprostate spectra, ͑iv͒ peak overlap owing to contributions from multiple metabolites, and ͑v͒ baseline distortion and line broadening. 22 In order to avoid the limitations of model and peak detection based approaches for MRS, recently some researchers have begun to explore domain independent techniques such as z score and principal component analysis ͑PCA͒. An excellent comprehensive comparison of quantification and pattern recognition schemes used for MRS analysis is provided in Ref.…”

“…An excellent comprehensive comparison of quantification and pattern recognition schemes used for MRS analysis is provided in Ref. 22.…”

Processing spectral data

“…[3] Prostate spectra reflect the different metabolism of tumorous and healthy tissue in a similar way, with citrate replacing NAA. [4] The third data set consists of energy-dispersive X-ray (EDX) spectra recorded with a scanning electron microscope operated at 20 keV acceleration voltage and operated in variable pressure mode. Bombarding a material with electrons can provoke the excitation of atoms by knocking free inner shell electrons.…”

Classification of prostate magnetic resonance spectra using Support Vector Machine

“…Kelm et al [8] have compared two approaches : subspace methods on spectral patterns versus quantification of some metabolites in spectra. The datasets were classified with linear and non linear classifiers (Support Vector Machine, Gaussian processes, random forests) and they obtained their best results with a non-linear classifier on magnitude spectra.…”

“…It was our aim, therefore, to develop an automatic classification scheme based on MRS data in order to assist prostate cancer localisation. To this end, we have chosen the support vector machine (SVM), a machine learning technique originating from statistical theory [8] and often used for the classification of images. The SVM has been widely used in pattern recognition applications due to its computational efficiency and good generalization performance even in the case of non linearly separable classes and in case of non-uniform distribution.…”