Àá½Ã¸¸ ±â´Ù·Á ÁÖ¼¼¿ä. ·ÎµùÁßÀÔ´Ï´Ù.
KMID : 0360220160570050772
Journal of the Korean Ophthalmological Society
2016 Volume.57 No. 5 p.772 ~ p.778
Comparison of Reliability in Diabetic Macular Edema Estimates between Two Image Analysis Algorithms
°èÈ¿Á¤:Gye Hyo-Jung
¹èÁ¤ÈÆ:Bae Jeong-Hun/¼Û¼öÁ¤:Song Su-Jeong
Abstract
Purpose: To evaluate segmentation reliability in diabetic macular edema (DME) estimates between a CirrusTM HD-OCT image analysis algorithm and an Iowa reference algorithm, which are an automatic segmentation software.

Methods: Thirty eyes from 23 patients diagnosed with DME were included and underwent spectral-domain optical coherence scans (CirrusTM HD-OCT). Central foveal thickness (CFT) and ganglion cell layer-inner plexiform layer segmentation data were compared with those produced by the CirrusTM HD-OCT segmentation algorithm and Iowa reference algorithm. Measurement agreement was assessed using intraclass correlation (ICC) and segmentation errors were confirmed by 2 ophthalmologists.

Results: The mean CFT in the 1-mm central area determined by the manufacturer-supplied Cirrus software and Iowa reference algorithm was 512.07 ¡¾ 182.35 ¥ìm and 476.53 ¡¾ 32.36 ¥ìm, respectively (p < 0.05). The mean paired difference was 35.53 ¡¾ 92.46 ¥ìm (ICC, 0.929). Segmentation errors were demonstrated in eyes with a CFT less than 400 ¥ìm, specifically for 45% of scans obtained by the Cirrus algorithm and 9% from the Iowa algorithm; in eyes with a CFT equal to or higher than 400 ¥ìm, the error rates were 95% and 42%, respectively.

Conclusions: CFT measurement in eyes with diabetic macular edema using the Cirrus algorithm and Iowa algorithm showed relatively high degrees of agreement and significant correlation. In eyes with a CFT equal to or higher than 400 ¥ìm, the Iowa algorithm showed higher reliability in retinal segmentation than the Cirrus algorithm.
KEYWORD
Central foveal thickness, Diabetic macular edema, Optical coherence tomography, Reliability, Segmentation algorithm
FullTexts / Linksout information
 
Listed journal information
ÇмúÁøÈïÀç´Ü(KCI) KoreaMed ´ëÇÑÀÇÇÐȸ ȸ¿ø