Dataset Information

Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-Analysis.

ABSTRACT: Otitis media is one of the most common childhood diseases worldwide, but because of lack of doctors and health personnel in developing countries it is often misdiagnosed or not diagnosed at all. This may lead to serious, and life-threatening complications. There is, thus a need for an automated computer based image-analyzing system that could assist in making accurate otitis media diagnoses anywhere.A method for automated diagnosis of otitis media is proposed. The method uses image-processing techniques to classify otitis media. The system is trained using high quality pre-assessed images of tympanic membranes, captured by digital video-otoscopes, and classifies undiagnosed images into five otitis media categories based on predefined signs. Several verification tests analyzed the classification capability of the method.An accuracy of 80.6% was achieved for images taken with commercial video-otoscopes, while an accuracy of 78.7% was achieved for images captured on-site with a low cost custom-made video-otoscope.The high accuracy of the proposed otitis media classification system compares well with the classification accuracy of general practitioners and pediatricians (~64% to 80%) using traditional otoscopes, and therefore holds promise for the future in making automated diagnosis of otitis media in medically underserved populations.

SUBMITTER: Myburgh HC

PROVIDER: S-EPMC4816811 | biostudies-other | 2016 Mar

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-Analysis.

Myburgh Hermanus C HC van Zijl Willemien H WH Swanepoel DeWet D Hellström Sten S Laurent Claude C

EBioMedicine 20160208

<h4>Background</h4>Otitis media is one of the most common childhood diseases worldwide, but because of lack of doctors and health personnel in developing countries it is often misdiagnosed or not diagnosed at all. This may lead to serious, and life-threatening complications. There is, thus a need for an automated computer based image-analyzing system that could assist in making accurate otitis media diagnoses anywhere.<h4>Methods</h4>A method for automated diagnosis of otitis media is proposed. ...[more]

PMID: 27077122

Similar Datasets

Project description:BackgroundCanine rabies is a neglected disease causing 55,000 human deaths worldwide per year, and 99% of all cases are transmitted by dog bites. In N'Djaména, the capital of Chad, rabies is endemic with an incidence of 1.71/1,000 dogs (95% C.I. 1.45-1.98). The gold standard of rabies diagnosis is the direct immunofluorescent antibody (DFA) test, requiring a fluorescent microscope. The Centers for Disease Control and Prevention (CDC, Atlanta, United States of America) developed a histochemical test using low-cost light microscopy, the direct rapid immunohistochemical test (dRIT).Methodology/principal findingsWe evaluated the dRIT in the Chadian National Veterinary Laboratory in N'Djaména by testing 35 fresh samples parallel with both the DFA and dRIT. Additional retests (n = 68 in Chad, n = 74 at CDC) by DFA and dRIT of stored samples enhanced the power of the evaluation. All samples were from dogs, cats, and in one case from a bat. The dRIT performed very well compared to DFA. We found a 100% agreement of the dRIT and DFA in fresh samples (n = 35). Results of retesting at CDC and in Chad depended on the condition of samples. When the sample was in good condition (fresh brain tissue), we found simple Cohen's kappa coefficient related to the DFA diagnostic results in fresh tissue of 0.87 (95% C.I. 0.63-1) up to 1. For poor quality samples, the kappa values were between 0.13 (95% C.I. -0.15-0.40) and 0.48 (95% C.I. 0.14-0.82). For samples stored in glycerol, dRIT results were more likely to agree with DFA testing in fresh samples than the DFA retesting.Conclusion/significanceThe dRIT is as reliable a diagnostic method as the gold standard (DFA) for fresh samples. It has an advantage of requiring only light microscopy, which is 10 times less expensive than a fluorescence microscope. Reduced cost suggests high potential for making rabies diagnosis available in other cities and rural areas of Africa for large populations for which a capacity for diagnosis will contribute to rabies control.

Dataset Information

Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-Analysis.

Publications

Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-Analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets