Current Proceedings on Technology

Yazarlar: Mohd Fadzil Abdul Kadir, Shinji Tsuruoka, Haruhiko Takase, Hiroharu Kawanaka, Fumio Okuyama, Yukitaka Uji, Hisashi Matsubara, Hisanori Yagami

Konular:-

Anahtar Kelimeler:Optical coherence tomography,Regional statistic,Region of interest

Özet: Optical Coherence Tomography (OCT) in ophthalmology is an emerging technology that can provide high-resolution cross-sectional images of the retina for identifying, and quantitatively assessing of the disease. In previous researches, we proposed some automatic measurement methods of the thickness between Inner Limiting Membrane (ILM) and Retinal Pigment Epithelium (RPE) from OCT images. The method has a large problem that cannot extract the border of an abnormal part for the evaluation of the effect in some cases using the treatment by medical doctors. In this paper, we propose a new method to measure the disease area using regional statistics, that is, mean and standard deviation. The objective of this research is to extract the border of abnormal part so that we can evaluate the effectiveness of the treatment by comparing the abnormal area before and after taking treatment or between the previous observed images and a new current image.  The method calculates the mean and standard deviation of gray level in the region of interest (ROI) in the abnormal area at pointed area by medical doctor. These values compare with every ROI in the abnormal area to determine, extract, and calculate the disease area. The accuracy of the proposed automatic extraction is more than 90%.

---