access icon free Ensemble-based glioma grade classification using Gabor filter bank and rotation forest

This work aims at developing an automated ensemble-based glioma grade classification framework that classifies glioma into low-grade glioma (LGG) and high-grade glioma (HGG). Discriminant features are extracted using the Gabor filter bank and concatenated in a vectorised form. The feature set is then divided into k subsets of features. An ensemble of base classifiers known as rotation forest is employed for classification purpose. Independent components analysis (ICA) is applied on every feature subset and independent features are extracted. Each classifier in the ensemble is trained with these independent features from all the subset of features. These k feature subsets are responsible for different rotations during the training phase. This results in classifier diversity in the ensemble. Extensive experiments are conducted on benchmark BraTS 2017 data set and comparative analysis reveals that the proposed framework outperforms the competitive techniques in terms of various performance metrics. Data-augmentation technique, synthetic minority over-sampling technique is applied to oversample minority class samples alleviate class biasness problem. The proposed classification framework achieves an accuracy of 98.63%, dice similarity coefficient of 0.98 and sensitivity of 0.96. The authors conduct different comparative experiments with state-of-the-art ensemble-based, deep learning-based and traditional machine learning-based classification approaches to validate the performance of the proposed framework.

Inspec keywords: independent component analysis; tumours; learning (artificial intelligence); biomedical MRI; brain; Gabor filters; pattern classification; image classification; medical image processing; image segmentation; feature extraction; support vector machines; Bayes methods

Other keywords: discriminant features; automated ensemble-based glioma grade classification framework; classifier diversity; deep learning-based; rotation forest; independent features; traditional machine learning-based classification; different rotations; base classifiers; k feature subsets; feature set; synthetic minority over-sampling technique; feature subset; independent components analysis; state-of-the-art ensemble-based; Gabor filter bank; high-grade glioma; classification purpose

Subjects: Knowledge engineering techniques; Medical magnetic resonance imaging and spectroscopy; Combinatorial mathematics; Biomedical magnetic resonance imaging and spectroscopy; Other topics in statistics; Data handling techniques; Biology and medical computing; Patient diagnostic methods and instrumentation; Optical, image and video signal processing; Other topics in statistics; Image recognition; Computer vision and image processing techniques

References

    1. 1)
      • 7. Sun, L., Zhang, S.: ‘Multi-view 3D CNN with dense CRF for brain tumor segmentation and survival prediction’. Proc. Pre-Conf. 7th MICCAI BraTS Challenge, Shenzhen, People's Republic of China, 2018, pp. 448456.
    2. 2)
      • 8. Abd-Ellah, M.K., Awad, A.I., Khalaf, A.A., et al: ‘Two-phase multi-model automatic brain tumour diagnosis system from magnetic resonance images using convolutional neural networks’, EURASIP J. Image Video Process., 2018, 2018, (1), p. 97.
    3. 3)
      • 29. Comon, P.: ‘Independent component analysis, a new concept?’, Signal Process., 1994, 36, (3), pp. 287314.
    4. 4)
      • 16. Li, Q., Gao, Z., Wang, Q., et al: ‘Glioma segmentation with a unified algorithm in multimodal MRI images’, IEEE Access, 2018, 6, pp. 95439553.
    5. 5)
      • 30. Kuncheva, L.I., Whitaker, C.J.: ‘Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy’, Mach. Learn., 2003, 51, (2), pp. 181207.
    6. 6)
      • 42. Saouli, R., Akil, M., Kachouri, R.: ‘Fully automatic brain tumor segmentation using end-to-end incremental deep neural networks in MRI images’, Comput. Methods Programs Biomed., 2018, 166, pp. 3949.
    7. 7)
      • 25. Field, D.J.: ‘Relations between the statistics of natural images and the response properties of cortical cells’, Josa a, 1987, 4, (12), pp. 23792394.
    8. 8)
      • 3. Singh, R., Goel, A., Raghuvanshi, D.K.: ‘Computer-aided diagnostic network for brain tumor classification employing modulated Gabor filter banks’, Vis. Comput., 2020, pp. 115, https://doi.org/10.1007/s00371-020-01977-4.
    9. 9)
      • 38. Huda, S., Yearwood, J., Jelinek, H.F., et al: ‘A hybrid feature selection with ensemble classification for imbalanced healthcare data: a case study for brain tumor diagnosis’, IEEE Access, 2016, 4, pp. 91459154.
    10. 10)
      • 2. Girshick, R., Donahue, J., Darrell, T., et al: ‘Rich feature hierarchies for accurate object detection and semantic segmentation’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 580587.
    11. 11)
      • 28. Rodriguez, J.J., Kuncheva, L.I., Alonso, C.J.: ‘Rotation forest: a new classifier ensemble method’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (10), pp. 16191630.
    12. 12)
      • 45. Ali, H.A.M., Ahmed, M.A., Hussein, E.M.: ‘MRI brain tumour segmentation based on multimodal clustering and level-set method’. 2018 Int. Conf. on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), 2018, August, pp. 15.
    13. 13)
      • 18. Lyksborg, M., Puonti, O., Agn, M., et al: ‘An ensemble of 2D convolutional neural networks for tumor segmentation’. Scandinavian Conf. on Image Analysis, 2015, June, pp. 201211.
    14. 14)
      • 1. Tumor Types: Understanding Brain Tumors. National brain tumor society, 2018.
    15. 15)
      • 35. Bakas, S., Reyes, M., Jakab, A., et al: ‘Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge’, arXiv preprint arXiv:1811.02629, 2018.
    16. 16)
      • 26. Jones, J.P., Palmer, L.A.: ‘An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex’, J. Neurophysiol., 1987, 58, (6), pp. 12331258.
    17. 17)
      • 22. Barcelos, C.A.Z., Pires, V.B.: ‘An automatic based nonlinear diffusion equations scheme for skin lesion segmentation’, Appl. Math. Comput., 2009, 215, (1), pp. 251261.
    18. 18)
      • 19. Barzegar, Z., Jamzad, M.: ‘A reliable ensemble-based classification framework for glioma brain tumor segmentation’, SIViP, 2020, 14, pp. 15911599, https://doi.org/10.1007/s11760-020-01699-z.
    19. 19)
      • 33. Menze, B.H., Jakab, A., Bauer, S., et al: ‘The multimodal brain tumor image segmentation benchmark (BRATS)’, IEEE Trans. Med. Imaging, 2014, 34, (10), pp. 19932024.
    20. 20)
      • 21. Festa, J., Pereira, S., Mariz, J.A., et al: ‘Automatic brain tumor segmentation of multi-sequence MR images using random decision forests’. Proc. of NCI-MICCAI BRATS, Berlin, Germany, 2013, vol. 1, pp. 2326.
    21. 21)
      • 9. Swati, Z.N.K., Zhao, Q., Kabir, M., et al: ‘Brain tumor classification for MR images using transfer learning and fine-tuning’, Comput. Med. Imaging Graph., 2019, 75, pp. 3446.
    22. 22)
      • 40. Gupta, N., Bhatele, P., Khanna, P.: ‘Glioma detection on brain MRIs using texture and morphological features with ensemble learning’, Biomed. Signal Process. Control, 2019, 47, pp. 115125.
    23. 23)
      • 43. Vijay, V., Kavitha, A.R., Rebecca, S.R.: ‘Automated brain tumor segmentation and detection in MRI using enhanced Darwinian particle swarm optimization (EDPSO)’, Procedia Comput. Sci., 2016, 92, pp. 475480.
    24. 24)
      • 17. Dietterich, T.G.: ‘An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization’, Mach. Learn., 2000, 40, (2), pp. 139157.
    25. 25)
      • 23. Perona, P., Malik, J.: ‘Scale-space and edge detection using anisotropic diffusion’, IEEE Trans. Pattern Anal. Mach. Intell., 1990, 12, (7), pp. 629639.
    26. 26)
      • 20. Thaha, M.M., Kumar, K.P.M., Murugan, B.S., et al: ‘Brain tumor segmentation using convolutional neural networks in MRI images’, J. Med. Syst., 2019, 43, (9), p. 294.
    27. 27)
      • 32. Margineantu, D.D., Dietterich, T.G.: ‘Pruning adaptive boosting’, ICML'97, 1997.
    28. 28)
      • 37. Breiman, L.: ‘Random forests’, Mach. Learn., 2001, 45, (1), pp. 532.
    29. 29)
      • 11. Xu, C., Xu, L., Gao, Z., et al: ‘Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture’, Med. Image Anal., 2018, 50, pp. 8294.
    30. 30)
      • 31. Kuncheva, L.I.: ‘Diversity in multiple classifier systems’, Inf. Fusion, 2005, 1, (6), pp. 34.
    31. 31)
      • 4. Hu, K., Gan, Q., Zhang, Y., et al: ‘Brain tumor segmentation using multi-cascaded convolutional neural networks and conditional random field’, IEEE Access, 2019, 7, pp. 9261592629.
    32. 32)
      • 5. Razzak, M.I., Imran, M., Xu, G.: ‘Efficient brain tumor segmentation with multiscale two-pathway-group conventional neural networks’, IEEE. J. Biomed. Health Inf., 2018, 23, (5), pp. 19111919.
    33. 33)
      • 34. Bakas, S., Akbari, H., Sotiras, A., et al: ‘Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features’, Sci. Data, 2017, 4, p.170117.
    34. 34)
      • 13. Caver, E., Chang, L., Zong, W., et al: ‘Automatic brain tumor segmentation using a U-net neural network’. Pre-Conf. Proc. of the 7th MICCAI BraTS Challenge, Detroit, MI, USA, 2018, pp. 6373.
    35. 35)
      • 36. Chawla, N.V., Bowyer, K.W., Hall, L.O., et al: ‘SMOTE: synthetic minority over-sampling technique’, J. Artif. Intell. Res., 2002, 16, pp. 321357.
    36. 36)
      • 27. Lades, M., Vorbruggen, J.C., Buhmann, J., et al: ‘Distortion invariant object recognition in the dynamic link architecture’, IEEE Trans. Comput., 1993, 42, (3), pp. 300311.
    37. 37)
      • 39. Minz, A., Mahobiya, C.: ‘MR image classification using Adaboost for brain tumor type’. 2017 IEEE 7th Int. Advance Computing Conf. (IACC), 2017, January, pp. 701705.
    38. 38)
      • 47. Aljawarneh, S., Yassein, M.B., Aljundi, M.: ‘An enhanced J48 classification algorithm for the anomaly intrusion detection systems’, Cluster Comput., 2019, 22, (5), pp. 1054910565.
    39. 39)
      • 15. Cabezas, M., Valverde, S., González-Villà, S., et al: ‘Survival prediction using ensemble tumor segmentation and transfer learning’, arXiv preprint arXiv:1810.04274, 2018.
    40. 40)
      • 41. Bauer, S, Fejes, T.: ‘Segmentation of brain tumor images based on integrated hierarchical classification and regularization’. Proc. MICCAI BRATS, Nice, France, 2012.
    41. 41)
      • 14. Feng, X., Tustison, N.J., Patel, S.H., et al: ‘Brain tumor segmentation using an ensemble of 3d u-nets and overall survival prediction using radiomic features’, Front. Comput. Neurosci., 2020, 14, p. 25.
    42. 42)
      • 12. Marcinkiewicz, M., Nalepa, J., Lorenzo, P.R., et al: ‘Automatic brain tumor segmentation using a two-stage multi-modal fcnn’ (Springer, Spain, 2018), pp. 314321.
    43. 43)
      • 10. Behrmann, J., Etmann, C., Boskamp, T., et al: ‘Deep learning for tumor classification in imaging mass spectrometry’, Bioinformatics, 2018, 34, (7), pp. 12151223.
    44. 44)
      • 46. Gupta, N., Bhatele, P., Khanna, P.: ‘Identification of gliomas from brain MRI through adaptive segmentation and run length of centralized patterns’, J. Comput. Sci., 2018, 25, pp. 213220.
    45. 45)
      • 44. Kumar, A., Ashok, A., Ansari, M.A.: ‘Brain tumor classification using hybrid model Of PSO and SVM classifier’. 2018 Int. Conf. on Advances in Computing, Communication Control and Networking (ICACCCN), 2018, October, pp. 10221026.
    46. 46)
      • 6. Chen, H., Dou, Q., Yu, L., et al: ‘Voxresnet: deep voxelwise residual networks for brain segmentation from 3D MR images’, NeuroImage, 2018, 170, pp. 446455.
    47. 47)
      • 24. Daugman, J.G.: ‘Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression’, IEEE Trans. Acoust. Speech Signal Process., 1988, 36, (7), pp. 11691179.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2020.0908
Loading

Related content

content/journals/10.1049/iet-ipr.2020.0908
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading