Skip to main content

Advertisement

SpringerLink
Log in

Wilson disease tissue classification and characterization using seven artificial intelligence models embedded with 3D optimization paradigm on a weak training brain magnetic resonance imaging datasets: a supercomputer application

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Wilson’s disease (WD) is caused by copper accumulation in the brain and liver, and if not treated early, can lead to severe disability and death. WD has shown white matter hyperintensity (WMH) in the brain magnetic resonance scans (MRI) scans, but the diagnosis is challenging due to (i) subtle intensity changes and (ii) weak training MRI when using artificial intelligence (AI). Design and validate seven types of high-performing AI-based computer-aided design (CADx) systems consisting of 3D optimized classification, and characterization of WD against controls. We propose a “conventional deep convolution neural network” (cDCNN) and an “improved DCNN” (iDCNN) where rectified linear unit (ReLU) activation function was modified ensuring “differentiable at zero.” Three-dimensional optimization was achieved by recording accuracy while changing the CNN layers and augmentation by several folds. WD was characterized using (i) CNN-based feature map strength and (ii) Bispectrum strengths of pixels having higher probabilities of WD. We further computed the (a) area under the curve (AUC), (b) diagnostic odds ratio (DOR), (c) reliability, and (d) stability and (e) benchmarking. Optimal results were achieved using 9 layers of CNN, with 4-fold augmentation. iDCNN yields superior performance compared to cDCNN with accuracy and AUC of 98.28 ± 1.55, 0.99 (p < 0.0001), and 97.19 ± 2.53%, 0.984 (p < 0.0001), respectively. DOR of iDCNN outperformed cDCNN fourfold. iDCNN also outperformed (a) transfer learning–based “Inception V3” paradigm by 11.92% and (b) four types of “conventional machine learning–based systems”: k-NN, decision tree, support vector machine, and random forest by 55.13%, 28.36%, 15.35%, and 14.11%, respectively. The AI-based systems can potentially be useful in the early WD diagnosis.

Graphical Abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Dusek P, Litwin T, Czlonkowska A (2015) Wilson disease and other neurodegenerations with metal accumulations. Neurol Clin 33(1):175–204

    Article  PubMed  Google Scholar 

  2. Medici V, Rossaro L, Sturniolo G (2007) Wilson disease—a practical approach to diagnosis, treatment and follow-up. Dig Liver Dis 39(7):601–609

    Article  CAS  PubMed  Google Scholar 

  3. Rosencrantz R and Schilsky M (2011) “Wilson disease: pathogenesis and clinical considerations in diagnosis and treatment,” in Seminars in liver disease 31(03):245–259. © Thieme Medical Publishers, pp.

  4. Roberts EA, Schilsky ML (2003) A practice guideline on Wilson disease. Hepatology 37(6):1475–1492

    Article  PubMed  Google Scholar 

  5. Singh P, Ahluwalia A, Saggar K, Grewal CS (2011) Wilson’s disease: Mri features. J Pediatr Neurosci 6(1):27

    Article  PubMed  PubMed Central  Google Scholar 

  6. Parekh JR, Agrawal PR (2014) Wilson’s disease: ‘face of giant panda’ and ‘trident’ signs together. Oxford Medical Case Reports 2014(1):16–17

    Article  PubMed  PubMed Central  Google Scholar 

  7. Yousaf M, Kumar M, Ramakrishnaiah R, Vanhemert R, Angtuaco E (2009) Atypical MRI features involving the brain in Wilson’s disease. Radiol Case Rep 4(3):312

    Article  PubMed  Google Scholar 

  8. El-Baz A, Suri JS (2011) Lung imaging and computer aided diagnosis. CRC Press

  9. El-Baz A, Jiang X, Suri JS (2016) Biomedical image segmentation: advances and trends. CRC Press

  10. Khanna NN, Jamthikar AD, Gupta D, Araki T, Piga M, Saba L, Carcassi C, Nicolaides A, Laird JR, Suri HS, Gupta A, Mavrogeni S, Protogerou A, Sfikakis P, Kitas GD, Suri JS (2019) Effect of carotid image-based phenotypes on cardiovascular risk calculator: Aecrs1. 0. Med Biol Eng Comput 57(7):1553–1566

    Article  PubMed  Google Scholar 

  11. Abiwinanda N, Hanif M, Hesaputra ST, Handayani A, and Mengko TR (2019) “Brain tumor classification using convolutional neural network,” in World Congress on Medical Physics and Biomedical Engineering 2018. Springer, pp. 183–189.

  12. Sharma AM, Gupta A, Kumar PK, Rajan J, Saba L, Nobutaka I, Laird JR, Nicolades A, Suri JS (2015) A review on carotid ultrasound atherosclerotic tissue characterization and stroke risk stratification in machine learning framework. Curr Atheroscler Rep 17(9):55

    Article  PubMed  Google Scholar 

  13. Saba L, Tiwari A, Biswas M, Gupta SK, Godia-Cuadrado E, Chaturvedi A, Turk M, Suri HS, Orru S, Sanches JM et al (2019) Wilson’s disease: a new perspective review on its genetics, diagnosis and treatment. Front Biosci (Elite edition) 11:166–185

    Google Scholar 

  14. Wee C-Y, Yap P-T, Zhang D, Wang L, Shen D (2014) Group-constrained sparse fMRI connectivity modeling for mild cognitive impairment identification. Brain Struct Funct 219(2):641–656

    Article  PubMed  Google Scholar 

  15. Prasad G, Joshi SH, Nir TM, Toga AW, Thompson PM, A. D. N. I. ADNI et al (2015) Brain connectivity and novel network measures for Alzheimer’s disease classification. Neurobiol Aging 36:S121–S131

    Article  PubMed  Google Scholar 

  16. Khedher L, Raḿırez J, Górriz JM, Brahim A, Segovia F, Initiative ADN et al (2015) Early diagnosis of Alzheimer’s disease based on partial least squares, principal component analysis and support vector machine using segmented MRI images. Neurocomputing 151:139–150

    Article  Google Scholar 

  17. Affonso C, Rossi ALD, Vieira FHA, de Leon Ferreira ACP et al (2017) Deep learning for biological image classification. Expert Syst Appl 85:114–122

    Article  Google Scholar 

  18. Baloglu UB, Talo M, Yildirim O, San Tan R, Acharya UR (2019) Classification of myocardial infarction with multi-lead ECG signals and deep CNN. Pattern Recogn Lett 122:23–30

    Article  Google Scholar 

  19. Biswas M, Kuppili V, Saba L, Edla DR, Suri HS, Sharma A, Cuadrado-Godia E, Laird JR, Nicolaides A, Suri JS (2019) Deep learning fully convolution network for lumen characterization in diabetic patients using carotid ultrasound: a tool for stroke risk. Med Biol Eng Comput 57(2):543–564

    Article  PubMed  Google Scholar 

  20. Druzhkov P, Kustikova V (2016) A survey of deep learning methods and software tools for image classification and object detection. Pattern Recognit Image Anal 26(1):9–15

    Article  Google Scholar 

  21. Skandha SS, Gupta SK, Saba L, Koppula VK, Johri AM, Khanna NN, Mavrogeni S, Laird JR, Pareek G, Miner M, Sfikakis PP, Protogerou A, Misra DP, Agarwal V, Sharma AM, Viswanathan V, Rathore VS, Turk M, Kolluri R, Viskovic K, Cuadrado-Godia E, Kitas GD, Nicolaides A, Suri JS (2020) 3-D optimized classification and characterization artificial intelligence paradigm for cardiovascular/stroke risk stratification using carotid ultrasound-based delineated plaque: Atheromatic™ 2.0. Comput Biol Med 125:103958

    Article  CAS  PubMed  Google Scholar 

  22. Saba L, Agarwal M, Sanagala S, Gupta S, Sinha G, Johri A, Khanna N, Mavrogeni S, Laird J, Pareek G et al (2020) Brain MRI-based Wilson disease tissue classification: an optimised deep transfer learning approach. Electronics Letters

  23. Pareek G, Acharya UR, Sree SV, Swapna G, Yantri R, Martis RJ, Saba L, Krishnamurthi G, Mallarini G, El-Baz A et al (2013) Prostate tissue characterization/classification in 144 patient population using wavelet and higher order spectra features from transrectal ultrasound images. Technol Cancer Res Treat 12(6):545–557

    Article  PubMed  Google Scholar 

  24. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, and Wojna Z (2016) “Rethinking the inception architecture for computer vision,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818–2826.

  25. Ferenci P (2006) Regional distribution of mutations of the atp7b gene in patients with Wilson disease: impact on genetic testing. Hum Genet 120(2):151–159

    Article  CAS  PubMed  Google Scholar 

  26. Vrabelova S, Letocha O, Borsky M, Kozak L (2005) Mutation analysis of the atp7b gene and genotype/phenotype correlation in 227 patients with Wilson disease. Mol Genet Metab 86(1-2):277–285

    Article  CAS  PubMed  Google Scholar 

  27. Saba L, Lucatelli P, Anzidei M, di Martino M, Suri JS, Montisci R (2018) Volumetric distribution of the white matter hyper-intensities in subject with mild to severe carotid artery stenosis: does the side play a role? J Stroke Cerebrovasc Dis 27(8):2059–2066

    Article  PubMed  Google Scholar 

  28. Saba L, Sanfilippo R, Porcu M, Lucatelli P, Montisci R, Zaccagna F, Suri JS, Anzidei M, Wintermark M (2017) Relationship between white matter hyperintensities volume and the circle of Willis configurations in patients with carotid artery pathology. Eur J Radiol 89:111–116

    Article  PubMed  Google Scholar 

  29. Porcu M, Balestrieri A, Siotto P, Lucatelli P, Anzidei M, Suri JS, Zaccagna F, Argiolas GM, Saba L (2018) Clinical neuroimaging markers of response to treatment in mood disorders. Neurosci Lett 669:43–54

    Article  CAS  PubMed  Google Scholar 

  30. Kim T, Kim IO, Kim WS, Cheon J-E, Moon S, Kwon J, Seo J, Yeon K (2006) MR imaging of the brain in Wilson disease of childhood: findings before and after treatment with clinical correlation. Am J Neuroradiol 27(6):1373–1378

    CAS  PubMed  PubMed Central  Google Scholar 

  31. Hu X, Chen S, Huang C-B, Qian Y, Yu Y (2017) Frequency-dependent changes in the amplitude of low-frequency fluctuations in patients with Wilson’s disease: a resting-state fMRI study. Metab Brain Dis 32(3):685–692

    Article  PubMed  PubMed Central  Google Scholar 

  32. Corgiolu S, Barberini L, Suri JS, Mandas A, Costaggiu D, Piano P, Zaccagna F, Lucatelli P, Balestrieri A, Saba L (2018) Resting-state functional connectivity MRI analysis in human immunodeficiency virus and hepatitis c virus co-infected subjects. a pilot study. Eur J Radiol 102:220–227

    Article  PubMed  Google Scholar 

  33. Porcu M, Wintermark M, Suri JS, Saba L (2020) The influence of the volumetric composition of the intracranial space on neural activity in healthy subjects: a resting-state functional magnetic resonance study. Eur J Neurosci 51(9):1944–1961

    Article  PubMed  Google Scholar 

  34. Kaden M, Riedel M, Hermann W, Villmann T (2015) Border-sensitive learning in generalized learning vector quantization: an alternative to support vector machines. Soft Comput 19(9):2423–2434

    Article  Google Scholar 

  35. Jing R, Han Y, Cheng H, Han Y, Wang K, Weintraub D, Fan Y (2019) Altered large-scale functional brain networks in neurological Wilson’s disease. Brain Imaging Behav:1–11

  36. Shattuck DW, Leahy RM (2002) Brainsuite: an automated cortical surface identification tool. Med Image Anal 6(2):129–142

    Article  PubMed  Google Scholar 

  37. Manjón JV, Coupé P (2016) volBrain: an online MRI brain volumetry system. Front Neuroinform 10:30

    Article  PubMed  PubMed Central  Google Scholar 

  38. Saba L, Biswas M, Kuppili V, Godia EC, Suri HS, Edla DR, Omerzu T, Laird JR, Khanna NN, Mavrogeni S et al (2019) The present and future of deep learning in radiology. Eur J Radiol 114:14–24

    Article  PubMed  Google Scholar 

  39. Saba L, Biswas M, Suri HS, Viskovic K, Laird JR, Cuadrado-Godia E, Nicolaides A, Khanna N, Viswanathan V, Suri JS (2019) Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm. Cardiovasc Diagn Ther 9(5):439

    Article  PubMed  PubMed Central  Google Scholar 

  40. Biswas M, Kuppili V, Araki T, Edla DR, Godia EC, Saba L, Suri HS, Omerzu T, Laird JR, Khanna NN, Nicolaides A, Suri JS (2018) Deep learning strategy for accurate carotid intima-media thickness measurement: an ultrasound study on Japanese diabetic cohort. Comput Biol Med 98:100–117

    Article  PubMed  Google Scholar 

  41. Biswas M, Saba L, Chakrabartty S, Khanna NN, Song H, Suri HS, Sfikakis PP, Mavrogeni S, Viskovic K, Laird JR, Cuadrado-Godia E, Nicolaides A, Sharma A, Viswanathan V, Protogerou A, Kitas G, Pareek G, Miner M, Suri JS (2020) Two-stage artificial intelligence model for jointly measurement of atherosclerotic wall thickness and plaque burden in carotid ultrasound: a screening tool for cardiovascular/stroke risk assessment. Comput Biol Med 123:103847

    Article  CAS  PubMed  Google Scholar 

  42. Biswas M, Kuppili V, Edla DR, Suri HS, Saba L, Marinhoe RT, Sanches JM, Suri JS (2018) Symtosis: a liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm. Comput Methods Prog Biomed 155:165–177

    Article  Google Scholar 

  43. Tandel GS, Biswas M, Kakde OG, Tiwari A, Suri HS, Turk M, Laird JR, Asare CK, Ankrah AA, Khanna N et al (2019) A review on a deep learning perspective in brain cancer classification. Cancers 11(1):111

    Article  PubMed Central  Google Scholar 

  44. Li Y and Yuan Y (2017) “Convergence analysis of two-layer neural networks with relu activation,” in Adv Neural Inf Proces Syst, pp. 597–607.

  45. Maniruzzaman M, Kumar N, Abedin MM, Islam MS, Suri HS, El-Baz AS, Suri JS (2017) Comparative approaches for classification of diabetes mellitus data: machine learning paradigm. Comput Methods Prog Biomed 152:23–34

    Article  Google Scholar 

  46. Acharya UR, Faust O, Sree SV, Molinari F, Saba L, Nicolaides A, Suri JS (2011) An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans. IEEE Trans Instrum Meas 61(4):1045–1053

    Article  Google Scholar 

  47. Suri JS, Kathuria C, and Molinari F (2010) Atherosclerosis disease management. Springer Science & Business Media.

    Google Scholar 

  48. Saba L, Jain PK, Suri HS, Ikeda N, Araki T, Singh BK, Nicolaides A, Shafique S, Gupta A, Laird JR et al (2017) Plaque tissue morphology-based stroke risk stratification using carotid ultrasound: a polling-based pca learning paradigm. J Med Syst 41(6):98

    Article  PubMed  Google Scholar 

  49. Acharya UR, Faust O, Alvin A, Krishnamurthi G, Seabra JC, Sanches J, Suri JS et al (2013) Understanding symptomatology of atherosclerotic plaque by image-based tissue characterization. Comput Methods Prog Biomed 110(1):66–75

    Article  Google Scholar 

  50. Acharya UR, Mookiah MRK, Sree SV, Afonso D, Sanches J, Shafique S, Nicolaides A, Pedro LM, Fernandes JFE, Suri JS (2013) Atherosclerotic plaque tissue characterization in 2d ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment. Med Biol Eng Comput 51(5):513–523

    Article  PubMed  Google Scholar 

  51. Molinari F, Mantovani A, Deandrea M, Limone P, Garberoglio R, Suri JS (2010) Characterization of single thyroid nodules by contrast-enhanced 3-d ultrasound. Ultrasound Med Biol 36(10):1616–1625

    Article  PubMed  Google Scholar 

  52. Acharya UR, Swapna G, Sree SV, Molinari F, Gupta S, Bardales RH, Witkowska A, Suri JS (2014) A review on ultrasound-based thyroid cancer tissue characterization and automated classification. Technol Cancer Res Treat 13(4):289–301

    Article  CAS  PubMed  Google Scholar 

  53. Acharya UR, Molinari F, Sree SV, Swapna G, Saba L, Guerriero S, Suri JS (2015) Ovarian tissue characterization in ultrasound: a review. Technol Cancer Res Treat 14(3):251–261

    Article  CAS  PubMed  Google Scholar 

  54. Acharya UR, Sree SV, Kulshreshtha S, Molinari F, Koh JEW, Saba L, Suri JS (2014) Gynescan: an improved online paradigm for screening of ovarian cancer via tissue characterization. Technol Cancer Res Treat 13(6):529–539

    Article  PubMed  Google Scholar 

  55. Acharya UR, Sree SV, Ribeiro R, Krishnamurthi G, Marinho RT, Sanches J, Suri JS (2012) Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm. Med Phys 39(7Part1):4255–4264

    Article  PubMed  Google Scholar 

  56. Saba L, Dey N, Ashour AS, Samanta S, Nath SS, Chakraborty S, Sanches J, Kumar D, Marinho R, Suri JS (2016) Automated stratification of liver disease in ultrasound: an online accurate feature classification paradigm. Comput Methods Prog Biomed 130:118–134

    Article  Google Scholar 

  57. Than JC, Saba L, Noor NM, Rijal OM, Kassim RM, Yunus A, Suri HS, Porcu M, Suri JS (2017) Lung disease stratification using amalgamation of Riesz and Gabor transforms in machine learning framework. Comput Biol Med 89:197–211

    Article  PubMed  Google Scholar 

  58. Shrivastava VK, Londhe ND, Sonawane RS, Suri JS (2016) Computer-aided diagnosis of psoriasis skin images with hos, texture and color features: a first comparative study of its kind. Comput Methods Prog Biomed 126:98–109

    Article  Google Scholar 

  59. Wu DH, Chen Z, North JC, Biswas M, Vo J, Suri JS (2020) Machine learning paradigm for dynamic contrast-enhanced MRI evaluation of expanding bladder. Front Biosci (Landmark Edition) 25:1746–1764

    Article  CAS  Google Scholar 

  60. Acharya UR, Sree SV, Krishnan MMR, Krishnananda N, Ranjan S, Umesh P, Suri JS (2013) Automated classification of patients with coronary artery disease using grayscale features from left ventricle echocardiographic images. Comput Methods Prog Biomed 112(3):624–632

    Article  Google Scholar 

  61. Jamthikar AD, Gupta D, Mantella LE, Saba L, Laird JR, Johri AM, Suri JS (2020) Multiclass machine learning vs. conventional calculators for stroke/CVD risk assessment using carotid plaque predictors with coronary angiography scores as gold standard: a 500 participants study. Int J Cardiovasc Imaging:1–17

  62. Jamthikar A, Gupta D, Khanna NN, Saba L, Laird JR, Suri JS (2020) Cardiovascular/stroke risk prevention: a new machine learning framework integrating carotid ultrasound image-based phenotypes and its harmonics with conventional risk factors. Indian Heart J 72(4):258–264

    Article  PubMed  PubMed Central  Google Scholar 

  63. Jamthikar A, Gupta D, Khanna NN, Saba L, Araki T, Viskovic K, Suri HS, Gupta A, Mavrogeni S, Turk M et al (2019) A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes. Cardiovasc Diagn Ther 9(5):420

    Article  PubMed  PubMed Central  Google Scholar 

  64. Khanna NN, Jamthikar AD, Gupta D, Piga M, Saba L, Carcassi C, Giannopoulos AA, Nicolaides A, Laird JR, Suri HS et al (2019) Rheumatoid arthritis: atherosclerosis imaging and cardiovascular risk assessment using machine and deep learning–based tissue characterization. Curr Atheroscler Rep 21(2):7

    Article  PubMed  Google Scholar 

  65. Banchhor SK, Londhe ND, Araki T, Saba L, Radeva P, Laird JR, Suri JS (2017) Wall-based measurement features provides an improved IVUS coronary artery risk assessment when fused with plaque texture-based features during machine learning paradigm. Comput Biol Med 91:198–212

    Article  PubMed  Google Scholar 

  66. Suri JS, “Imaging based symptomatic classification and cardiovascular stroke risk score estimation,” Oct. 20 2011, uS Patent App. 13/053,971.

  67. Cuadrado-Godia E, Dwivedi P, Sharma S, Santiago AO, Gonzalez JR, Balcells M, Laird J, Turk M, Suri HS, Nicolaides A et al (2018) Cerebral small vessel disease: a review focusing on pathophysiology, biomarkers, and machine learning strategies. Journal of Stroke 20(3):302

    Article  PubMed  PubMed Central  Google Scholar 

  68. Martis RJ, Acharya UR, Prasad H, Chua CK, Lim CM, Suri JS (2013) Application of higher order statistics for atrial arrhythmia classification. Biomed Signal Proces Control 8(6):888–900

    Article  Google Scholar 

  69. Maniruzzaman M, Rahman MJ, Ahammed B, Abedin MM, Suri HS, Biswas M, El-Baz A, Bangeas P, Tsoulfas G, Suri JS (2019) Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms. Comput Methods Prog Biomed 176:173–193

    Article  Google Scholar 

  70. Kuppili V, Biswas M, Sreekumar A, Suri HS, Saba L, Edla DR, Marinhoe RT, Sanches JM, Suri JS (2017) Extreme learning machine framework for risk stratification of fatty liver disease using ultrasound tissue characterization. J Med Syst 41(10):152

    Article  PubMed  Google Scholar 

  71. Glas AS, Lijmer JG, Prins MH, Bonsel GJ, Bossuyt PM (2003) The diagnostic odds ratio: a single indicator of test performance. J Clin Epidemiol 56(11):1129–1135

    Article  PubMed  Google Scholar 

  72. Kadam P, Bhalerao S (2010) Sample size calculation. Int J Ayurveda Res 1(1):55

    Article  PubMed  PubMed Central  Google Scholar 

  73. Araki T, Ikeda N, Shukla D, Jain PK, Londhe ND, Shrivastava VK, Banchhor SK, Saba L, Nicolaides A, Shafique S, Laird JR, Suri JS (2016) PCA-based polling strategy in machine learning framework for coronary artery disease risk assessment in intravascular ultrasound: a link between carotid and coronary grayscale plaque morphology. Comput Methods Prog Biomed 128:137–158

    Article  Google Scholar 

  74. Suk H-I, Lee S-W, Shen D, Initiative ADN et al (2017) Deep ensemble learning of sparse regression models for brain disease diagnosis. Med Image Anal 37:101–113

    Article  PubMed  PubMed Central  Google Scholar 

  75. Zhang Y, Zhang H, Chen X, Liu M, Zhu X, Lee S-W, Shen D (2019) Strength and similarity guided group-level brain functional network construction for mci diagnosis. Pattern Recogn 88:421–430

    Article  Google Scholar 

  76. Abrol A, Bhattarai M, Fedorov A, Du Y, Plis S, Calhoun V, Initiative ADN et al. (2020) “Deep residual learning for neuroimaging: an application to predict progression to Alzheimer’s disease,” J Neurosci Methods, p. 108701.

  77. Richhariya B, Tanveer M, Rashid A, Initiative ADN et al (2020) Diagnosis of Alzheimer’s disease using universum support vector machine based recursive feature elimination (USVM-RFE). Biomed Signal Proces Control 59:101903

    Article  Google Scholar 

  78. Liu J, Pan Y, Wu F.-X, and Wang J (2020) “Enhancing the feature representation of multi-modal MRI data by combining multi-view information for mci classification,” Neurocomputing

  79. Tandel GS, Balestrieri A, Jujaray T, Khanna NN, Saba L, and Suri JS (2020) “Multiclass magnetic resonance imaging brain tumor classification using artificial intelligence paradigm,” Computers in Biology and Medicine, p. 103804.

  80. El-Baz A, Gimel’farb G, Suri JS (2015) Stochastic modeling for medical image analysis. CRC Press

  81. Suri JS, Wilson DL, and Laxminarayan S ( 2005) Handbook of Biomedical Image Analysis: Segmentation models part B. Kluwer Academic/Plenum Publishers

  82. Suri JS, Wilson D, Laxminarayan S (2005) Handbook of biomedical image analysis. Springer Science & Business Media 2

  83. Narayanan R, Kurhanewicz J, K. Shinohara, E. D. Crawford, A. Simoneau, and J. S. Suri (2009) “MRI-ultrasound registration for targeted prostate biopsy,” in 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Mael2019neurologicalcro. IEEE, pp. 991–994.

  84. El-Baz A and Suri JS (2019) “Neurological disorders and imaging physics, volume 2; engineering and clinical perspectives of multiple sclerosis,” ndi2

  85. Acharya R, Ng YE, and J. S. Suri (2008) Image modeling of the human eye. Artech House.

  86. Molinari F, Liboni W, Giustetto P, Badalamenti S, Suri JS (2009) Automatic computer-based tracings (act) in longitudinal 2-d ultrasound images using different scanners. J Mech Med Biol 9(04):481–505

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. CSE Department, Bennett University, Greater Noida, UP, India

    Mohit Agarwal & Suneet K. Gupta

  2. Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), Cagliari, Italy

    Luca Saba

  3. Department of Medicine, Division of Cardiology, Queen’s University, Ontario, Kingston, Canada

    Amer M. Johri

  4. Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi, India

    Narendra N. Khanna

  5. Cardiology Clinic, Onassis Cardiac Surgery Center, Athens, Greece

    Sophie Mavrogeni

  6. Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA, USA

    John R. Laird

  7. Minimally Invasive Urology Institute, Brown University, Providence, RI, USA

    Gyan Pareek

  8. Men’s Health Center, Miriam Hospital Providence, Providence, RI, USA

    Martin Miner

  9. Rheumatology Unit, National Kapodistrian University of Athens, Athens, Greece

    Petros P. Sfikakis

  10. Department of Cardiovascular Prevention, National and Kapodistrian Univ. of Athens, Athens, Greece

    Athanasios Protogerou

  11. Division of Cardiovascular Medicine, University of Virginia, Charlottesville, VA, USA

    Aditya M. Sharma

  12. MV Hospital for Diabetes & Professor M Viswanathan Diabetes Research Centre, Chennai, India

    Vijay Viswanathan

  13. R & D Academic Affairs, Dudley Group NHS Foundation Trust, Dudley, UK

    George D. Kitas

  14. Vascular Screening and Diagnostic Centre, University of Nicosia, Nicosia, Cyprus

    Andrew Nicolaides

  15. Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, 95661, USA

    Jasjit S. Suri

Authors
  1. Mohit Agarwal
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luca Saba
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Suneet K. Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Amer M. Johri
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Narendra N. Khanna
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sophie Mavrogeni
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. John R. Laird
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Gyan Pareek
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Martin Miner
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Petros P. Sfikakis
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Athanasios Protogerou
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Aditya M. Sharma
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Vijay Viswanathan
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. George D. Kitas
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Andrew Nicolaides
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Jasjit S. Suri
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jasjit S. Suri.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

If TP, FP, TN, FN, TPR, and FPR represent true positive, false positive, true negative, false negative, true-positive rate, and false-positive rate, respectively, then the performance parameters can be computed as follows:

$$ \mathrm{Accuracy}=\frac{\mathrm{TP}+\mathrm{TN}}{\mathrm{TP}+\mathrm{TN}+\mathrm{FP}+\mathrm{FN}} $$
(8)
$$ \mathrm{Sensitivity}=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FN}} $$
(9)
$$ \mathrm{Specificity}=\frac{\mathrm{TN}}{\mathrm{TN}+\mathrm{FP}} $$
(10)
$$ \mathrm{TPR}=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FN}} $$
(11)
$$ \mathrm{FPR}=\frac{\mathrm{FP}}{\mathrm{FP}+\mathrm{TN}} $$
(12)
$$ \hbox{\pounds}\left(\Theta \right)=-\left[{y}_i\times \log {p}_i+\left(1-{y}_i\right)\times \log \left(1-{p}_i\right)\right] $$
(13)

where yi is the class label for input and pi is the predicted probability of class being yi.

$$ \sigma =\sqrt{\frac{\sum \limits_{i=1}^N{\left({x}_i-\mu \right)}^2}{N}}\kern0.5em $$
(14)

where σ is the standard deviation and xi is the accuracy at ith combination of K-fold cross-validation, μ is the mean accuracy, and N is the number of combinations, equal to 10 for K10.

Fig. 14.
figure 14

a Three-dimensional optimization for best cDCNN layer and augmentation combination (cDCNN9*), where * shows the optimized CNN layer. The black arrow represents optimized value at cDL9A4. b Three-dimensional optimization for best iDCNN layer and augmentation combination (iDCNN9*), where * shows the optimized CNN layer. The black arrow represents the optimized value at iDL9A4.

Full size image
Fig. 15
figure 15

Comparison of cDCNN9* and iDCNN9* for different training protocols

Full size image

Scientific validation of DCNN systems

The DCNN9*-Augm4* system was validated using well-accepted and well-published facial biometric data. The facial dataset consisted of 72 subjects, and each subject represented a class. Each subject had 20 different face images totaling to 1440 images in the dataset. Using K10 protocol, the accuracy obtained with cDCNN, tDCNN, and iDCNN was 96.72 ± 2.01%, 97.18 ± 1.23%, and 98.27 ± 1.55%, respectively. These numbers are comparable with the accuracy obtained in WD. The order of performance was iDCNN > tDCNN > cDCNN. The results demonstrated the proposed DCNN methods as they promised encouraging high accuracy on an already published dataset. Table 11 shows the 10 K10 combinations of cDCNN, tDCNN, and iDCNN for the facial biometric dataset in sorted form.

Table 11 K10 performance of three DCNN models on the facial biometric dataset
Full size table
Table 12 Symbol table
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Agarwal, M., Saba, L., Gupta, S.K. et al. Wilson disease tissue classification and characterization using seven artificial intelligence models embedded with 3D optimization paradigm on a weak training brain magnetic resonance imaging datasets: a supercomputer application. Med Biol Eng Comput 59, 511–533 (2021). https://doi.org/10.1007/s11517-021-02322-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-021-02322-0

Keywords

Search

Navigation