The use of the Hellwig's method for feature selection in the detection of myeloma bone destruction based on radiographic images

• Autorzy: Omiotek Zbigniew , Stepanchenko Olga , Wójcik Waldemar , Legieć Wojciech , Szatkowska Malgorzata

Identyfikatory

DOI

10.1016/j.bbe.2018.11.008

• Języki publikacji: EN

Abstrakty

EN

The radiological test is cost-effective, widely available, allows for the visualisation of large areas of the skeleton and can identify long bones potentially at risk for fractures in osteolysis sites. Therefore, radiology is often used in the early stages of multiple myeloma, in the detection and characterisation of complications, and in the assessment of the patient's response to treatment. The accuracy of this method can be improved through the use of appropriate algorithms of computer image processing and analysis. In the study, the feature vector based on humerus CR images was extracted. As a result of the analysis, 279 image descriptors were obtained. Hellwig's method in the selection process was applied. It found the set of feature combinations of the largest integral index of information capacity. To evaluate these combinations, 11 classifiers were built and tested. As a result, 2 feature sets were identified that provided the highest classification accuracy in combination with the K-NN classifier. The 9-NN classifier for the first combination (2 features) was used and 5-NN for the second one (3 features). The classification accuracy (depending on the quality index used) was as follows: overall classification accuracy – 93%, classification sensitivity – 92%, classification specificity – 96%, positive predictive value – 96% and negative predictive value – 93%. Results show that: (1) the use of humerus CR images may be useful in the detection of bone damages caused by multiple myeloma; (2) the Hellwig's method is effective in the feature selection of the analysed kind of images.

Słowa kluczowe

EN

Hellwig's method; feature selection; texture classification; computed radiography; multiple myeloma

PL

metoda Hellwiga; selekcja cech; klasyfikacja tekstur; radiografia komputerowa; szpiczak mnogi

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 2
• Strony: 328--338
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wykr.

Twórcy

autor

Omiotek Zbigniew

• Lublin University of Technology, Faculty of Electrical Engineering and Computer Science, Nadbystrzycka 38d, 20-618 Lublin, Poland

autor

Stepanchenko Olga

• Institute of Automatics, Cybernetics and Computer Engineering, National University of Water and Environmental Engineering, Rivne, Ukraine

autor

Wójcik Waldemar

• Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, Lublin, Poland

autor

Legieć Wojciech

• Independent Clinical Transplantology Unit, Medical University of Lublin, Lublin, Poland

autor

Szatkowska Malgorzata

• Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, Lublin, Poland

Bibliografia

• [1] Ghosh S, Wadhwa P, Kumar A, Pai KM, Seshadri S, Manohar C, et al. Abnormal radiological features in a multiple myeloma patient: a case report and radiological review of myelomas. Dentomaxillofac Radiol 2011;40:513–8.
• [2] Healy CF, Murray JG, Eustace SJ, Madewell J, O'Gorman PJ, O'Sullivan P, et al. Multiple myeloma: a review of imaging features and radiological techniques. Bone Marrow Res 2011. http://dx.doi.org/10.1155/2011/583439.
• [3] Durie BG, Salmon SE. A clinical staging system for multiple myeloma. Correlation of measured myeloma cell mass with presenting clinical features, response to treatment, and survival. Cancer 1975;36:842–54.
• [4] Snapper I, Khan A. Myelomatosis: fundamentals and clinical features. Baltimore: University Park Press; 1971.
• [5] Scane AC, Masud T, Johnson FJ, Francis RM, et al. The reliability of diagnosing osteoporosis from spinal radiographs. Age Ageing 1994;23:283–6.
• [6] Collins CD. Multiple myeloma. Cancer Imag 2004;14:47–53.
• [7] Lecouvet FE, Malghem J, Michaux L, Maldague B, Ferrant A, Michaux JL, et al. Skeletal survey in advanced multiple myeloma: radiographic versus MR imaging survey. Br J Haematol 1999;106:35–9.
• [8] Dimopoulos M, Kyle R, Fermand JP, Rajkumar SV, San Miguel J, Chanan-Khan A, et al. Consensus recommendations for standard investigative workup: report of the International Myeloma Workshop Consensus Panel 3. Blood 2011;117(18):4701–5. http://dx.doi.org/10.1182/blood-2010-10-299529.
• [9] Rajkumar SV. Evolving diagnostic criteria for multiple myeloma. Hematology Am Soc Hematol Educ Program 2015;2015:272–8. http://dx.doi.org/10.1182/asheducation-2015.1.272.
• [10] Dutoit JC, Verstraete KL. MRI in multiple myeloma: a pictorial review of diagnostic and post-treatment findings. Insights Imaging 2016;7(4):553–69.
• [11] Hanbali A, Hassanein M, Rasheed W, Aljurf M, Alsharif F, et al. The evolution of prognostic factors in multiple myeloma. Adv Hematol 2017;2017:4812637. http://dx.doi.org/10.1155/2017/4812637.
• [12] Hanrahan CJ, Christensen CR, Crim JR. Current concepts in the evaluation of multiple myeloma with MR imaging and FDG PET/CT. Radiographics 2010;30(1):127–42.
• [13] Ferraro R, Agarwal A, Martin-Macintosh EL, Peller PJ, Subramaniam RM. MR imaging and PET/CT in diagnosis and management of multiple myeloma. Radiographics 2015;35(2):438–54.
• [14] Zamagni E, Cavo M. The role of imaging techniques in the management of multiple myeloma. Br J Haematol 2012;159 (5):499–513.
• [15] Rubini G, Niccoli-Asabella A, Ferrari C, Racanelli V, Maggialetti N, Dammacco F. Myeloma bone and extra-medullary disease: role of PET/CT and other whole-body imaging techniques. Crit Rev Oncol Hematol 2016;101:169–83.
• [16] Bhutani M, Turkbey B, Tan E, Korde N, Kwok M, Manasanch EE, et al. Bone marrow abnormalities and early bone lesions in multiple myeloma and its precursor disease: a prospective study using functional and morphologic imaging. Leuk Lymphoma 2016;57(5):1114–21.
• [17] Tian C, Wang L, Wu L, Zhu L, Xu W, Ye Z, et al. Clinical characteristics and prognosis of multiple myeloma with bone-related extramedullary disease at diagnosis. Biosci Rep 2018;38(3). http://dx.doi.org/10.1042/BSR20171697.
• [18] Zhang Y, Zhao C, Liu H, Hou H, Zhang H. Multiple metastasis-like bone lesions in scintigraphic imaging. J Biomed Biotechnol 2012;2012:957364. http://dx.doi.org/10.1155/2012/957364.
• [19] Saeedizadeh Z, Mehri Dehnavi A, Talebi A, Rabbani H, Sarrafzadeh O, Vard A, et al. Automatic recognition of myeloma cells in microscopic images using bottleneck algorithm, modified watershed and SVM classifier. J Microsc 2016;261(1):46–56.
• [20] Martinez-Martinez F, Kybic J, Lambert L. Automatic detection of bone marrow infiltration by multiple myeloma detection in low-dose CT. IEEE International Conference on Image Processing (ICIP); 2015.
• [21] Martínez-Martínez F, Kybic J, Lambert L, Mecková Z, et al. Fully-automated classification of bone marrow infiltration in low-dose CT of patients with multiple myeloma based on probabilistic density model and supervised learning. Comput Biol Med 2016. http://dx.doi.org/10.1016/j.compbiomed.2016.02.001.
• [22] Fränzle A, Hillengass J, Bendl R. Spinal focal lesion detection in multiple myeloma using multimodal image features. Proc SPIE 2015;9414. http://dx.doi.org/10.1117/12.2081990.
• [23] Hering J, Kybic J, Lambert L. Detecting multiple myeloma via generalized multiple-instance learning. Proc SPIE 2018;10574. http://dx.doi.org/10.1117/12.2293112.
• [24] Anand VK, Krishnamurthi G, Balaji R. Semi-automatic identification of myelomatous lesions from multi modal MR images. ECR 2018/C-2274. https://doi.org/10.1594/ecr2018/C-2274.
• [25] Haralick R. Statistical and structural approaches to texture. Proc IEEE 1979;67(5):786–804.
• [26] Haralick R, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern 1973;3 (6):610–21.
• [27] Hu Y, Dennis T. Textured image segmentation by context enhanced clustering. IEE Proc Visual Image Signal Process 1994;141(6):413–21.
• [28] Lerski R, Straughan K, Shad L, Boyce D, Blüml S, Zuna I, et al. MR image texture analysis – an approach to tissue characterization. Magnet Reson Imaging 1993;11:873–87.
• [29] Omiotek Z. Fractal analysis of the grey and binary images in diagnosis of Hashimoto's thyroiditis. Biocybern Biomed Eng 2017;37(4):655–65.
• [30] Omiotek Z. Improvement of the classification quality in detection of Hashimoto's disease with a combined classifier approach. Proc Inst Mech Eng H 2017;231(8):774–82.
• [31] MaZda, www.eletel.p.lodz.pl/programy/cost/progr_mazda.html; 2018 [accessed 13.06.18].
• [32] Hellwig Z. On the optimal choice of predictors. In: Gostkowski Z, editor. Toward a system of quantitative indicators of components of human resources development. Paris: UNESCO; 1968.
• [33] Breiman L, Friedman J, Olshen RA, Stone CJ, et al. Classification and regression trees. London: CRC Press; 1984.
• [34] Enas GG, Chai SC. Choice of the smoothing parameter and efficiency of the k-nearest neighbor classification. Comput Math Appl 1986;12:235–44.
• [35] Liao SH, Chu PH, Hsiao PY. Data mining techniques and applications –a decade review from 2000 to 2011. Expert Syst Appl 2012;39:11303–11.
• [36] Quinlan JR. Induction of decision trees. Mach Learn 1986;1:81–106.
• [37] Venables WN, Ripley BD. Modern applied statistics with S-PLUS. Berlin: Springer; 1998.
• [38] Breiman L. Bagging predictors. Mach Learn 1996;24:123–40.
• [39] Breiman L. Random forests. Mach Learn 2001;45:5–32.
• [40] Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci Int 1996;55:119–39.
• [41] Hothorn T, Lausen B. Bundling classifiers by bagging trees. Comput Stat Data Anal 2005;49(4):1068–78.
• [42] Raudys SJ, Jain A. Small sample size effects in statistical pattern recognition: recommendations for practitioners. IEEE Trans PAMI 1991;13(3):252–64.
• [43] Jain AK, Duin RPW, Mao J. Statistical pattern recognition: a review. IEEE Trans PAMI 2000;22(1):4–37.

Uwagi

PL

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