No Access

SEGMENTATION AND CLASSIFICATION OF ISCHEMIC STROKE USING OPTIMIZED FEATURES IN BRAIN MRI

Asit Subudhi

Department of Electronics & Communication Engineering, ITER, Siksha ‘O’ Anusandhan, India

Search for more papers by this author

Sanatnu Sahoo

Department of Electronics & Communication Engineering, ITER, Siksha ‘O’ Anusandhan, India

Search for more papers by this author

Pradyut Biswal

Department of Electronics & Communication Engineering, IIIT, Bhubaneswar, Odisha, India

Search for more papers by this author

, and

Sukanta Sabut

Department of Electronics Engineering, Ramrao Adik Institute of Technology, Navi Mumbai, India

E-mail Address: sukanta207@gmail.com

Corresponding author.

Search for more papers by this author

https://doi.org/10.4015/S1016237218500114Cited by:12 (Source: Crossref)

Abstract

Detection of ischemic stroke using brain magnetic resonance imaging (MRI) images is vital and a challenging task in clinical practice. We propose a novel method based on optimization technique to identify stroke lesion in diffusion-weighted imaging (DWI) MRI sequences of the brain. The algorithm was tested in a specific slice having large area of stroke region from a series of 292 real-time images obtained from different stroke affected subjects from IMS and SUM Hospital. The proposed method consists of pre-processing, segmentation, extraction of important features and classification of stroke type. The particle swarm optimization (PSO) and Darwinian particle swarm optimization (DPSO) algorithms were applied in segmenting the stroke lesions. The important features were extracted with the gray-level co-occurrence matrix (GLCM) algorithm and in decision making process, the feature set is classified into three types of stroke according to The Oxfordshire Community Stroke Project (OCSP) classification using support vector machine (SVM) classifier. The lesion area was segmented effectively with DPSO process with classification weighted accuracy of 90.23%, which is higher than PSO method having weighted accuracy of 85.19%. Similarly, the values of different measured parameters were high in DPSO technique, the computational time was also higher in DPSO method for segmenting the stroke lesions. These results confirm that the DPSO-based approach with SVM classifier is an effective way to identify the decision making process of ischemic stroke lesion in MRI images of the brain.

Keywords:

References

1. Kabir Y, Dojat M, Scherrer B, Forbes F, Garbay C , Multimodal MRI segmentation of ischemic stroke lesions, Conf Proc IEEE Eng Med Biol Soc, pp. 1595–1598, 2007. Google Scholar
2. MacIntosh BJ, Graham SJ , Magnetic resonance imaging to visualize stroke and characterize stroke recovery: A review, Front Neurol 4 :1–14, 2013. Web of Science, Google Scholar
3. Lutsep HL, Albers GW, DeCrespigny A, Kamat GN, Marks MP, Moseley ME , Clinical utility of diffusion weighted magnetic resonance imaging in the assessment of ischemic stroke, Ann Neuro 41 (5) :574–580, 1997. Web of Science, Google Scholar
4. Newcombe VF, Das T, Cross JJ , Diffusion imaging in neurological disease, J Neurol 260 (1) :335–342, 2013. Web of Science, Google Scholar
5. Fiez JA, Damasio H, Grabowski TJ , Lesion segmentation and manual warping to a reference brain: Intra- and inter-observer reliability, Human Brain Mapping 9 :192–211, 2000. Web of Science, Google Scholar
6. Seghier ML, Ramlackhansingh A, Crinion J, Leff AP, Price CJ , Lesion identification using unified segmentation-normalization models and fuzzy clustering, Neuroimage 41 (4) :1253–1266, 2008. Web of Science, Google Scholar
7. Wilke M, de Haan B, Juenger H, Karnath HO , Manual, semi-automated and automated delineation of chronic brain lesions: A comparison of methods, Neuroimage 56 (4) :2038–2046, 2011. Web of Science, Google Scholar
8. Gonzalez-Villaa S, Arnau O, Valverde S, Wang L, Zwiggelaar R, Llado X , A review on brain structures segmentation in magnetic resonance imaging, Artif Intell Med 73 :45–69, 2016. Web of Science, Google Scholar
9. Kuoa WF, Linc CY, Suna YN , Brain MR images segmentation using statistical ratio: Mapping between watershed and competitive hopfield clustering network algorithms, Comput Methods Programs Biomed 1 (3) :191–198, 2008. Web of Science, Google Scholar
10. Clark MC, Hall, LO, Goldgof DB, Velthuizen R, Murtagh FR, Silbiger MS , Automatic tumor segmentation using knowledge-based techniques, IEEE Trans Med Imaging 17 (2) :187–201, 1998. Web of Science, Google Scholar
11. Vinitski S, Seshagiri S, Mohamed FB et al., Tissue characterization by MR: Data segmentation using 3D-feature map, Vernazza G, Venetsanopoulos AN, Braccini C (eds.), Image Processing Theory and Applications, Elsevier Science Publishers, Amsterdam, pp. 325–328, 1993. Google Scholar
12. Menze BH, Van Leemput K, Lashkari D, Riklin-Raviv T, Geremia E, Alberts E, Gruber P, Wegener S, Weber MA, Szekely G, Ayache N, Golland P , A generative probabilistic model and discriminative extensions for brain lesion segmentation-with application to tumor and stroke, IEEE Trans Med Imaging 35 (4) :933–946, 2016. Web of Science, Google Scholar
13. Matesin M, Loncaric S, Petravic D , A rule-based approach to stroke lesion analysis from CT brain images, Proc 2nd Int Symp Image and Signal Processing and Analysis, pp. 219–223, 2011. Google Scholar
14. Haan Bde, Clas P, Juenger H, Wilke , Karnath HO , Fast semi-automated lesion demarcation in stroke, NeuroImage Clin 9 :69–74, 2015. Web of Science, Google Scholar
15. Hamarneh G, Li X , Watershed segmentation using prior shape and appearance knowledge, Image Vis Comput 27 (1) :59–68, 2009. Web of Science, Google Scholar
16. Macenko M, Celenk M, Ma L , Lesion detection using morphological watershed segmentation and model based, 18th Int Conf on Pattern Recognition, pp. 1–4, 2006. Google Scholar
17. Tang F, Ng KS, Chow HK , An image feature approach for computer-aided detection of ischemic stroke, Comput Biol Med 41 :529–536, 2011. Web of Science, Google Scholar
18. Rajini NH, Bhavani R , Computer aided detection of ischemic stroke using segmentation and texture features, Measurement 46 :1865–1874, 2013. Web of Science, Google Scholar
19. Menaka R, Karthik R, Gupta R, Mishra A , Ischemic stroke detection from MRI diffusion images using bifurcation analysis of texture features and fuzzy based segmentation, Int J Tomogr Simul 28 (2) :117–125, 2015. Google Scholar
20. Mustafa S, Abbosh A, Henin B, Ireland D , Brain stroke detection using continuous wavelets transform matching filters, Proc Int Biomedical Engg Conf, pp. 194–197, 2012. Google Scholar
21. Zhang Y, Dong Z, Wu L, Wang S , A hybrid method for MRI brain image classification, Exp Syst Appl 38 (8) :10049–1115, 2011. Web of Science, Google Scholar
22. Huang S, Shen Q, Duong TQ , Artificial neural network prediction of ischemic tissue fate in acute stroke imaging, J Cereb Blood Flow Metab 30 :1661–1670, 2010. Web of Science, Google Scholar
23. Cuingnet R, Rosso C, Lehericy S et al., Spatially regularized SV M for the detection of brain areas associated with stroke outcome, Medical Image Computing and Computer-Assisted Intervention-MICCAI 2010, Lecture Notes in Computer Science, Vol. 6361, pp. 316–323, 2010. Google Scholar
24. Takahashi N, Lee Y, Tsai DY, Matsuyama E, Kinoshita T, Ishii K , An automated detection method for the MCA dot sign of acute stroke in unenhanced CT, Radiol Phys Technol 7 :79–88, 2014. Google Scholar
25. De A, Das RL, Bhattacharjee AK, Sharma D , Masking based segmentation of diseased MRI images, IEEE Int Conf on Information Science and Applications (ICISA), South Korea, pp. 1–7, 2010. Google Scholar
26. Si T, De A, Bhattacharjee AK , Grammatical swarm based segmentation methodology for lesion segmentation in brain MRI, Int J Computer Appl 121 (4) :1–8, 2015. Google Scholar
27. Maier O, Wilms M, Gablentz J. Von der U, Kramer M, Munte TF, Handels, H , Extra tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences, J Neurosci Methods 240 :89–100, 2015. Web of Science, Google Scholar
28. Griffis JC, Allendorfer JB, Jerzy P, Szaflarski, JP , Voxel-based Gaussian naive Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans, J Neurosci Methods 257 :97–108, 2016. Web of Science, Google Scholar
29. Karthik R, Menaka R , A multi-scale approach for detection of ischemic stroke from brain MR images using discrete curvelet transformation, Measurement 100 :223–232, 2017. Web of Science, Google Scholar
30. Kennedy J, Eberhart, R , Particle swarm optimization, Proc. IEEE Int Conf Neural Networks, Vol. 4, pp. 1942–1948, 1995. Google Scholar
31. Chander A, Chatterjee A, Siarry P , A new social and momentum component adaptive PSO algorithm for image segmentation, Exp Syst Appl 38 :4998–5004, 2011. Web of Science, Google Scholar
32. Borsotti M, Campadelli P, Schettini R , Quantitative evaluation of color image segmentation results, Pattern Recognit Lett 19 :741–747, 1998. Web of Science, Google Scholar
33. Couceiro MS, Rocha RP, Ferreira NM, Machado AT , Introducing the fractional-order Darwinian PSO, SIViP 6 :343–350, 2012. Google Scholar
34. Tillett J, Rao T, Sahin F, Rao R, Darwinian particle swarm optimization, University of Rochester, USA, 2005. Google Scholar
35. Ghamisi P, Couceiro MS, Benediktsson JA, Ferreira NF , An efficient method for segmentation of images based on fractional calculus and natural selection, Expert Syst Appl 39 :12407–12417, 2012. Web of Science, Google Scholar
36. Hua BO, Fu-long MA, Li-cheng JIAO , Research on computation of GLCM of image texture, Acta Automatica Sin 34 :155–158, 2006. Google Scholar
37. Cortes C, Vapnik V , Support-vector networks, Mach Learning 20 (3) :273–297, 1995. Web of Science, Google Scholar
38. Muda AF, Saad NM, Abu SR, Muda S, Abdullah AR . Brain lesion segmentation using fuzzy c-means on diffusion-weighted imaging, ARPN J Eng Appl Sci 10 :1138–1144, 2015. Google Scholar
39. Mitra J, Bourgeat P, Fripp J, Ghose S, Rose S, Salvado O, Connelly A, Campbell B, Palmer S, Sharma G, Christensen S, Carey L . Lesion segmentation from multimodal MRI using random forest following ischemic stroke, Neuroimage 98 :324–335, 2014. Web of Science, Google Scholar