A RULE-BASED METHOD FOR TUMOR RECOGNITION IN LIVER ULTRASOUND IMAGES
Abstract
A method is suggested for detecting malignant tumors in liver ultrasonic images. The method is based on decision rules which utilize quantitative features of liver image texture such as the degree of texture anisotropy, distribution of intensity gradients, the area of connected components with certain image properties and some other. On a set of 1280 regions of interests sampled from 26 test images it is demonstrated that the method provides an acceptable level of tumor recognition accuracy in 96,8 % of cases.
References
1. Оценка эндогенной интоксикации и прогнозирование гнойно-воспалительных осложнений у онкологических больных (инструкция по применению) / Р.М. Смолякова [и др.]. – Утв. Минздравом Респ. Беларусь 01.07.05. – Минск : НИИ онкологии и медицинской радиологии им. Н.Н. Александрова, 2005. – 16 с.
2. Способ дифференциальной диагностики стерильного и инфицированного панкреонекроза : пат. 14881 Респ. Беларусь, МПК (2006) G 01N 33/52 / А.А. Литвин [и др.] ; заяв. Гомельский мед. ун-т ; опубл. 2010.08.30 // Афiцыйны бюл. / Нац. цэнтр iнтэлектуал. уласнасцi. – 2010. – № 4. – С. 31–32.
3. Оценка анизотропии КТ-изображений в диагностике инфицированного панкреонекроза / А.А. Литвин [и др.] // Вестник новых медицинских технологий. – 2013. – Т. 20, № 3. – С. 22–26.
4. Simple ultrasound rules to distinguish between benign and malignant adnexal masses before surgery: prospective validation by IOTA group / D. Timmerman [et al.] // British Medical Journal. – 2010. – Vol. 341. – P. 6839.
5. A simple clinical decision rule to rule out appendicitis in patients with nondiagnostic ultrasound results / M.M. Leeuwenburgh [et al.] // Academic Emergency Medicine. – 2014. – Vol. 21(5). – P. 488–496.
6. An atlas of surface microscopy of pigmented skin lesions: Dermatoscopy. 2 ed. / S.W. Menzies [et al.]. – Sydney : McGraw-Hill Book Company Australia, 2002. – 186 p.
7. Сасов, А.Ю. Развитие аналитических методов обработки информации в растровой электронной микроскопии : автореф. дис. … канд. физ.-мат. наук / А.Ю. Сасов. – М. : МГУ, 1984.
8. Kovalev, V.A. Texture anisotropy in 3D images / V.A. Kovalev, M. Petrou, Y.S. Bondar // IEEE Transactions on Image Processing. – 1999. – Vol. 8, no. 3. – P. 346–360.
9. Kovalev, V.A. Texture analysis in three dimensions as a cue to medical diagnosis / V.A. Kovalev, M. Petrou // Processing and Analysis: Handbook of Medical Imaging; I. Bankman (ed.). – San Diego : Academic Press, 2000. – P. 231–247.
10. Kovalev, V. Texture anisotropy of the brain's white matter as revealed by anatomical MRI V. Kovalev, F. Kruggel // IEEE Transactions Medical Imaging. – 2007. – Vol. 26, no 5. – P. 678–685.
Review
For citations:
Kovalev V.А. A RULE-BASED METHOD FOR TUMOR RECOGNITION IN LIVER ULTRASOUND IMAGES. Informatics. 2016;(2):59-70. (In Russ.)
Views: 871
Email this article 