Mimicking the human expert: Pattern recognition for an automated assessment of data quality in MR spectroscopic images

Magnetic Resonance in Medicine

Volumn 59, Issue 6, 2008, Pages 1457-1466

  Menze, Bjoern H ^a   Kelm, B Michael ^a   Weber, Marc André ^b   Bachert, Peter ^a,b   Hamprecht, Fred A ^a,c  

^a UNIVERSITY OF HEIDELBERG   (Germany)

^b GERMAN CANCER RESEARCH CENTER DKFZ   (Germany)

^c INF   (Germany)

Author keywords

Artifact recognition; Automated diagnostic systems; Expert systems; Magnetic resonance spectroscopic imaging; Quality classification

Indexed keywords

AUTOMATION; CLASSIFICATION (OF INFORMATION); CURVE FITTING; DATA HANDLING; DECISION TREES; DIAGNOSIS; EXPERT SYSTEMS; IMAGE QUALITY; LEARNING SYSTEMS; MAGNETIC RESONANCE; MAGNETIC RESONANCE SPECTROSCOPY; PATTERN RECOGNITION; RANDOM ERRORS; RELIABILITY ANALYSIS; SIGNAL RECEIVERS; SIGNAL TO NOISE RATIO; SPECTROSCOPIC ANALYSIS; TURING MACHINES;

ARTIFACT RECOGNITION; AUTOMATED DIAGNOSTIC SYSTEMS; MAGNETIC RESONANCE SPECTROSCOPIC IMAGING; MR SPECTROSCOPIC IMAGING; PROBABILISTIC ASSESSMENTS; QUALITY CLASSIFICATION; RANDOM FOREST CLASSIFIER; RECEIVER OPERATOR CHARACTERISTICS;

QUALITY CONTROL;

AREA UNDER THE CURVE; ARTICLE; ARTIFACT; AUTOANALYSIS; AUTOMATION; BRAIN TUMOR; DIAGNOSTIC IMAGING; IMAGE ANALYSIS; INFORMATION PROCESSING; NEUROIMAGING; NUCLEAR MAGNETIC RESONANCE SPECTROSCOPY; PATTERN RECOGNITION; PROBABILITY; QUALITATIVE ANALYSIS; QUALITY CONTROL; QUANTITATIVE ANALYSIS; RECEIVER OPERATING CHARACTERISTIC; TUMOR DIAGNOSIS;

EID: 44949144064     PISSN: 07403194     EISSN: 15222594     Source Type: Journal    
DOI: 10.1002/mrm.21519     Document Type: Article

References (34)

1. Maudsley AA. Can MR spectroscopy ever be simple and effective? Am J Neurorad 2005;26:2167.
2. Vanhamme L, van den Boogaart A, van Huffel S. Improved method for accurate and efficient quantification of MRS data with use of prior knowledge. J Magn Reson 1997;129:35-43.
3. Provencher SW. Estimation of metabolite concentrations from localized in vivo proton NMR spectra. Magn Reson Med 1993;30:672-679.
4. Ratiney H, Sdika M, Coenradie Y, Cavassila S, van Ormondt D, Graveron-Demilly D. Time-domain semi-parametric estimation based on a metabolite basis set. NMR Biomed 2005;18:1-13.
5. Soher BJ, Young K, Govindaraju V, Maudsley AA. Automated spectral analysis III: application to in vivo proton MR spectroscopy and spectroscopic imaging. Magn Reson Med 1998;40:822-31.
6. 1H MR spectroscopy of the brain: absolute quantification of metabolites. Radiology 2006;240:318-32.
7. Hagberg G. From magnetic resonance spectroscopy to classification of tumors. A review of pattern recognition methods. NMR Biomed 1998;11:148-156.
8. 1H brain tumor spectra: a multicenter study. Magn Reson Med 2003;49:29-36.
9. 1H MR spectra. J Magn Reson 2004;170:164-75.
10. Laudadio T, Pels P, de Lathauwer L, van Hecke P, van Huffel S. Tissue segmentation and classification of MRSI data using canonical correlation analysis. Magn Reson Med 2005;54:1519-29.
11. Menze BH, Lichy MP, Bachert P, Kelm BM, Schlemmer HP, Hamprecht FA. Optimal classification of long echo time in vivo magnetic resonance spectra in the detection of recurrent brain tumors. NMR Biomed 2006:19:599-60.
12. Saitta L, Neri F. Learning in the "real world." Machine Learn 1998;30:133-163.
13. Brodley CE. The need for diagnostics for classification algorithms. International Conference on Machine Learning Research (ICML), 1997. Workshop on Machine Learning Applications in the Real World; Methodological Aspects and Implications, Nashville, Tennessee, July 8-12, 1997.
14. 1H magnetic resonance spectroscopy and a gallery of artifacts. NMR Biomed 2004;17:361-381.
15. Tate AR, Underwood J, Acosta DM, Jnlià-Sapé M, Majós C, Moreno-Torres A, Howe FA, van der Graaf M, Lefournier V, Murphy MM, Loosemore A, Ladroue C, Wesseling P, Bosson JL, Cabañas ME, Simonetti AW, Gajewicz W, Calvar J, Capdevila A, Wilkins PR, Anthony Bell B, Rémy C, Heerschap A, Watson D, Griffiths JR, Arús C. Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra. NMR Biomed 2006;19:411-434.
16. Cavassila S, Deval S, Huegen C, van Ormondt D, Graveron-Demilly D. Cramér-Rao bounds: an evaluation tool for quantitation. NMR Biomed 2001;14:278-83.
17. Young Y, Khetselius D, Soher BJ, Maudsley AA. Confidence images for MR spectroscopic imaging. Magn Reson Med 2000;44:537-545.
18. Vanhamme L, Lemmerling P, van Huffel S. Comments on "Confidence Images for MR Spectroscopic Imaging" by Young, Khetselius, Soher and Maudsley. Magn Reson Med 2001;46:1254-56.
19. Ebel A, Soher BJ, Maudsley AA. Assessment of 3D proton MR echoplanar spectroscopic imaging using automated spectral analysis. Magn Reson Med 2001;46:1072-1078.
20. Elster C, Schubert F, Link A, Walzel M, Seifert F, Rinneberg H. Quantitative magnetic resonance spectroscopy: Semiparametric modeling and determination of uncertainties. Magn Reson Med 2005;53:1288-1296.
21. Jiru F, Skoch A, Klose U, Grodd W, Hajek M. Error images for spectroscopic imaging by LCModel using Cramér Rao bounds. MAGMA 2006;19:1-14.
22. Naressi A, Couturier C, Devos JM, Janssen M, Mangeat C. de Beer R, Graveron-Demilly D. Java-based graphical user interface for the MRUI quantitation software package. MAGMA 2001;12:141-152.
23. Breiman L. Random forests. Machine Learn J 2001;45:5-32.
24. Liaw A, Wiener M. Classification and regression by random Forest. R News 2001;2:18-22.
25. Seber GAF, Wild CJ. Nonlinear regression. New York: John Wiley & Sons; 1989.
26. Schlemmer HP, Bachert P, Herfarth KK, Zuna I, Debus J, van Kaick G. Proton MR spectroscopic evaluation of suspicious brain lesions after stereotactic radiotherapy. AJNR Am J Neuroradiol 2001;22:1316-1324.
27. Ihaka R, Gentleman R. R: a language for data analysis and graphics. J Comput Graph Stat 1996;5:299-314.
28. Sing T, Sander O, Beerenwinkel N, Lengauer T. ROCR: visualizing classifier performance in R. Bioinformatics 2005;21:3940-3941.
29. Nelson S. Novel approaches to spectral processing and quantification. In: ISMRM 14th Scientific Meeting, Seattle, Washington, 6-12 May 2006.
30. Kelm BM, Menze BH, Zechmann CM, Baudendistel KT, Hamprecht FA. Automated estimation of tumor probability in prostate magnetic resonance spectroscopic imaging: pattern recognition vs quantification. Magn Reson Med 2007;57:150-159.
31. Lukas L, Devos A, Suykens JA, Vanhamme L, Howe FA, Majós C, Moreno-Torres A, van der Graaf M, Tate AR, Arús C, van Huffel S. Brain tumor classification based on long echo proton MRS signals. Artif Intel Med 2004;31:73-89.
32. Menze BH, Kelm BM, Heck D, Lichy MP, Hamprecht FA. Machine based rejection of low-quality spectra, and estimation of brain tumor probabilities from magnetic resonance spectroscopic images. In: Handels H, Ehrhardt J, Horsch A, Meinzer HP, Tolxdorf T, editors. Proceedings of the BVM-Workshop, Informatik aktuell. New York: Springer; 2006. p 31-35.
33. Guha R, Jurs PC. Determining the validity of a QSAR model - a classification approach. J Chem Inf Model 2005;45:65-73.
34. Maudsley AA, Darkazanli A, Alger JR, Hall LO, Schuff N, Studholme C, Yu Y, Ebel A, Frew A, Goldgof D, Gu Y, Pagare R, Rousseau F, Sivasankaran K, Soher BJ, Weber P, Young K, Zhu X. Comprehensive processing, display and analysis for in vivo MR spectroscopic imaging. NMR Biomed 2006;19:492-503.