Fig. 7.13 Boxplots showing the NFL scores for each of the NDS groups calculated manually (left) and automatically (right)

(3.68–33.91) for the manual analysis to (1.22–20.03) for the automated analysis. ANOVA analysis results in a p-value for discrimination among these groups which is slightly higher for the automated than the manual analysis, though both are highly significant (p ≈ 0) (Table 7.2).

7.6 Conclusion

The analysis of CCM images requires the identification of fiber-like structures with low contrast in noisy images. This is a requirement shared by a number of imaging applications in biology, medicine, and other fields. A number of methods have been applied in these applications, and we have compared some of these, and more generic methods, with a dual-model detection algorithm devised for this study. The comparison used a large set of images with manual ground-truth. In terms of both error-rates (pixel misclassification) and signal-to-noise ratio, the dual model achieved the highest performance. It seems reasonable to propose that this filter is likely to prove equally useful in applications of a similar nature.

The question of the clinical utility of the method was also addressed. The evaluation has shown that the automatic analysis is consistent with the manual ground-truth with a correlation of r = 0.93. Similarity in grouping control and patient subjects between manual and automated analysis was also achieved with (p ≈ 0). Therefore, we conclude that automated analysis of corneal nerve fibers is a much quicker and potentially more reliable practical alternative to manual analysis due to its consistency and immunity to the inter/intra-observer variability. These prosperities will help deliver CCM from a research tool to a practical and potentially large scale clinical technique for the assessment of neuropathic severity.

Acknowledgments The authors thank Dr. Mitra Tavakoli and Mr. Ioannis Petropoulos for capturing the CCM images and providing the manually delineated ground-truth. The authors also thank the Juvenile Diabetes Research Foundation (JDRF) for the financial support under the scholar grant 17–2008–1031.

References

1.Malik, R.A., Kallinikos, P., Abbott, C.A., van Schie, C.H.M., Morgan, P., Efron, N., Boulton, A.J.M.: Corneal confocal microscopy: A non-invasive surrogate of nerve fibre damage and repair in diabetic patients. Diabetologia 46, 683–688 (2003)

2.Kallinikos, P., Berbanu, M., O’Donnell, C., Boulton, A., Efron, N., Malik, R.: Corneal nerve tortuosity in diabetic patients with neuropathy. Invest. Ophthalmol. Vis. Sci. 45, 418–422 (2004)

3.Hossain, P., Sachdev, A., Malik, R.A.: Early detection of diabetic peripheral neuropathy with corneal confocal microscopy. Lancet 366, 1340–1343 (2005)

4.Ruggeri, A., Scarpa, F., Grisan, E.: Analysis of corneal images for the recognition of nerve structures. In: IEEE Conference of the Engineering in Medicine and Biology Society (EMBS),

pp.4739–4742, September 2006

5.Dabbah, M.A., Graham, J., Tavakoli, M., Petropoulos, Y., Malik, R.A.: Nerve fibre extraction in confocal corneal microscopy images for human diabetic neuropathy detection using gabor filters. In: Medical Image Understanding and Analysis (MIUA), pp. 254–258, July 2009

6.Dixon, R.N., Taylor, C.J.: Automated asbestos fibre counting. Mach. Aided Image Anal. 178–185 (1979)

7.Bryson, N., Dixon, R.N., Hunter, J.J., Taylor, C.J.: Contextual classification of cracks. Image Vis. Comput. 12, 149–154 (1994)

8.Zwiggelaar, R., Astley, S., Boggis, C., Taylor, C.: Linear structures in mammographic images: Detection and classification. IEEE Trans. Med. Imag. 23, 1077–1086 (2004)

9.Jain, A.K., Farrokhnia, F.: Unsupervised texture segmentation using Gabor filters. Pattern Recogn. 24, 1167–1186 (1991)

10.Lorenz, C., Carlsen, I., Buzug, T.: Fassnacht, C., Weese, J.: Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images. In: CVRMed-MRCAS’97, pp. 233–242 (1997)

11.Sato, Y., Nakajima, S., Atsumi, H., Koller, T., Gerig, G., Yoshida, S., Kikinis, R.: 3D multiscale line filter for segmentation and visualization of curvilinear structures in medical images. In: CVRMed-MRCAS’97, pp. 213–222 (1997)

12.Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Medical Image Computing and Computer-Assisted Interventation (MICCAI),

pp.130–137, July 1998

13.Krissian, K., Malandain, G., Ayache, N., Vaillant, R., Trousset, Y.: Model-based detection of tubular structures in 3D images. Comput. Vis. Image Underst. 80, 130–171 (2000)

14.Kingsbury, N.: Complex wavelets for shift invariant analysis and filtering of signals. Appl. Comput. Harmonic Anal. 10, 234–253 (2001)

15.Kingsbury, N.: Rotation-invariant local feature matching with complex wavelets. In: European Conference on Signal Processing (EUSIPCO), Florence, pp. 4–8, 2006

16.Sadeghzadeh, R., Berks, M., Astley, S., Taylor, C.: Detection of retinal blood vessels using complex wavelet transforms and random forest classification. In: Proceedings of Medical Image Understanding and Analysis (MIUA), pp. 127–131 (2010)

17.Chen, Z., Berks, M.: Astley, S., Taylor, C., Classification of linear structures in mammograms using random forests. In: Digital Mammography, pp. 153–160 (2010)

18.Felsberg, M., Sommer, G.: The Monogenic Signal. IEEE Trans. Signal Process. 49, 3136–3144 (2001)

19.Pan, X.B., Brady, M., Highnam, R., Declerck, J.: The use of multi-scale monogenic signal on structure orientation identification and segmentation. In: Digital Mammography, pp. 601–608 (2006)

20.Ali, R., Gooding, M., Christlieb, M., Brady, M.: Advanced phase-based segmentation of multiple cells from brightfield microscopy images. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI), pp. 181–184 (2008)

21.Minsky, M.: Microscopy apparatus US Patent 3013467. U. S. P. Office, Ed. US, 1961

22.Dyck, P., Norell, J., Tritschler, H., Schuette, K., Samigullin, R., Ziegler, D., Bastyr, E., Litchy, W., O’Brien, P.: Challenges in design of multicenter trials: end points assessed longitudinally for change and monotonicity. Diabetes Care 30, 2619–2625 (2007)

23.Umapathi, T., Tan, W., Loke, S., Soon, P., Tavintharan, S., Chan, Y.: Intraepidermal nerve fiber density as a marker of early diabetic neuropathy. Muscle Nerve 35, 591–598 (2007)

24.Loseth, S., Stalberg, E., Jorde, R., Mellgren, S.: Early diabetic neuropathy: thermal thresholds

and intraepidermal nerve fibre density in patients with normal nerve conduction studies.

J. Neurol. 255, 1197–1202 (2008)

25.Malik, R., Tesfaye, S., Newrick, P., Walker, D., Rajbhandari, S., Siddique, I., Sharma, A., Boulton, A., King, R., Thomas, P., Ward, J.: Sural nerve pathology in diabetic patients with minimal but progressive neuropathy. Diabetologia 48, 578–585 (2005)

26.Malik, R., Veves, A., Walker, D., Siddique, I., Lye, R., Schady, W., Boulton, A.: Sural nerve fibre pathology in diabetic patients with mild neuropathy: relationship to pain, quantitative sensory testing and peripheral nerve electrophysiology. Acta Neuropathol. (Berl.) 101, 367–374 (2001)

27.Novella, S., Inzucchi, S., Goldstein, J.: The frequency of undiagnosed diabetes and impaired glucose tolerance in patients with idiopathic sensory neuropathy. Muscle Nerve 24, 1229–1231 (2001)

28.Singleton, J., Smith, A., Bromberg, M.: Increased prevalence of impaired glucose tolerance in patients with painful sensory neuropathy. Diabetes Care 24, 1448–1453 (2001)

29.Sumner, C., Sheth, S., Griffin, J., Cornblath, D., Polydefkis, M.: The spectrum of neuropathy in diabetes and impaired glucose tolerance. Neurology 60, 108–111 (2003)

30.Quattrini, C., Tavakoli, M., Jeziorska, M., Kallinikos, P., Tesfaye, S., Finnigan, J., Marshall, A., Boulton, A.J.M., Efron, N., Malik, R.A.: Surrogate markers of small fiber damage in human diabetic neuropathy. Diabetes 56, 2148–2154 (2007)

31.Tavakoli, M., Kallinikos, P.A., Efron, N., Boulton, A.J.M., Malik, R.A.: Corneal sensitivity is reduced and relates to the severity of neuropathy in patients with diabetes. Diabetes Care 30, 1895–1897 (2007)

32.Mehra, S., Tavakoli, M., Kallinikos, P.A., Efron, N., Boulton, A.J.M., Augustine, T., Malik, R.A.: Corneal confocal microscopy detects early nerve regeneration after pancreas transplantation in patients with type 1 diabetes. Diabetes Care 30, 2608–2612 (2007)

33.Tavakoli, M., Marshall, A., Thompson, L., Kenny, M., Waldek, S., Efron, N., Malik, R.A.: Corneal confocal microscopy: A novel noninvasive means to diagnose neuropathy in patients with Fabry disease. Muscle and Nerve 40, 976–984 (2009)

34.Tavakoli, M., Marshall, A., Pitceathly, R., Fadavi, H., Gow, D., Roberts, M.E., Efron, N., Boulton, A.J.M., Malik, R.A.: Corneal confocal microscopy: A novel means to detect nerve fibre damage in idiopathic small fibre neuropathy. Exp. Neurol. 223, 245–250 (2010)

35.Tavakoli, M., Quattrini, C., Abbott, C., Kallinikos, P., Marshall, A., Finnigan, J., Morgan, P., Efron, N., Boulton, A.J.M., Malik, R.A.: Corneal confocal microscopy: A novel non-invasive test to diagnose and stratify the severity of human diabetic neuropathy. Diabetes Care 33, 1792–1797 (2010)

36.Dougherty, G., Johnson, M.J., Wiers, M.D.: Measurement of retinal vascular tortuosity and its application to retinal pathologies. Med. Biol. Eng. Comput. 48, 87–95 (2010)

37.Dabbah, M.A., Graham, J., Tavakoli, M., Petropoulos, Y., Malik, R.A.: Dual-model automatic detection of nerve-fibres in corneal confocal microscopy images. In: The International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), vol. 6361, pp. 300–307 (2010)

38.Daugman, J.G.: Two-dimensional spectral analysis of cortical receptive field profiles. Vis. Res. 20, 847–856 (1980)

39.Rao, A.R.: A taxonomy for texture description and identification. Springer, New York (1990)

40.Kass, M., Witkin, A.: Analyzing oriented patterns. Comp. Vis. Graph. Image Process. 37, 362–385 (1987)

41.Hong, L., Wan, Y., Jain, A.: Fingerprint image enhancement: algorithm and performance evaluation. IEEE Trans. Pattern Anal. Mach. Intell. 20, 777–789 (1998)

42.Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. Commun. ACM 27, 236–239 (1984)

43.Rutovitz, D.: Pattern recognition. J. R. Stat. Soc. A (General) 129, 504–530 (1966)

44.Kingsbury, N.: Dual-tree complex wavelet transform pack. http://www-sigproc.eng.cam.ac. uk/\ ngk/. Accessed June 2002

45.Kovesi, P.: An implementation of Felsberg’s monogenic filters. http://www.csse.uwa.edu. au1pk/research/matlabfns/. Accessed August 2005

46.Kroon, D.J., Schrijver, M.: Hessian based Frangi Vesselness filter. http://www.mathworks.co. uk/. Accessed October 2009

47.Abbott, C.A., Carrington, A.L., Ashe, H., Bath, S., Every, L.C., Griffiths, J., Hann, A.W., Hussein, A., Jackson, N., Johnson, K.E., Ryder, C.H., Torkington, R., Ross, E.R.E.V., Whalley, A.M., Widdows, P., Williamson, S., Boulton, A.J.M.: The North-West diabetes foot care study: Incidence of, and risk factors for, new diabetic foot ulceration in a community-based patient cohort. Diabetic Med. 19, 377–384 (2002)