Combination of hand-crafted and unsupervised learned features for ischemic stroke lesion detection from Magnetic Resonance Images

• Autorzy: Bharathi Praveen Gurunath , Agrawal Anita , Sundaram Ponraj , Sardesai Sanjay

Identyfikatory

DOI

10.1016/j.bbe.2019.01.003

• Języki publikacji: EN

Abstrakty

EN

Detection of ischemic stroke lesions plays a vital role in the assessment of stroke treatments such as thrombolytic therapy and embolectomy. Manual detection and quantification of stroke lesions is a time-consuming and cumbersome process. In this paper, we present a novel automatic method to detect acute ischemic stroke lesions from Magnetic Resonance Image (MRI) volumes using textural and unsupervised learned features. The proposed method proficiently exploits the 3D contextual evidence using a patch-based approach, which extracts patches randomly from the input MR volumes. Textural feature extraction (TFE) using Gray Level Co-occurrence Matrix (GLCM) and unsupervised feature learning (UFL) based on k-means clustering approaches are employed independently to extract features from the input patches. These features obtained from the two feature extractors are then given as input to the Random Forest (RF) classifier to discriminate between normal and lesion classes. A hybrid approach based on the combination of TFE using GLCM and UFL based on the k-means clustering is proposed in this work. Hybrid combination approach results in more discriminative feature set compared with the traditional approaches. The proposed method has been evaluated on the Ischemic Stroke Lesion Segmentation (ISLES) 2015 training dataset. The proposed method achieved an overall dice coefficient (DC) of 0.886, precision of 0.979, recall of 0.831 and accuracy of 0.8201. Quantitative measures show that the proposed approach is 28.4%, 27.14%, and 5.19% higher than the existing methods in terms of DC, precision, and recall, respectively.

Słowa kluczowe

EN

ischemic stroke lesion detection; magnetic resonance imaging; unsupervised feature learning; K-means; textural feature extraction; random forest classifier

PL

wykrywanie udaru mózgu; rezonans magnetyczny; algorytm k-średnich; ekstrakcja cech; las losowy

• 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: 410--425
• Opis fizyczny: Bibliogr. 67 poz., rys., tab., wykr.

Twórcy

autor

Bharathi Praveen Gurunath

• Department of Electrical and Electronics Engineering, BITS PILANI – K.K Birla Goa Campus, Goa, India

autor

Agrawal Anita

• Department of Electrical and Electronics Engineering, BITS PILANI – K.K Birla Goa Campus, Goa, India

autor

Sundaram Ponraj

• Department of Neurosurgery, Goa Medical College, Goa, India

autor

Sardesai Sanjay

• Department of Radiodiagnosis, Goa Medical College, Goa, India

Bibliografia

• [1] Truelsen T, Begg S, Mathers C. The global burden of cerebrovascular disease. Geneva: World Health Organisation; 2000.
• [2] Kim BJ, Kang HG, Kim HJ, Ahn SH, Kim NY, Warach S, et al. Magnetic resonance imaging in acute ischemic stroke treatment. J Stroke 2014;16(3):131–45.
• [3] Heiss WD, Kidwell CS. Imaging for prediction of functional outcome and assessment of recovery in ischemic stroke. Stroke 2014;45(4):1195–201.
• [4] Fiebach J, Schellinger P, Jansen O, Meyer M, Wilde P, Bender J, et al. CT and diffusion-weighted MR imaging in randomized order: diffusion-weighted imaging results in higher accuracy and lower interrater variability in the diagnosis of hyperacute ischemic stroke. Stroke 2002;33 (9):2206–10.
• [5] Audebert HJ, Fiebach JB. Brain imaging in acute ischemic stroke MRI or CT? Curr Neurol Neurosci Rep 2015;15(3):6–12.
• [6] Chalela JA, Kidwell CS, Nentwich LM, Luby M, Butman JA, Demchuk AM, et al. Magnetic resonance imaging and computed tomography in emergency assessment of patients with suspected acute stroke: a prospective comparison. Lancet 2007;369(9558):293–8.
• [7] Jeena R, Kumar S. A comparative analysis of MRI and CT brain images for stroke diagnosis. Emerging Research Areas and 2013 International Conference on Microelectronics, Communications and Renewable Energy (AICERA/ICMiCR), 2013 Annual International Conference on; 2013. pp. 1–5.
• [8] Karthik R, Menaka R. A multi-scale approach for detection of ischemic stroke from brain MR images using discrete curvelet transformation. Measurement 2017;100:223–32.
• [9] Sivakumar P, Ganeshkumar P. An efficient automated methodology for detecting and segmenting the ischemic stroke in brain MRI images. Int J Imaging Syst Technol 2017;27(3):265–72.
• [10] Bowles C, Qin C, Guerrero R, Gunn R, Hammers A, Dickie DA, et al. Brain lesion segmentation through image synthesis and outlier detection. NeuroImage: Clin 2017;16:643–58.
• [11] Kamnitsas K, Ledig C, Newcombe VF, Simpson JP, Kane AD, Menon DK, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 2017;36:61–78.
• [12] Pereira S, Meier R, McKinley R, Wiest R, Alves V, Silva CA, et al. Enhancing interpretability of automatically extracted machine learning features: application to a RBM-Random Forest system on brain lesion segmentation. Med Image Anal 2018;44:228–44.
• [13] Maier O, Wilms M, von der Gablentz J, Krämer UM, Münte TF, Handels H. Extra tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences. J Neurosci Methods 2015;240:89–100.
• [14] de Haan B, Clas P, Juenger H, Wilke M, Karnath H. Fast semi-automated lesion demarcation in stroke. NeuroImage: Clin 2015;9:69–74.
• [15] Chen L, Bentley P, Rueckert D. Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks. NeuroImage: Clin 2017;15:633–43.
• [16] Rajinikanth V, Satapathy SC. Segmentation of ischemic stroke lesion in brain MRI based on Social Group Optimization and Fuzzy-Tsallis Entropy. Arab J Sci Eng 2018;1–14.
• [17] Griffis JC, Allendorfer JB, Szaflarski JP. Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans. J Neurosci Methods 2016;257:97–108.
• [18] Karthikeyan S, Ezhilarasi M. Automatic stroke lesion segmentation from diffusion weighted MRI images. Int J Adv Eng Technol 2016;7(2):111–5.
• [19] Maier O, Schröder C, Forkert ND, Martinetz T, Handels H. Classifiers for ischemic stroke lesion segmentation: a comparison study. PLOS ONE 2015;10(12):1–18.
• [20] Alex V, M.S. KP, Chennamsetty SS, Krishnamurthi G. Generative adversarial networks for brain lesion detection. Medical Imaging 2017: Image Processing, vol. 10133, International Society for Optics and Photonics. 2017. pp. 1– 9. 101330G.
• [21] Gupta S, Mishra A, Menaka R. Ischemic stroke detection using image processing and ANN. Advanced Communication Control and Computing Technologies (ICACCCT), 2014 International Conference on; 2014. pp. 1416–20.
• [22] Kabir Y, Dojat M, Scherrer B, Forbes F, Garbay C. Multimodal MRI segmentation of ischemic stroke lesions. Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE; 2007. pp. 1595–8.
• [23] Kanchana R, Menaka R. A novel approach for characterisation of ischemic stroke lesion using histogram bin-based segmentation and gray level co-occurrence matrix features. Imaging Sci J 2017;65(2):124–36.
• [24] Tang Fh, Ng DK, Chow DH. An image feature approach for computer-aided detection of ischemic stroke. Comput Biol Med 2011;41(7):529–36.
• [25] Gillebert CR, Humphreys GW, Mantini D. Automated delineation of stroke lesions using brain CT images. NeuroImage: Clin 2014;4:540–8.
• [26] Rajini NH, Bhavani R. Computer aided detection of ischemic stroke using segmentation and texture features. Measurement 2013;46(6):1865–74.
• [27] Tyan YS, Wu MC, Chin CL, Kuo YL, Lee MS, Chang HY. Ischemic stroke detection system with a computer-aided diagnostic ability using an unsupervised feature perception enhancement method. J Biomed Imaging 2014;2014:19–31.
• [28] Rebouças Filho PP, Sarmento RM, Holanda GB, de Alencar Lima D. New approach to detect and classify stroke in skull CT images via analysis of brain tissue densities. Comput Methods Progr Biomed 2017;148:27–43.
• [29] Bentley P, Ganesalingam J, Jones ALC, Mahady K, Epton S, Rinne P, et al. Prediction of stroke thrombolysis outcome using CT brain machine learning. NeuroImage: Clin 2014;4:635–40.
• [30] Shalikar A, Ashouri MR, Shahraki MHN. A CAD system for automatic classification of brain strokes in CT images. Int J Mechatron Electr Comput Technol 2014;4(10):67–85.
• [31] Chawla M, Sharma S, Sivaswamy J, Kishore L. A method for automatic detection and classification of stroke from brain CT images. Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE; 2009. pp. 3581–4.
• [32] Sajjadi M, Amirfattahi R, Ahmadzadeh MR, Saghafi MA. A new filter bank algorithm for enhancement of early signs of ischemic stroke in brain CT images. Signal and Image Processing Applications (ICSIPA), 2011 IEEE International Conference on; 2011. pp. 384–9.
• [33] Sajjadi M, Karami M, Amirfattahi R, Bateni V, Ahamadzadeh MR, Ebrahimi B. A promising method of enhancement for early detection of ischemic stroke. J Res Med Sci 2012;17(9):843–9.
• [34] Hampton-Till J, Harrison M, Kühn AL, Anderson O, Sinha D, Tysoe S, et al. Automated quantification of stroke damage on brain computed tomography scans: e-ASPECTS. EMJ Neurol 2015;3:69–74.
• [35] Ali AH, Abdulsalam SI, Nema IS. Detection and segmentation of ischemic stroke using textural analysis on brain CT images. Int J Sci Eng Res 2015;6(2):396–400.
• [36] Usinskas A, Gleizniene R. Ischemic stroke region recognition based on ray tracing. Electronics Conference, 2006 International Baltic; 2006. pp. 1–4.
• [37] Ušinskas A, Dobrovolskis RA, Tomandl BF. Ischemic stroke segmentation on CT images using joint features. Informatica 2004;15(2):283–90.
• [38] Rebouças EdS, Braga AM, Sarmento RM, Marques RC, Rebouças Filho PP. Level set based on brain radiological densities for stroke segmentation in CT images. 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS); 2017. pp. 391–6.
• [39] Rekik I, Allassonnière S, Carpenter TK, Wardlaw JM. Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal. NeuroImage: Clin 2012;1(1):164–78.
• [40] Lee EJ, Kim YH, Kim N, Kang DW. Deep into the brain: artificial intelligence in stroke imaging. J Stroke 2017;19 (3):277–85.
• [41] Mirajkar PR, Bhagwat KA, Singh A, Ashalatha M. Acute ischemic stroke detection using wavelet based fusion of CT and MRI images. Advances in Computing, Communications and Informatics (ICACCI), 2015 International Conference on; 2015. pp. 1123–30.
• [42] Akkus Z, Galimzianova A, Hoogi A, Rubin DL, Erickson BJ. Deep learning for brain MRI segmentation: state of the art and future directions. J Dig Imaging 2017;30(4):449–59.
• [43] Maier O, Menze BH, von der Gablentz J, Häni L, Heinrich MP, Liebrand M, et al. Isles 2015 – a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med Image Anal 2017;35:250–69.
• [44] Breiman L. Random forests. Mach Learn 2001;45(1):5–32.
• [45] Van Leemput K, Maes F, Vandermeulen D, Suetens P. Automated model-based bias field correction of MR images of the brain. IEEE Trans Med Imaging 1999;18(10):885–96.
• [46] Haralick RM, Shanmugam K. Textural features for image classification. IEEE Trans Syst Man Cybern 1973;(6):610–21.
• [47] Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput 2006;18(7):1527–54.
• [48] Ranzato MA, Poultney C, Chopra S, Cun YL. Efficient learning of sparse representations with an energy-based model. Adv Neural Inf Process Syst 2007;19:1137–44.
• [49] Lee H, Battle A, Raina R, Ng AY. Efficient sparse coding algorithms. Adv Neural Inf Process Syst 2007;19:801–8.
• [50] Ranzato MA, lan Boureau Y, Cun YL. Sparse feature learning for Deep Belief Networks. In: Platt JC, Koller D, Singer Y, Roweis ST, editors. Advances in neural information processing systems, vol. 20. 2008. pp. 1185–92.
• [51] Vincent P, Larochelle H, Bengio Y, Manzagol PA. Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning;; 2008. p. 1096–103.
• [52] Coates A, Ng A, Lee H. An analysis of single-layer networks in unsupervised feature learning. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, vol. 15; 2011. p. 215–23.
• [53] Bell AJ, Sejnowski TJ. The ‘‘independent components' of natural scenes are edge filters. Vision Res 1997;37(23):3327–38.
• [54] Friedman J, Hastie T, Tibshirani R. The elements of statistical learning. vol. 1. New York, NY, USA: Springer series in statistics; 2001.
• [55] Mairal J, Bach F, Ponce J, et al. Sparse modeling for image and vision processing. Found Trends Comput Graph Vis 2014;8(2–3):85–283.
• [56] Gregor K, LeCun Y. Learning fast approximations of sparse coding. Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML'10; 2010. p. 399–406.
• [57] Hotelling H. Analysis of a complex of statistical variables into principal components. J Educ Psychol 1933;24(6):417.
• [58] Gislason PO, Benediktsson JA, Sveinsson JR. Random forests for land cover classification. Pattern Recogn Lett 2006;27 (4):294–300.
• [59] Liaw A, Wiener M. Classification and regression by random forest. R News 2002;2(3):18–22.
• [60] Dutil F, Havaei M, Pal C, Larochelle H, Jodoin P. A convolutional neural network approach to brain lesion segmentation. Ischemic Stroke Lesion Segment 2015;51–6.
• [61] Kamnitsas K, Chen L, Ledig C, Rueckert D, Glocker B. Multi-scale 3D convolutional neural networks for lesion segmentation in brain MRI. Ischemic Stroke Lesion Segment 2015;13–6.
• [62] Reza SM, Pei L, Iftekharuddin K. Ischemic stroke lesion segmentation using local gradient and texture features. Ischemic Stroke Lesion Segment 2015;23–6.
• [63] Haeck T, Maes F, Suetens P. Automated model-based segmentation of ischemic stroke in MR images. International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries; 2015. pp. 246–53.
• [64] Mahmood Q, Basit A. Automatic ischemic stroke lesion segmentation in multi-spectral MRI images using random forests classifier. International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries; 2015. pp. 266–74.
• [65] Chen L, Bentley P, Rueckert D. A novel framework for sub-acute stroke lesion segmentation based on random forest. Ischemic Stroke Lesion Segment 2015;9–12.
• [66] Robben D, Christiaens D, Rangarajan JR, Gelderblom J, Joris P, Maes F, et al. A voxel-wise, cascaded classification approach to ischemic stroke lesion segmentation. International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries; 2015. pp. 254–65.
• [67] Maier O, Wilms M, Handels H. Random forests with selected features for stroke lesion segmentation. Ischemic Stroke Lesion Segment 2015;17–22.

Uwagi

PL

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