Eye Institute, Eye and Ear, Nose, and Throat Hospital of Fudan University, Shanghai, China.
Key Laboratory of Myopia, Ministry of Health, Shanghai, China.
Transl Vis Sci Technol. 2024 Sep 3;13(9):12. doi: 10.1167/tvst.13.9.12.
To develop a novel classification of highly myopic eyes using artificial intelligence (AI) and investigate its relationship with contrast sensitivity function (CSF) and fundus features.
We enrolled 616 highly myopic eyes of 616 patients. CSF was measured using the quantitative CSF method. Myopic macular degeneration (MMD) was graded according to the International META-PM Classification. Thickness of the macula and peripapillary retinal nerve fiber layer (p-RNFL) were assessed by fundus photography and optical coherence tomography, respectively. Classification was performed by combining CSF and fundus features with principal component analysis and k-means clustering.
With 83.35% total variance explained, highly myopic eyes were classified into four AI categories. The percentages of AI categories 1 to 4 were 14.9%, 37.5%, 36.2%, and 11.4%, respectively. Contrast acuity of the eyes in AI category 1 was the highest, which decreased by half in AI category 2. For AI categories 2 to 4, every increase in category led to a decrease of 0.23 logarithm of the minimum angle of resolution in contrast acuity. Compared with those in AI category 1, eyes in AI category 2 presented a higher percentage of MMD2 and thinner temporal p-RNFL. Eyes in AI categories 3 and 4 presented significantly higher percentage of MMD ≥ 3, thinner nasal macular thickness and p-RNFL (P < 0.05). Multivariate regression showed AI category 4 had higher MMD grades and thinner macular compared with AI category 3.
We proposed an AI-based classification of highly myopic eyes with clear relevance to visual function and fundus features.
This classification helps to discover the early hidden visual deficits of highly myopic patients, becoming a useful tool to evaluate the disease comprehensively.
利用人工智能（AI）开发一种新的高度近视眼分类方法，并研究其与对比敏感度功能（CSF）和眼底特征的关系。
我们纳入了 616 名 616 例高度近视患者的 616 只眼。使用定量 CSF 方法测量 CSF。根据国际 META-PM 分类对近视性黄斑变性（MMD）进行分级。通过眼底照相和光学相干断层扫描分别评估黄斑和视盘周围视网膜神经纤维层（p-RNFL）的厚度。通过主成分分析和 K-均值聚类结合 CSF 和眼底特征进行分类。
用 83.35%的总方差解释，高度近视眼分为 4 个 AI 类别。AI 类别 1 至 4 的百分比分别为 14.9%、37.5%、36.2%和 11.4%。AI 类别 1 眼的对比视力最高，在 AI 类别 2 中降低了一半。对于 AI 类别 2 到 4，每个类别增加都会导致对比视力中的最小分辨角对数降低 0.23。与 AI 类别 1 相比，AI 类别 2 眼的 MMD2 发生率更高，颞侧 p-RNFL 更薄。AI 类别 3 和 4 眼的 MMD≥3 发生率更高，鼻侧黄斑厚度和 p-RNFL 更薄（P<0.05）。多元回归显示，与 AI 类别 3 相比，AI 类别 4 具有更高的 MMD 分级和更薄的黄斑。
我们提出了一种基于 AI 的高度近视眼分类方法，与视觉功能和眼底特征具有明显的相关性。
石亚东
