基于深度学习的近视儿童感兴趣区脉络膜结构分析全自动程序
A Deep Learning-Based Fully Automated Program for Choroidal Structure Analysis Within the Region of Interest in Myopic Children.
机构信息
State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-Sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China.
Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Victoria, Australia.
出版信息
Transl Vis Sci Technol. 2023 Mar 1;12(3):22. doi: 10.1167/tvst.12.3.22.
PURPOSE
To develop and validate a fully automated program for choroidal structure analysis within a 1500-µm-wide region of interest centered on the fovea (deep learning-based choroidal structure assessment program [DCAP]).
METHODS
A total of 2162 fovea-centered radial swept-source optical coherence tomography (SS-OCT) B-scans from 162 myopic children with cycloplegic spherical equivalent refraction ranging from -1.00 to -5.00 diopters were collected to develop the DCAP. Medical Transformer network and Small Attention U-Net were used to automatically segment the choroid boundaries and the nulla (the deepest point within the fovea). Automatic denoising based on choroidal vessel luminance and binarization were applied to isolate choroidal luminal/stromal areas. To further compare the DCAP with the traditional handcrafted method, the luminal/stromal areas and choroidal vascularity index (CVI) values for 20 OCT images were measured by three graders and the DCAP separately. Intraclass correlation coefficients (ICCs) and limits of agreement were used for agreement analysis.
RESULTS
The mean ± SD pixel-wise distances from the predicted choroidal inner, outer boundary, and nulla to the ground truth were 1.40 ± 1.23, 5.40 ± 2.24, and 1.92 ± 1.13 pixels, respectively. The mean times required for choroidal structure analysis were 1.00, 438.00 ± 75.88, 393.25 ± 78.77, and 410.10 ± 56.03 seconds per image for the DCAP and three graders, respectively. Agreement between the automatic and manual area measurements was excellent (ICCs > 0.900) but poor for the CVI (0.627; 95% confidence interval, 0.279-0.832). Additionally, the DCAP demonstrated better intersession repeatability.
CONCLUSIONS
The DCAP is faster than manual methods. Also, it was able to reduce the intra-/intergrader and intersession variations to a small extent.
TRANSLATIONAL RELEVANCE
The DCAP could aid in choroidal structure assessment.
目的
开发并验证一种基于深度学习的 1500μm 宽黄斑中心凹感兴趣区（ROI）范围内脉络膜结构分析的全自动程序（基于深度学习的脉络膜结构评估程序[DCAP]）。
方法
共采集了 162 名近视儿童的 2162 个黄斑中心凹径向扫频源光相干断层扫描（SS-OCT）B 扫描，这些儿童的散瞳等效球镜屈光度范围为-1.00 至-5.00 屈光度，用于开发 DCAP。采用医学 Transformer 网络和小注意力 U-Net 自动分割脉络膜边界和黄斑中心凹最深处（nula）。基于脉络膜血管亮度和二值化进行自动去噪，以分离脉络膜管腔/基质区域。为了进一步将 DCAP 与传统的手工方法进行比较，由三位分级员和 DCAP 分别对 20 张 OCT 图像的管腔/基质区域和脉络膜血管指数（CVI）值进行测量。采用组内相关系数（ICC）和一致性界限进行一致性分析。
结果
预测的脉络膜内、外边界和 nula 与真实边界的平均像素距离分别为 1.40±1.23、5.40±2.24 和 1.92±1.13 像素。DCAP 和三位分级员分别分析脉络膜结构的平均用时为 1.00、438.00±75.88、393.25±78.77 和 410.10±56.03 秒/张。自动和手动面积测量的一致性非常好（ICC>0.900），但 CVI 的一致性较差（0.627；95%置信区间，0.279-0.832）。此外，DCAP 显示出更好的内/间次重复性。
结论
DCAP 比手动方法更快。此外，它还能够在一定程度上减少内/间分级员和间次变化。
翻译
曹泽宇
Zotero 插件