빛간섭단층촬영 영상의 분석 알고리즘에 따른 당뇨황반부종 측정치의 신뢰도 비교

Comparison of Reliability in Diabetic Macular Edema Estimates between Two Image Analysis Algorithms

목적: 당뇨황반부종에서 자동망막경계설정 소프트웨어(automatic segmentation software)인 CirrusTM High definition optical coherence tomography (HD-OCT) segmentation algorithm과 Iowa reference algorithm을 이용하여 망막층의 경계설정 신뢰도를 비교하고자 하였다. 대상과 방법: Cirrus algorithm과 Iowa algorithm을 이용하여 당뇨황반부종 환자 23명(30안)의 중심와두께를 측정하고 망막층을 세분화하여 신뢰도를 비교하였다. 두 알고리즘의 일치도, 상관관계 및 신경절세포층과 망막신경섬유층의 경계설정 오류빈도를 평가하였다. 결과: Cirrus software로 측정한 중심와두께는 평균 512.07 ± 182.35 μm로 Iowa algorithm 측정치인 476.53 ± 32.36 μm에 비해 유의하게 높았다(p＜0.05). 두 알고리즘 측정치의 급내상관계수는 0.929였고 유의한 상관관계를 보였다(β=0.868, p＜0.001). 신경절세포층과 망막신경섬유층의 경계설정 오류빈도는 중심와두께가 400 μm 미만인 경우 Cirrus algorithm과 Iowa algorithm에서 각각 45%, 9%였고 400 μm 이상인 경우 95%, 42%였다. 결론: 당뇨황반부종에서 중심와두께는 Cirrus algorithm과 Iowa algorithm 사이에 비교적 높은 일치도와 유의한 상관관계를 보였으나, 신경절세포층과 망막신경섬유층 측정에 있어서는 두 알고리즘이 차이를 보였고, 특히 중심와두께가 400 μm 이상인 경우 망막층의 경계설정 신뢰도는 Iowa algorithm에서 더 높았다.

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 ± 182.35 μm and 476.53 ± 32.36 μm, respectively (p < 0.05). The mean paired difference was 35.53 ± 92.46 μm (ICC, 0.929). Segmentation errors were demonstrated in eyes with a CFT less than 400 μm, 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 μm, 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 μm, the Iowa algorithm showed higher reliability in retinal segmentation than the Cirrus algorithm.