Comparative analysis of selected classifiers in posterior cruciate ligaments computer aided diagnosis

• Autorzy: Zarychta P. , Badura P. , Pietka E.

Identyfikatory

DOI

10.1515/bpasts-2017-0008

• Języki publikacji: EN

Abstrakty

EN

A study on computer aided diagnosis of posterior cruciate ligaments is presented in this paper. The diagnosis relies on T1-weighted magnetic resonance imaging. During the image analysis stage, the ligament region is automatically detected, localized, and extracted using fuzzy segmentation methods. Eight geometric features are defined for the ligament object. With a clinical reference database containing 107 cases of both healthy and pathological cases, a Fisher linear discriminant is used to select 4 most distinctive features. At the classification stage we employ five different soft computing classifiers to evaluate the feature vector suitability for the computerized ligament diagnosis. Among the classifiers we introduce and specify the particle swarm optimization based Sugeno-type fuzzy inference system and compare its performance to other established classification systems. The classification accuracy metrics: sensitivity, specificity, and Dice index all exceed 90% for each classifier under consideration, indicating high level of the proposed feature vector relevance in the computer aided ligaments diagnosis.

Słowa kluczowe

EN

posterior cruciate ligament; computer aided diagnosis; feature extraction; classification; soft computing

PL

więzadło krzyżowe tylne; diagnostyka wspierana komputerowo; klasyfikacja; obliczenia miękkie

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2017
• Tom: Vol. 65, nr 1
• Strony: 63--70
• Opis fizyczny: Bibliogr. 40 poz., tab., wykr., rys.

Twórcy

autor

Zarychta P.

• Silesian University of Technology, Faculty of Biomedical Engineering, 40 Roosevelta St., 41-800 Zabrze, Poland

autor

Badura P.

• Silesian University of Technology, Faculty of Biomedical Engineering, 40 Roosevelta St., 41-800 Zabrze, Poland

autor

Pietka E.

• Silesian University of Technology, Faculty of Biomedical Engineering, 40 Roosevelta St., 41-800 Zabrze, Poland

Bibliografia

• [1] A. Bochenek and M. Reicher, “The human anatomy”, PZWL, Warsaw, 1990, [in Polish].
• [2] A. Pasierbinski and A. Jarzabek, “Biobiomechanics of the cruciate ligament”, Acta Clinica 4(1), 284-293 (2001), [in Polish].
• [3] J. Voos, C. Mauro, T. Wente, R. Warren, and T. Wickiewicz, “Posterior cruciate ligament. Anatomy, biomechanics and outcomes”, Am. J. Sports. Med. 40(1), 222-231 (2012).
• [4] A. Dziak, “Injuries of the cruciate ligaments of the knee joint”, Acta Clinica 4(1), 271-274 (2001), [in Polish].
• [5] P. Zarychta, “Features extraction in anterior and posterior cruciate ligaments analysis”, Comput. Med. Imag. Grap. 46, Part 2, 108-120 (2015).
• [6] M. Aiello, “MRI for posterior cruciate ligament injuries”, available online: http://emedicine.medscape.com/article/400845-overview [accessed 2016‒06‒06].
• [7] A. Alcala-Galiano, M. Baeva, M. Ismael, and M. Argueso, “Imaging of posterior cruciate ligament (PCL) reconstruction: normal postsurgical appearance and complications”, Skeletal Radiol. 43(12), 1659-1668 (2014).
• [8] F.R. Noyes, and S.D. Barber-Westin, Noyes’ knee disorders: surgery, rehabilitation, clinical outcomes, 2nd ed., Elsevier, 2017.
• [9] P. Zarychta, “Posterior cruciate ligament - 3D visualization”, in Conference on Computer Recognition Systems, Advances in Intelligent and Soft Computing 45, 695-702 (2007).
• [10] R. Wright et al., “Outcome of revision anterior cruciate ligament reconstruction: a systematic review”, J. Bone Joint Surg. Am. 94(6), 531-536 (2012).
• [11] B. Crespo, E. James, L. Metsavaht, and R. LaPrade, “Injuries to posterolateral corner of the knee: a comprehensive review from anatomy to surgical treatment”, Revista Brasileira de Ortopedia (English Edition) 50(4), 363-370 (2015).
• [12] D. Hensler, C. Van Eck, F. Fu, and J. Irrgang, “Anatomic anterior cruciate ligament reconstruction utilizing the doublebundle technique”, J. Orthop. Sport. Phys. 42(3), 184-195 (2012).
• [13] S. Czuppon, B. Racette, S. Klein, and M. Harris-Hayes, “Variables associated with return to sport following anterior cruciate ligament reconstruction: a systematic review”, Brit. J. Sport. Med. 48, 356-364 (2014).
• [14] L. Kruse, B. Gray, and L. Wright, “Rehabilitation after anterior cruciate ligament reconstruction”, J. Bone Joint Surg. Am. 94(19), 1737-1748 (2012).
• [15] P. Glasgow, “Simplicity: the ultimate sophistication”, Brit. J. Sport. Med. 48, 345 (2014).
• [16] J. Cavanaugh, A. Saldivar, and R. Marx, “Postoperative rehabilitation after posterior cruciate ligament reconstruction and combined posterior cruciate ligament reconstruction-posterior lateral corner surgery”, Oper. Techn. Sport. Med. 23(4), 372- 384 (2015).
• [17] P. Zarychta, “Cruciate ligaments of the knee joint in the computer analysis”, in Information Technologies in Biomedicine, Advances in Intelligent Systems and Computing 283, 71-80 (2014).
• [18] P. Zarychta, “ACL and PCL of the knee joint in the computer diagnostics”, in 21st International Conference Mixed Design of Integrated Circuits and Systems MIXDES2014, 489-492 (2014).
• [19] A. Zarychta-Bargiela, P. Zarychta, “The importance of the features of the posteriori cruciate ligament in diagnosis”, in Information Technologies in Medicine, Advances in Intelligent Systems and Computing 471, 165-177 (2016).
• [20] W. Wieclawek and E. Pietka, “Watershed based intelligent scissors”, Comput. Med. Imag. Grap. 43, 122-129 (2015).
• [21] P. Zarychta and A. Zarychta-Bargiela, “Anterior and posterior cruciate ligament-extraction and 3D visualization”, in Information Technologies in Biomedicine, Advances in Intelligent and Soft Computing 69, 115-122 (2010).
• [22] M. Young, The technical writer’s handbook, Mill Valley, Toronto, 1989.
• [23] R.A. Fisher, “The use of multiple measurements in taxonomic problems”, Annals of Eugenics 7(2), 179-188 (1936).
• [24] S. Haykin, Neural networks: a comprehensive foundation, 2nd ed., Prentice Hall PTR, USA, 1998.
• [25] C. Cortes and V. Vapnik, “Support-vector networks”, Mach. Learn. 20(3), 273-297 (1995).
• [26] J. Czajkowska, M. Rudzki, and Z. Czajkowski, “A new fuzzy support vectors machine for biomedical data classification”, in 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 4676-4679 (2008).
• [27] J.S.R. Jang, “ANFIS: adaptive-network-based fuzzy inference system”, IEEE T. Syst. Man Cyb. 23(3), 665-685 (1993).
• [28] T. Takagi and M. Sugeno, “Fuzzy identification of systems and its applications to modeling and control”, IEEE T. Syst. Man Cyb. 15, 116-132 (1985).
• [29] J. Kawa and E. Pietka, “Image clustering with median and myriad spatial constraint enhanced FCM”, in Conference on Computer Recognition Systems, Advances in Soft Computing, 211-218 (2005).
• [30] J. Kennedy, R.C. Eberhart, “Particle swarm optimization”, in Proc. IEEE International Conference on Neural Networks, 1942-1948 (1995).
• [31] M.M. Millonas, “Swarms, phase transitions, and collective intelligence”, in Artificial Life III, Addison-Wesley (1994).
• [32] H.J. Escalante, et al., “Acute leukemia classification by ensemble particle swarm model selection”, Artif. Intell. Med. 55, 163-175 (2012).
• [33] C. Guarnizo, A. A. Orozco, M. A. Alvarez, “Optimal sampling frequency in wavelet-based signal feature extraction using particle swarm optimization”, in 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 993-996 (2013).
• [34] S. Alam, G. Dobbie, Y. S. Koh, P. Riddle, S. U. Rehman, “Research on particle swarm optimization based clustering: a systematic review of literature and techniques”, Swarm and Evolutionary Computation 17, 1-13 (2014).
• [35] I. Zyout, J. Czajkowska, M. Grzegorzek, “Multi-scale textural feature extraction and particle swarm optimization based model selection for false positive reduction in mammography”, Comput. Med. Imag. Grap. 46, Part 2, 95-107 (2015).
• [36] M. Galinska, P. Badura, “Swarm intelligence approach to 3D medical image segmentation”, in Information Technologies in Medicine, Advances in Intelligent Systems and Computing 471, 15-24 (2016).
• [37] P. Badura, E. Pietka, “3D fuzzy liver tumor segmentation”, in Information Technologies in Biomedicine, Lecture Notes in Bioinformatics 7339, 47-57 (2012).
• [38] M. V. Oliveira and R. Schirru, “Applying particle swarm optimization algorithm for tuning a neuro-fuzzy inference system for sensor monitoring”, Prog. Nucl. Energ. 51(1), 177-183 (2009).
• [39] S. Arlot, A. Celisse, “A survey of cross-validation procedures for model selection”, Statistics Surveys 4, 40-79 (2010).
• [40] J. Kawa, J. Juszczyk, B. Pycinski, P. Badura, and E. Pietka, “Radiological atlas for patient specific model generation”, in Information Technologies in Biomedicine, Advances in Intelligent Systems and Computing 284 (4), 69-82 (2014).

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).