Optimization of MRI Acquisition and Texture Analysis to Predict Physico-chemical Parameters of Loins by Data Mining
- 159 Downloads
The main objective of this study was to configure the acquisition and analysis of low-field magnetic resonance imaging (MRI) to predict physico-chemical characteristics of Iberian loin, evaluating the use of different MRI sequences (spin echo, SE; gradient echo, GE; turbo 3D, T3D), computational texture feature methods (GLCM, NGLDM, GLRLM, GLCM + NGLDM + GLRLM), and data mining techniques (multiple linear regression, MLR; isotonic regression, IR). Moderate to very good correlation coefficients and low mean absolute error were found when applying MLR or IR on any method of computational texture features from MRI acquired with SE or GE. For T3D sequence, accurate results are only obtained by applying IR on GLCM or GLCM + NGLDM + GLRLM methods. Considering not only the accuracy of the methodology but also consumed time and required resources, the use of SE sequences for MRI acquisition, GLCM method for MRI texture analysis, and MLR could be indicated for prediction physico-chemical characteristics of loin.
KeywordsLow-field MRI sequence Computational texture features Data mining prediction Physico-chemical characteristics Loin
The authors wish to acknowledge the funding received from the FEDER-MICIN-Infrastructure Research Project (UNEX10-1E-402). We also wish to thank the “Montesano” company from Jerez de los Caballeros (Badajoz), as well as the Animal Source Foodstuffs Innovation Service (SIPA) from the University of Extremadura, for their direct contribution and support.
- Association of Official Analytical Chemist (2000). Official methods of analysis of AOAC International (17th ed.). Gaithersburg: AOAC International.Google Scholar
- Barlow, R. E., Bartholomew, D., Bremner, J. M., & Brunk, H. D. (1972). Statistical Inference under order restriction: the theory and application of isotonic regression. New York: Wiley.Google Scholar
- Borge, L. (1985). Estimación y contrastes de hipótesis en el modelo lineal general con restricciones de desigualdad. Doctoral thesis: University of Valladolid, Spain.Google Scholar
- Cernadas, E., Antequera, T., Rodriguez, P. G., Duran, M. L., Gallardo, R., & Villa, D. (2001). Magnetic resonance imaging to classify loin from Iberian pig. In G. A. Webb, P. S. Belton, A. M. Gil, & I. Delgadillo (Eds.), Magnetic resonance imaging in food science. A view to the future (pp. 239–245). Cambridge: The Royal Society of Chemistry.CrossRefGoogle Scholar
- Colton, T. (1974). Statistical in medicine. New York: Little Brown and Co..Google Scholar
- Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). From data mining to knowledge discovery in databases. American Association for Artificial Intelligence, 17, 37–54.Google Scholar
- Haralick, R. M., & Shapiro, L. G. (1993). Computer and robot vision. Chicago: Addison-Wesley.Google Scholar
- Holmes, G., Fletcher, D., & Reutermann, P. (2012). An application of data mining to fruit and vegetable sample identification using gas chromatography-mass spectrometry. In International congress on environmental modeling and software managing resources of a limited planet. Leipzig: Germany.Google Scholar
- Nong, Y. (2014). Data mining: theories, algorithms, and examples. Boca Raton, FL: CRC Press.Google Scholar
- Sonka, M., Hlavac, V., & Boyle, R. (1999). Image processing, analysis, and machine vision. Stanford: International Thomsom Publishing ITP.Google Scholar