A Proposal of Measuring Method for the Size of Abnormal Part Using Correlation Coefficient on Intensity Distribution from Optical Coherence Tomography Images

In ophthalmology, optical coherence tomography(OCT) is rapidly becoming popular to diagnose retinal diseases.However, the quantitative evaluation of retinal diseases has notbeen established for OCT image. Some clinical doctors desire acomputer-aided diagnosis system to evaluate the size and thedegree of disease quantitatively. In previous researches, thesize of the retinal diseases is measured as abnormal parts ofsmall regions in the number of layer boundaries, which isestimated by analysis method on a gray level profile for anOCT image. However, in an abnormal part, the difference ofthe number of layer boundaries is small between abnormalparts and normal parts, and the previous method can’t detectthe size of the abnormal part. In this research, we propose anew method to measure the size of abnormal parts using correlationcoefficient in gray level distribution for an OCT image.In the gray level distributions of the OCT image, the correlationcoefficient is large in normal parts, and the coefficient issmall between normal regions and abnormal parts. Therefore,our system can detect the position of borders between abnormalparts and normal parts using the distribution of correlationcoefficient. We apply the proposed method to some retinaldisease images. For an OCT image, we obtained the overlaprate 92.3[%] between the identified part by the proposed methodand the clinical doctor for the abnormal part. The overlaprate is improved for 21 OCT images among 25 OCT images,and the improved rate in the proposed method is 84[%]compared with the previous metho