Colourimetric image analysis as a diagnostic tool in female genital schistosomiasis

Sigve Dhondup Holmen; Eyrun Floerecke Kjetland; Myra Taylor; Elisabeth Kleppa; Kristine Lillebø; Svein Gunnar Gundersen; Mathias Onsrud; Fritz Albregtsen

doi:10.1016/j.medengphy.2014.12.007

Colourimetric image analysis as a diagnostic tool in female genital schistosomiasis

Med Eng Phys. 2015 Mar;37(3):309-14. doi: 10.1016/j.medengphy.2014.12.007. Epub 2015 Jan 24.

Authors

Sigve Dhondup Holmen¹, Eyrun Floerecke Kjetland², Myra Taylor³, Elisabeth Kleppa⁴, Kristine Lillebø², Svein Gunnar Gundersen⁵, Mathias Onsrud⁶, Fritz Albregtsen⁷

Affiliations

¹ Centre for Imported and Tropical Diseases, Oslo University Hospital, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Norway. Electronic address: sigve.holmen@medisin.uio.no.
² Centre for Imported and Tropical Diseases, Oslo University Hospital, Oslo, Norway.
³ School of Public Health, Nelson Mandela School of Medicine, University of KwaZulu-Natal, South Africa.
⁴ Centre for Imported and Tropical Diseases, Oslo University Hospital, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Norway.
⁵ Centre for Imported and Tropical Diseases, Oslo University Hospital, Oslo, Norway; Research Department, Sørlandet Hospital HF, Kristiansand, Norway; Institute of Development Studies, University of Agder, Kristiansand, Norway.
⁶ Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Norway.
⁷ Department of Informatics, University of Oslo, Oslo, Norway; Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway.

PMID: 25630808
DOI: 10.1016/j.medengphy.2014.12.007

Abstract

Female genital schistosomiasis (FGS) is a highly prevalent waterborne disease in some of the poorest areas of sub-Saharan Africa. Reliable and affordable diagnostics are unavailable. We explored colourimetric image analysis to identify the characteristic, yellow lesions caused by FGS. We found that the method may yield a sensitivity of 83% and a specificity of 73% in colposcopic images. The accuracy was also explored in images of simulated inferior quality, to assess the possibility of implementing such a method in simple, electronic devices. This represents the first step towards developing a safe and affordable aid in clinical diagnosis, allowing for a point-of-care approach.

Keywords: Cervix; Colour; Colposcopy; Diagnosis; Female genital schistosomiasis; Lesion.

MeSH terms

Adolescent
Cell Phone
Colorimetry
Diagnosis, Computer-Assisted / methods*
Female
Humans
Image Processing, Computer-Assisted / methods*
ROC Curve
Reproductive Tract Infections / diagnosis*
Schistosomiasis / diagnosis*
Young Adult