Accurate diagnosis and prognosis of human cancers by proton MRS and a three-stage classification strategy

Lean, Cynthia L.; Somorjai, Ray L.; Smith, Ian C. P.; Russell, Peter; Mountford, Carolyn E.

doi:10.1016/s0066-4103(02)48004-0

Cited by 40 publications

(32 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The -errors are between 8 and 25%. There is virtually no difference between nonnormalized (method 1-4) and normalized methods (5)(6)(7)(8). When information from the images is also used during classification, the -error ranges between 6 and 12% and the -error between 4 and 8%.…”

Section: Resultsmentioning

confidence: 99%

“…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%

“…The interpretation of this data is difficult and subjective and therefore classification based on pattern recognition is under development. [5][6][7][8][9][10] At the moment, most MR-related strategies to obtain information about brain tumors use either MRI or MRSI. A combination of both data sources has not been extensively investigated yet.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…We demonstrate here that application of a multistage, supervised SCS developed for analysis of NMR spectra (24,44) . Amplification products were detected by staining with ethidium bromide and were visualized under UV light.…”

mentioning

confidence: 99%

“…1D proton ( 1 H) NMR spectra of cell suspensions provide an overview of mobile hydrogen-containing compounds, which can be identified by multidimensional NMR correlation spectroscopy. Multivariate analysis and pattern recognition techniques detect differences in gross spectral characteristics (shape and pattern) of spectroscopic data from biological samples without the need to identify individual compounds (2,14,17,24,30,44,45). It was shown in a preliminary study that analysis of 1 H NMR spectra by linear discriminate analysis is able to distinguish between selected species of streptococci and staphylococci with high accuracy (2).…”

mentioning

confidence: 99%

Rapid Identification ofCandidaSpecies by Using Nuclear Magnetic Resonance Spectroscopy and a Statistical Classification Strategy

Himmelreich

Somorjai

Dolenko

et al. 2003

Appl Environ Microbiol

Self Cite

View full text Add to dashboard Cite

Nuclear magnetic resonance (NMR) spectra were acquired from suspensions of clinically important yeast species of the genus Candida to characterize the relationship between metabolite profiles and species identification. Major metabolites were identified by using two-dimensional correlation NMR spectroscopy. Onedimensional proton NMR spectra were analyzed by using a staged statistical classification strategy. Analysis of NMR spectra from 442 isolates of Candida albicans, C. glabrata, C. krusei, C. parapsilosis, and C. tropicalis resulted in rapid, accurate identification when compared with conventional and DNA-based identification. Spectral regions used for the classification of the five yeast species revealed species-specific differences in relative amounts of lipids, trehalose, polyols, and other metabolites. Isolates of C. parapsilosis and C. glabrata with unusual PCR fingerprinting patterns also generated atypical NMR spectra, suggesting the possibility of intraspecies discontinuity. We conclude that NMR spectroscopy combined with a statistical classification strategy is a rapid, nondestructive, and potentially valuable method for identification and chemotaxonomic characterization that may be broadly applicable to fungi and other microorganisms.

show abstract

Musculoskeletal tumors: Use of proton MR spectroscopic imaging for characterization

Fayad

Bluemke

McCarthy

et al. 2005

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Purpose:To determine the value of multivoxel proton magnetic resonance spectroscopic imaging (MRSI) in distinguishing malignant skeletal tumors from benign tumors and normal bone marrow using the metabolite choline (Cho) as a marker for malignancy. Materials and Methods:Pathologic specimens obtained from 13 patients who had undergone wide resection for skeletal tumors underwent evaluation by MRSI at 1.5 T. Coronal T1-weighted gradient-echo sequence obtained for localization purposes (TR/TE ϭ 250/1.8 msec, field of view [FOV] ϭ 18 ϫ 18), and single-slice MRSI (TR/TE ϭ 2000/ 272 msec, FOV ϭ 18 ϫ 18, 10-mm slice-thickness) were performed. Water, lipid, and Cho images were reconstructed from MRSI data. Cho signal was measured in each specimen and expressed relative to background noise level (signal-to-noise ratio [SNR]) where noise was measured between 7.0 and 9.0 ppm. Cho SNRs were compared between areas containing malignant tumor and nonmalignant tissue (benign lesion or normal bone marrow) as determined by histopathology.Results: Specimens included 13 skeletal sarcomas (seven osteosarcomas, three chondrosarcomas, one malignant fibrous histiocytoma, one fibrosarcoma, and one leiomyosarcoma). All specimens included a sample of normal bone marrow and two specimens also contained benign lesions. All sarcomas demonstrated a signal at 3.2 ppm assigned to Cho-containing metabolites in areas of malignancy. Peak Cho SNR was significantly different for areas containing histologically-proven malignancy compared to nonmalignant tissue (9.8 Ϯ 5.1 vs. 2.7 Ϯ 1.4, respectively, P Ͻ 0.002). Conclusion:These preliminary results indicate that MRSI at 1.5 T is a promising noninvasive method of differentiating malignant skeletal tumors from nonmalignant tissue. Using MRSI, Cho can be detected in skeletal tumors and may serve as a marker for malignancy. MAGNETIC RESONANCE IMAGING (MRI) is the primary cross-sectional imaging modality used for identification and characterization of bone and soft tissue abnormalities due to the very high contrast resolution of the technique. However, although the sensitivity of MRI for malignancy is high, its specificity is low (1-3). In one study, malignancy was correctly assessed in only 55% of cases (3). As a result, there are relatively few lesions (e.g., cysts and lipomas) that are definitely characterized by conventional MRI. Gadolinium enhancement ratios with MRI have been used, but are not widely applied and are more useful for assessing treatment response (4). As a result, many lesions are indeterminate in nature, and must be biopsied or resected for definitive characterization and diagnosis. Thus, there are substantial gaps in our knowledge in the identification and classification of skeletal lesions based on MRI.Multivoxel proton magnetic resonance spectroscopic imaging (MRSI) is a new approach to the evaluation of musculoskeletal lesions. It is a means of molecular imaging with MRI that can potentially provide a noninvasive method for characterizing bone and soft tissue lesions for malignancy...

show abstract

Accurate diagnosis and prognosis of human cancers by proton MRS and a three-stage classification strategy

Cited by 40 publications

References 60 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

Rapid Identification ofCandidaSpecies by Using Nuclear Magnetic Resonance Spectroscopy and a Statistical Classification Strategy

Musculoskeletal tumors: Use of proton MR spectroscopic imaging for characterization

Contact Info

Product

Resources

About