SpecF2M：一种用于从儿童眼底照片估算眼轴长度和屈光不正的光谱感知多任务网络
SpecF2M: A Spectral-Aware Multi-task Network Estimating Axial Length and Refractive Error from Pediatric Fundus Photographs
- The Chinese University of Hong Kong（香港中文大学）
- Shenzhen MSU-BIT University（深圳北理莫斯科大学）
- Capital Medical University（首都医科大学）
- Zhengzhou Second Hospital（郑州市第二人民医院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出SpecF2M光谱感知多任务网络，结合解剖引导增强模块等，从儿童眼底照片估算眼轴长度等近视指标，在4359例儿童数据上优于基线模型，为近视筛查提供新方法。
AI中文摘要：
球镜当量屈光（SER）和眼轴长度（AL）是儿童近视筛查的核心指标，但它们的测量需要专用的生物测量设备和散瞳验光。眼底摄影是一种易获取的成像方式，因为在45°眼底图像中可见与近视相关的后极部变化，然而这些线索往往对比度低、空间分布弥散且具有多尺度特性。此外，AL、球镜度数（SPH）和柱镜度数（CYL）具有部分重叠但并不完全相同的解剖学关联。我们提出了SpecF2M，一种用于从儿童眼底照片估算AL和SER分量的光谱感知多任务网络。SpecF2M整合了确定性解剖引导增强模块、结合MixCNN和混合光谱学习（HSL）块的混合空间-光谱骨干网络，以及用于AL、SPH和CYL分量级估算的专家路由头。在包含4359次符合条件的儿童就诊和6966张眼底图像的儿童队列中，SpecF2M在AL和SPH估算任务上优于受控的CNN/ViT基线模型，分别达到0.5347 mm和0.7062 D的平均绝对误差（MAE）。分量级分析进一步揭示了不对称的任务耦合关系，其中CYL与眼底来源的近视模式的关联弱于AL/SPH。这些结果支持基于眼底图像的、面向筛查的儿童近视指标估算，不过在部署前仍需外部验证。
英文摘要：
Spherical Equivalent Refraction (SER) and Axial Length (AL) are core indicators for pediatric myopia screening, yet their measurements require dedicated biometry and cycloplegic refraction. Fundus photography offers an accessible imaging modality, as myopia-related posterior-pole changes are visible in 45$^\circ$ fundus images. However, these cues are often low-contrast, spatially diffuse, and multi-scale. Moreover, AL, Sphere (SPH), and Cylinder (CYL) share partially overlapping but non-identical anatomical correlates. We propose SpecF2M, a spectral-aware multi-task network for estimating AL and SER components from pediatric fundus photographs. SpecF2M integrates a deterministic anatomy-guided enhancement module, a hybrid spatial--spectral backbone combining MixCNN and Hybrid Spectral Learning (HSL) blocks, and an expert-routing head for component-level estimation of AL, SPH, and CYL. On a pediatric cohort of 4,359 eligible child visits and 6,966 fundus images, SpecF2M outperforms controlled CNN/ViT baselines for AL and SPH estimation, achieving MAEs of 0.5347 mm and 0.7062 D, respectively. Component-level analysis further reveals asymmetric task coupling, where CYL exhibits weaker association with fundus-derived myopic patterns than AL/SPH. These results support fundus-based, screening-oriented estimation of pediatric myopia indicators, while external validation remains necessary before deployment.
