© The Institution of Engineering and Technology
Wilson's disease (WD) is caused by the excessive accumulation of copper in the brain and liver, leading to death if not diagnosed early. WD shows its prevalence as white matter hyperintensity (WMH) in MRI scans. It is challenging and tedious to classify WD against controls when comparing visually, primarily due to subtle differences in WMH. This Letter presents a computer-aided design-based automated classification strategy that uses optimised transfer learning (TL) utilising two novel paradigms known as (i) MobileNet and (ii) the Visual Geometric Group-19 (VGG-19). Further, the authors benchmark TL systems against a machine learning (ML) paradigm. Using four-fold augmentation, VGG-19 is superior to MobileNet demonstrating accuracy and area under the curve (AUC) pairs as 95.46 ± 7.70%, 0.932 (p < 0.0001) and 86.87 ± 2.23%, 0.871 (p < 0.0001), respectively. Further, MobileNet and VGG-19 showed an improvement of 3.4 and 13.5%, respectively, when benchmarked against the ML-based soft classifier – Random Forest.
References
-
-
1)
-
33. Saba, L., Biswas, M., Kuppili, V., et al: ‘The present and future of deep learning in radiology’, Eur. J. Radiol., 2019, 114, pp. 14–24 (doi: 10.1016/j.ejrad.2019.02.038).
-
2)
-
11. Pareek, G., Acharya, U.R., Sree, S.V., et al: ‘Prostate tissue characterization/classification in 144 patient population using wavelet and higher order spectra features from transrectal ultrasound images’, Technol. Cancer Res. Treat., 2013, 12, (6), pp. 545–557 (doi: 10.7785/tcrt.2012.500346).
-
3)
-
30. Suri, J.S.: ‘Imaging based symptomatic classification and cardiovascular stroke risk score estimation’, , 2011.
-
4)
-
21. Maniruzzaman, M., Rahman, M.J., Ahammed, B., et al: ‘Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms’, Comput. Methods Programs Biomed., 2019, 176, pp. 173–193 (doi: 10.1016/j.cmpb.2019.04.008).
-
5)
-
10. Porcu, M., Balestrieri, A., Siotto, P., et al: ‘Clinical neuroimaging markers of response to treatment in mood disorders’, Neurosci. Lett., 2018, 669, pp. 43–54 (doi: 10.1016/j.neulet.2016.10.013).
-
6)
-
9. Saba, L., Sanfilippo, R., Porcu, M., et al: ‘Relationship between white matter hyperintensities volume and the circle of Willis configurations in patients with carotid artery pathology’, Eur. J. Radiol., 2017, 89, pp. 111–116 (doi: 10.1016/j.ejrad.2017.01.031).
-
7)
-
49. Biswas, M., Kuppili, V., Edla, D.R., et al: ‘Symtosis: a liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm’, Comput. Methods Programs Biomed., 2018, 155, pp. 165–177 (doi: 10.1016/j.cmpb.2017.12.016).
-
8)
-
47. Mirmehdi, M.: ‘Handbook of texture analysis’ (Imperial College Press, UK, 2008).
-
9)
-
3. Ala, A., Walker, A.P., Ashkan, K., et al: ‘Wilson's disease’, Lancet, 2007, 369, (9559), pp. 397–408 (doi: 10.1016/S0140-6736(07)60196-2).
-
10)
-
22. Acharya, U.R., Sree, S.V., Krishnan, M.M.R., et al: ‘Automated classification of patients with coronary artery disease using grayscale features from left ventricle echocardiographic images’, Comput. Methods Programs Biomed., 2013, 112, (3), pp. 624–632 (doi: 10.1016/j.cmpb.2013.07.012).
-
11)
-
35. Tandel, G.S., Balestrieri, A., Jujaray, T., et al: ‘Multiclass magnetic resonance imaging brain tumor classification using artificial intelligence paradigm’, Comput. Biol. Med., 2020, 122, p. 103804 (doi: 10.1016/j.compbiomed.2020.103804).
-
12)
-
50. Biswas, M., Kuppili, V., Araki, T., et al: ‘Deep learning strategy for accurate carotid intima-media thickness measurement: an ultrasound study on Japanese diabetic cohort’, Comput. Biol. Med., 2018, 98, pp. 100–117 (doi: 10.1016/j.compbiomed.2018.05.014).
-
13)
-
31. Acharya, U.R., Faust, O., Sree, S.V., et al: ‘An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans’, IEEE Trans. Instrum. Meas., 2011, 61, (4), pp. 1045–1053 (doi: 10.1109/TIM.2011.2174897).
-
14)
-
20. Maniruzzaman, M., Kumar, N., Abedin, M.M., et al: ‘Comparative approaches for classification of diabetes mellitus data: machine learning paradigm’, Comput. Methods Programs Biomed., 2017, 152, pp. 23–34 (doi: 10.1016/j.cmpb.2017.09.004).
-
15)
-
39. Kaden, M., Riedel, M., Hermann, W.: ‘Border-sensitive learning in generalized learning vector quantization: an alternative to support vector machines’, Soft Comput., 2015, 19, (9), pp. 2423–2434 (doi: 10.1007/s00500-014-1496-1).
-
16)
-
37. Rujirakul, K., So-In, C., Arnonkijpanich, B.: ‘PEM-PCA: a parallel expectation-maximization PCA face recognition architecture’, Scientific World J., 2014, 2014, (doi: 10.1155/2014/468176).
-
17)
-
25. van Ravenswaaij-Arts, C.M., Kollee, L.A., Hopman, J.C., et al: ‘Heart rate variability’, Ann. Intern. Med., 1993, 118, (6), pp. 436–447 (doi: 10.7326/0003-4819-118-6-199303150-00008).
-
18)
-
14. Acharya, U.R., Sree, S.V., Ribeiro, R., et al: ‘Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm’, Med. Phys., 2012, 39, (7Part1), pp. 4255–4264 (doi: 10.1118/1.4725759).
-
19)
-
43. Abrol, A., Bhattarai, M., Fedorov, A., et al: ‘Deep residual learning for neuroimaging: an application to predict progression to alzheimer's disease’, J. Neurosci. Methods, 2020, 339, p. 108701 (doi: 10.1016/j.jneumeth.2020.108701).
-
20)
-
36. Shattuck, D.W., Leahy, R.M.: ‘Brainsuite: an automated cortical surface identification tool’, Med. Image Anal., 2002, 6, (2), pp. 129–142 (doi: 10.1016/S1361-8415(02)00054-3).
-
21)
-
38. Golle, P.: ‘Machine learning attacks against the Asirra CAPTCHA’. Proc. of the 15th ACM Conf. on Computer and communications security, Alexandria, VA, USA, 2008.
-
22)
-
34. Biswas, M., Kuppili, V., Saba, L., et al: ‘State-of-the-art review on deep learning in medical imaging’, Front Biosci (Landmark Ed), 2019, 24, pp. 392–426 (doi: 10.2741/4725).
-
23)
-
19. Shrivastava, V.K., Londhe, N.D., Sonawane, R.S., et al: ‘Computer-aided diagnosis of psoriasis skin images with HOS, texture and color features: a first comparative study of its kind’, Comput. Methods Programs Biomed., 2016, 126, pp. 98–109 (doi: 10.1016/j.cmpb.2015.11.013).
-
24)
-
15. Saba, L., Dey, N., Ashour, A.S., et al: ‘Automated stratification of liver disease in ultrasound: an online accurate feature classification paradigm’, Comput. Methods Programs Biomed., 2016, 130, pp. 118–134 (doi: 10.1016/j.cmpb.2016.03.016).
-
25)
-
28. Acharya, U.R., Faust, O., Alvin, A., et al: ‘Understanding symptomatology of atherosclerotic plaque by image-based tissue characterization’, Comput. Methods Programs Biomed., 2013, 110, (1), pp. 66–75 (doi: 10.1016/j.cmpb.2012.09.008).
-
26)
-
46. Liu, J., Pan, Y., Wu, F.-X., et al: ‘Enhancing the feature representation of multi-modal MRI data by combining multi-view information for MCI classification’, Neurocomputing, 2020, 400, pp. 322–332 (doi: 10.1016/j.neucom.2020.03.006).
-
27)
-
4. Roberts, E.A.: ‘A practice guideline on Wilson disease’, Hepatology, 2003, 37, pp. 1475–1492 (doi: 10.1053/jhep.2003.50252).
-
28)
-
12. McClure, P., Elnakib, A., El-Ghar, M.A., et al: ‘In-vitro and in-vivo diagnostic techniques for prostate cancer: a review’, J. Biomed. Nanotechnol., 2014, 10, (10), pp. 2747–2777 (doi: 10.1166/jbn.2014.1990).
-
29)
-
24. Martis, R.J., Acharya, U.R., Prasad, H., et al: ‘Application of higher order statistics for atrial arrhythmia classification’, Biomed. Signal Proc. Control, 2013, 8, (6), pp. 888–900 (doi: 10.1016/j.bspc.2013.08.008).
-
30)
-
44. Jing, R., Han, Y., Cheng, H., et al: ‘Altered large-scale functional brain networks in neurological wilson's disease’, Brain Imaging Behav., 2019, 14, (5), pp. 1445–1455 (doi: 10.1007/s11682-019-00066-y).
-
31)
-
13. Acharya, U.R., Sree, S.V., Kulshreshtha, S., et al: ‘Gynescan: an improved online paradigm for screening of ovarian cancer via tissue characterization’, Technol. Cancer Res. Treat., 2014, 13, (6), pp. 529–539 (doi: 10.7785/tcrtexpress.2013.600273).
-
32)
-
32. Saba, L., Ikeda, N., Deidda, M., et al: ‘Association of automated carotid IMT measurement and HbA1c in Japanese patients with coronary artery disease’, Diabetes Res. Clin. Pract., 2013, 100, (3), pp. 348–353 (doi: 10.1016/j.diabres.2013.03.032).
-
33)
-
18. Acharya, U.R., Sree, S.V., Krishnan, M.M.R., et al: ‘Non-invasive automated 3D thyroid lesion classification in ultrasound: a class of ThyroScan™ systems’, Ultrasonics, 2012, 52, (4), pp. 508–520 (doi: 10.1016/j.ultras.2011.11.003).
-
34)
-
1. Dusek, P, Litwin, T., Czlonkowska, A.: ‘Wilson disease and other neurodegenerations with metal accumulations’, Neurol. Clin., 2015, 33, (1), pp. 175–204 (doi: 10.1016/j.ncl.2014.09.006).
-
35)
-
27. Saba, L., Jain, P.K., Suri, H.S., et al: ‘Plaque tissue morphology-based stroke risk stratification using carotid ultrasound: a polling-based PCA learning paradigm’, J. Med. Syst., 2017, 41, (6), p. 98 (doi: 10.1007/s10916-017-0745-0).
-
36)
-
42. Zhang, Y., Zhang, H., Chen, X., et al: ‘Strength and similarity guided group-level brain functional network construction for MCI diagnosis’, Pattern Recognit., 2019, 88, pp. 421–430 (doi: 10.1016/j.patcog.2018.12.001).
-
37)
-
6. Parekh, J.R., Agrawal, P.R.: ‘Wilson's disease:’face of giant panda'and ‘trident'signs together’, Oxf. Med. Case. Reports., 2014, 2014, (1), pp. 16–17 (doi: 10.1093/omcr/omu005).
-
38)
-
23. Araki, T., Ikeda, N., Shukla, D., et al: ‘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 Programs Biomed., 2016, 128, pp. 137–158 (doi: 10.1016/j.cmpb.2016.02.004).
-
39)
-
17. Acharya, U., Vinitha Sree, S., Mookiah, M., et al: ‘Diagnosis of Hashimoto's thyroiditis in ultrasound using tissue characterization and pixel classification’, Proc. Inst. Mech. Eng., H: J. Eng. Med., 2013, 227, (7), pp. 788–798 (doi: 10.1177/0954411913483637).
-
40)
-
2. Medici, V, Rossaro, L., Sturniolo, G.: ‘Wilson disease—a practical approach to diagnosis, treatment and follow-up’, Dig. Liver Dis., 2007, 39, (7), pp. 601–609 (doi: 10.1016/j.dld.2006.12.095).
-
41)
-
26. Acharya, U.R., Mookiah, M.R.K., Sree, S.V., et al: ‘Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment’, Med. Biol. Eng. Comput., 2013, 51, (5), pp. 513–523 (doi: 10.1007/s11517-012-1019-0).
-
42)
-
41. Abiwinanda, N., Hanif, M., Hesaputra, S.T., et al: ‘Brain tumor classification using convolutional neural network’. World Congress on Medical Physics and Biomedical Engineering 2018, Prague, Czech Republic (Springer, Singapore, 2019), pp. 183–189.
-
43)
-
5. Singh, P., Ahluwalia, A., Saggar, K., et al: ‘Wilson's disease: MRI features’, J. Pediatr. Neurosci., 2011, 6, (1), p. 27 (doi: 10.4103/1817-1745.97618).
-
44)
-
48. El-Baz, A., Gimel farb, G., Suri, J.S.: ‘Stochastic modeling for medical image analysis’ (CRC Press, USA, 2015).
-
45)
-
40. Suk, H.-I., Lee, S.-W., Shen, D., et al: ‘Deep ensemble learning of sparse regression models for brain disease diagnosis’, Med. Image Anal., 2017, 37, pp. 101–113 (doi: 10.1016/j.media.2017.01.008).
-
46)
-
16. Acharya, U.R., Swapna, G., Sree, S.V., et al: ‘A review on ultrasound-based thyroid cancer tissue characterization and automated classification’, Technol. Cancer Res. Treat., 2014, 13, (4), pp. 289–301 (doi: 10.7785/tcrt.2012.500381).
-
47)
-
29. Acharya, R.U., Faust, O., Alvin, A.P.C., et al: ‘Symptomatic vs. asymptomatic plaque classification in carotid ultrasound’, J. Med. Syst., 2012, 36, (3), pp. 1861–1871 (doi: 10.1007/s10916-010-9645-2).
-
48)
-
45. Richhariya, B., Tanveer, M., Rashid, A.H., et al: ‘Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE)’, Biomed. Signal Proc. Control, 2020, 59, p. 101903 (doi: 10.1016/j.bspc.2020.101903).
-
49)
-
8. Saba, L., Lucatelli, P., Anzidei, M., et al: ‘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., 2018, 27, (8), pp. 2059–2066 (doi: 10.1016/j.jstrokecerebrovasdis.2018.02.065).
-
50)
-
7. Yousaf, M., Kumar, M., Ramakrishnaiah, R., et al: ‘Atypical MRI features involving the brain in Wilson's disease’, Radiol. Case. Rep., 2009, 4, (3), p. 312 (doi: 10.2484/rcr.v4i3.312).
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2020.2102
Related content
content/journals/10.1049/el.2020.2102
pub_keyword,iet_inspecKeyword,pub_concept
6
6