Texture-based identification of dystrophy phase. Indicating the most suitable features for therapy testing

• Autorzy: Duda D.
• Języki publikacji: EN

Abstrakty

EN

In this study, texture analysis (TA) is applied for characterization of dystrophic muscles visualized on T2-weighted Magnetic Resonance (MR) images. The study proposes a strategy for indicating the textural features that are the most appropriate for testing the therapies of Duchenne muscular dystrophy (DMD). The strategy considers that muscle texture evolves not only along with the disease progression but also with the individual’s development. First, a Monte Carlo (MC) procedure is used to assess the relative importance of each feature in identifying the phases of growth in healthy controls. The features considered as age-dependent at a given acceptance threshold are excluded from further analyses. It is assumed that their application in therapies’ evaluation may entail an incorrect assessment of dystrophy response to treatment. Next, the remaining features are used in differentiation among dystrophy phases. At this step, an MC-based feature selection is applied to find an optimal subset of features. Experiments are repeated at several acceptance thresholds for age-dependent features. Different solutions are finally compared with two classifiers: Neural Network (NN) and Support Vector Machines (SVM). The study is based on the Golden Retriever Muscular Dystrophy (GRMD) model. In total, 39 features provided by 8 TA methods (statistical, filter- and model-based) are tested.

Słowa kluczowe

EN

Golden Retriever Muscular Dystrophy; MRI-based tissue characterization; texture analysis; Monte Carlo feature selection; classification

PL

dystrofia mięśniowa Duchenne'a; obrazowanie metodą rezonansu magnetycznego; analiza tekstury; klasyfikacja

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2018
• Tom: Vol. 27
• Strony: 29--40
• Opis fizyczny: Bibliogr. 30 poz., tab.

Twórcy

autor

Duda D.

• Faculty of Computer Science, Bialystok University of Technology, Wiejska 45a, 15-351 Bialystok, Poland

Bibliografia

• [1] BISHOP C. M. Neural networks for pattern recognition. 1995. Clarendon Press, Oxford, United Kingdom.
• [2] DE CERTAINES J. D., LARCHER T., DUDA D., AZZABOU N., ELIAT P.-A., ESCUDERO L. M., ET AL. Application of texture analysis to muscle MRI: 1-what kind of information should be expected from texture analysis? EPJ Nonlinear Biomed. Phys., 2015, Vol. 3. pp. 1–14.
• [3] DRAMINSKI M., RADA-IGLESIAS A., ENROTH S., WADELIUS C., KORONACKI J., KOMOROWSKI J. Monte Carlo feature selection for supervised classification. Bioinformatics, 2008, Vol. 24. pp. 110–117.
• [4] DUDA D. Classification d’images medicales bas ´ ee sur l’analyse de texture. 2009. Rennes, France. ´
• [5] DUDA D., KRETOWSKI M., AZZABOU N., DE CERTAINES J. D. MRI texture analysis for differentiation between healthy and Golden Retriever Muscular Dystrophy dogs at different phases of disease evolution. Computer Information Systems and Industrial Management. CISIM 2015, 2015, Vol. 9339 of Lecture Notes in Comput. Sci. Springer, Cham, pp. 255–266.
• [6] DUDA D., KRETOWSKI M., AZZABOU N., DE CERTAINES J. D. MRI texture-based classification of dystrophic muscles. A search for the most discriminative tissue descriptors. Computer Information Systems and Industrial Management. CISIM 2016, 2016, Vol. 9842 of Lecture Notes in Comput. Sci. Springer, Cham, pp. 116–128.
• [7] EUROPEAN MEDICINES AGENCY (EMA). COMMITTEE FOR MEDICINAL PRODUCTS FOR HUMAN USE (CHMP). Guideline on the clinical investigation of medicinal products for the treatment of Duchenne and Becker muscular dystrophy. 2015.
• [8] FAN Z., WANG J., AHN M., SHILOH-MALAWSKY Y., CHAHIN N., ELMORE S., ET AL. Characteristics of magnetic resonance imaging biomarkers in a natural history study of golden retriever muscular dystrophy. Neuromuscul. Disord., 2014, Vol. 24. pp. 178–191.
• [9] FINANGER E. L., RUSSMAN B., FORBES S. C., ROONEY W. D., WALTER G. A., VANDENBORNE K. Use of skeletal muscle MRI in diagnosis and monitoring disease progression in Duchenne Muscular Dystrophy. Phys. Med. Rehabil. Clin. N. Am., 2012, Vol. 23. pp. 1–10.
• [10] FREUND Y., SCHAPIRE R. E. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci., 1997, Vol. 55. pp. 119–139.
• [11] GALLOWAY M. M. Texture analysis using gray level run lengths. Comput. Graph. Image Process., 1975, Vol. 4. pp. 172–179.
• [12] GUIRAUD S., AARTSMA-RUS A., VIEIRA N. M., DAVIES K. E., VAN OMMEN G.-J. B., KUNKEL L. M. The pathogenesis and therapy of muscular dystrophies. Annu. Rev. Genomics Hum. Genet., 2015, Vol. 16. pp. 281–308.
• [13] GUYON I., ELISSEEFF A. An introduction to variable and feature selection. J. Mach. Learn. Res., 2003, Vol. 3. pp. 1157–1182.
• [14] HALL M., FRANK E., HOLMES G., PFAHRINGER B., REUTEMANN P., WITTEN I. H. The WEKA data mining software: an update. SIGKDD Explor. Newsl., 2009, Vol. 11. pp. 10–18.
• [15] HARALICK R., SHANMUGAM K., DINSTEIN I. Textural features for image classification. IEEE Trans. Syst. Man Cybern., 1973, Vol. SMC-3. pp. 610–621.
• [16] HOSMER D. W. J., LEMESHOW S., STURDIVANT R. X. Applied logistic regression. 3rd ed., 2013. John Wiley & Sons, Inc., Hoboken, NJ, USA.
• [17] KOHAVI R., JOHN G. H. Wrappers for feature subset selection. Artif. Intell., 1997, Vol. 97. pp. 273–324.
• [18] KORNEGAY J. N. The golden retriever model of Duchenne muscular dystrophy. Skelet. Muscle, 2017, Vol. 7. pp. 1–21.
• [19] LERSKI R. A., DE CERTAINES J. D., DUDA D., KLONOWSKI W., YANG G., COATRIEUX J. L., ET AL. Application of texture analysis to muscle MRI: 2 – technical recommendations. EPJ Nonlinear Biomed. Phys., 2015, Vol. 3. pp. 1–20.
• [20] MARTINS-BACH A. B., MALHEIROS J., MATOT B., MARTINS P. C. M., ALMEIDA C. F., CALDEIRA W., ET AL. Quantitative T2 combined with texture analysis of nuclear Magnetic Resonance Images identify different degrees of muscle involvement in three mouse models of muscle dystrophy: mdx, Large(myd) and mdx/Large(myd). PLOS ONE, 2015, Vol. 10. pp. 1–16.
• [21] PLATT J. C. Fast training of Support Vector Machines using Sequential Minimal Optimization. Advances in Kernel Methods – Support Vector Learning, 1998. MIT Press, Cambridge, MA, USA, pp. 185–208.
• [22] PUDIL P., NOVOVICOVA J., KITTLER J. Floating search methods in feature selection. Pattern Recog. Lett., 1994, Vol. 15. pp. 1119–1125.
• [23] QUINLAN J. R. C4.5: Programs for machine learning. 1993. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.
• [24] SALMANINEJAD A., VALILOU S. F., BAYAT H., EBADI N., DARAEI A., YOUSEFI M., ET AL. Duchenne muscular dystrophy: an updated review of common available therapies. Int. J. Neurosci., 2018, Vol. 5. pp. 1–11.
• [25] SZCZYPINSKI P. M., STRZELECKI M., MATERKA A., KLEPACZKO A. Mazda – a software package for image texture analysis. Comput. Methods Programs Biomed., 2009, Vol. 94. pp. 66–76.
• [26] THIBAUD J., AZZABOU N., BARTHELEMY I., FLEURY S., CABROL L., BLOT S., CARLIER P. G. Comprehensive longitudinal characterization of canine muscular dystrophy by serial NMR imaging of GRMD dogs. Neuromuscul. Disord., 2012, Vol. 22, Suppl. 2. pp. S85–S99.
• [27] VAPNIK V. N. The nature of statistical learning theory. 2nd ed., 2000. Springer, New York, USA.
• [28] WANG J., FAN Z., VANDENBORNE K., WALTER G., SHILOH-MALAWSKY Y., AN H., ET AL. A computerized MRI biomarker quantification scheme for a canine model of Duchenne muscular dystrophy. Int. J. Comput. Assist. Radiol. Surg., 2013, Vol. 8. pp. 763–774.
• [29] WESZKA J. S., DYER C. R., ROSENFELD A. A comparative study of texture measures for terrain classification. IEEE Trans. Syst., Man Cybern., 1976, Vol. SMC-6. pp. 269–285.
• [30] YANG G., LALANDE V., CHEN L., AZZABOU N., LARCHER T., DE CERTAINES J. D., ET AL. MRI texture analysis of GRMD dogs using orthogonal moments: A preliminary study. IRBM, 2015, Vol. 36. pp. 213–219.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).