Quantitative Conjunctival Provocation Test for Controlled Clinical Trials

I. Sárándi; D. P. Claßen; A. Astvatsatourov; O. Pfaar; L. Klimek; R. Mösges; T. M. Deserno

doi:10.3414/ME13-12-0142

Methods of Information in Medicine, Inhaltsverzeichnis

Methods Inf Med 2014; 53(04): 238-244
DOI: 10.3414/ME13-12-0142

Original Articles

Schattauer GmbH

Quantitative Conjunctival Provocation Test for Controlled Clinical Trials

I. Sárándi

¹Department of Medical Informatics, Uniklinik RWTH Aachen, Aachen, Germany

,

D. P. Claßen

²Center of Rhinology and Allergology, Wiesbaden, Germany

,

A. Astvatsatourov

³Institute of Medical Statistics, Informatics and Epidemiology, Cologne Ophthalmological Reading and Image Analysis Center, Experimental Ophthalmology, University Hospital Cologne, Cologne, Germany

,

O. Pfaar

²Center of Rhinology and Allergology, Wiesbaden, Germany

,

L. Klimek

²Center of Rhinology and Allergology, Wiesbaden, Germany

,

R. Mösges

⁴Institute of Medical Statistics, Informatics and Epidemiology, University Hospital Cologne, Cologne, Germany

,

T. M. Deserno

¹Department of Medical Informatics, Uniklinik RWTH Aachen, Aachen, Germany

› Institutsangaben

Abstract

Summary

Background: The conjunctival provocation test (CPT) is a diagnostic procedure for the assessment of allergic diseases. Photographs are taken before and after provocation increasing the redness of the conjunctiva due to hyperemia.

Objective: We propose and evaluate an automatic image processing pipeline for objective and quantitative CPT.

Method: After scale normalization based on intrinsic image features, the conjunctiva region of interest (ROI) is segmented combining thresholding, edge detection and Hough transform. Redness of the ROI is measured from 0 to 1 by the average pixel redness, which is defined by truncated projection in HSV space. In total, 92 images from an observational diagnostic study are processed for evaluation. The database contains images from two visits for assessment of the test- retest reliability (46 images per visit).

Result: All images were successfully processed by the algorithm. The relative redness increment correlates between the two visits with Pearson’s r = 0.672 (p < .001). Linear correlation of the automatic measure is larger than the manual measure (r = 0.59). This indicates a higher reproducibility and stability of the automatic method.

Conclusion: We presented a robust and effective way to objectify CPT. The algorithm operates on low resolution, is fast and requires no manual input. Quantitative CPT measures can now be established as surrogate endpoint in controlled clinical trials.

Keywords

Conjunctival provocation test - allergy - image processing - Hough transform - segmentation - clinical trials

Volltext

Referenzen

References
1 Pawankar R, Canonica GW, Holgate ST, Lockey RF. (eds). WAO White Book on Allergy. Milwaukee, WI, USA: World Allergy Organization (WAO); 2011. ISBN 9780 ISBN 978-0-615-46182-3.
2 Riechelmann H, Epple B, Gropper G. Comparison of conjunctival and nasal provocation test in allergic rhinitis to house dust mite. Int Arc Allergy Immunol 2003; 130 (01) 51-59.
3 Dogan S, Astvatsatourov A, Deserno T, Bock F, Shah-Hosseini K, Michels A. et al Objectifying the Conjunctival Provocation Test: Photography-Based Rating and Digital Analysis. Int Arch Allergy Immunol 2013; 163 (01) 59-68.
4 Horak F, Berger U, Menapace R, Schuster N. Quantification of conjunctival vascular reaction by digital imaging. J Allergy Clin Immunol 1996; 98: 495-500.
5 Fieguth P, Simpson T. Automated measurement of bulbar redness. Invest Ophthalmol Vis Sci 2002; 43: 340-347.
6 Owen CG, Ellis TJ, Woodward EG. A comparison of manual and automated methods of measuring conjunctival vessel widths from photographic and digital images. Ophthalmic Physiol Opt 2004; 24: 74-81.
7 Fukushima A, Tomita T. Image analyses of the kinetic changes of conjunctival hyperemia in histamine-induced conjunctivitis in guinea pigs. Cornea 2009; 28: 694-698.
8 Yoneda T, Sumi T, Takahashi A, Hoshikawa Y, Kobayashi M, Fukushima A. Automated hyperemia analysis software: reliability and reproducibility in healthy subjects. Jpn J Ophthalmol 2012; 56: 1-7.
9 Bista SR, Sarandi I, Dogan S, Astvatsatourov A, Mösges R, Deserno TM. Automatic conjunctival provocation test combining Hough circle transform and self-calibrated color measurements. Proc SPIE 2013; 8670-2J1.
10 Sarandi I, Deserno T, Classen D, Pfarr O, Astvatsatourov A, Mosges R. Quantitative conjunctival provocation test. In: Proceedings GMDS 2013, German Medical Sciences. http://www.egms.de/static/en/meetings/gmds2013/13gmds074.shtml
11 Lehmann TM, Kaupp A, Effert R, Meyer-Ebrecht D. Automatic strabometry by Hough-transformation and covariance-filtering. In: Proceedings ICIP-94. IEEE Computer Society Press, Los Alamitos, CA, 1994; 1: 421-425.
12 Lehmann TM, Gönner C, Spitzer K. Survey: Interpolation methods in medical image processing. IEEE Trans Med Imaging 1999; 18 (11) 1049-1075.
13 Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vis 2004; 60 (01) 91-110.
14 Fischler MA, Bolles RC. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Comm ACM 1981; 24 (06) 381-395.
15 Abramoff MD, Magalhaes PJ, Ram SJ. Image processing with ImageJ. Biophoton Int 2004; 11 (07) 36-42.
16 Meijering E. Imagescience.org. [Online]. Cited 2013 11 26. Available from. www.imagescience.org/meijering/software/featurej/releases/
17 Hicklin J. JAMA website. [Online]. Cited 2013 11 26. Available from. http://math.nist.gov/javanumerics/jama/
18 JavaGeom [Online]. Cited 2013 11 26. Available from. http://geom-java.sourceforge.net/
19 Longair M. Find Connected Regions Plugin. [Online]. Cited 2013 11 26. Available from. http://www.longair.net/edinburgh/imagej/find-connected-regions/
20 Saalfeld S. JavaSIFT. [Online]. Cited 2013 11 26. Available from. http://fly.mpi-cbg.de/~saalfeld/Projects/javasift.html
21 Bourrillion K. Guava: Google Core Libraries for Java 1.5+. 2010
22 Haak D, Jonas S, Gehlen J, Deserno TM. OC To-go: on patient’s site integration of images into OpenClinica in clinical trials by mobile devices. Proc SPIE. 2014: 9039 in press
23 Laakko T, Leppänen J, Lähteenmäki J, Nummiaho A. Mobile health and wellness application framework. Methods Inf Med 2008; 47 (03) 217-222.
24 Labrique A, Vasudevan L, Chang LW, Mehl G. H_pe for mHealth: more “y” or “o” on the horizon?. Int J Med Inform 2013; 82 (05) 467-469.
25 Struzik ZR, Yoshiuchi K, Sone M, Ishikawa T, Kikuchi H, Kumano H, Watsuji T, Natelson BH, Yamamoto Y. “Mobile Nurse” platform for ubiquitous medicine. Methods Inf Med 2007; 46 (02) 130-134.