Abstract
Automatic measurements of tear meniscus height (TMH) have been achieved by using deep learning techniques; however, annotation is significantly influenced by subjective factors and is both time-consuming and labor-intensive. In this paper, we introduce an automatic TMH measurement technique based on edge detection-assisted annotation within a deep learning framework. This method generates mask labels less affected by subjective factors with enhanced efficiency compared to previous annotation approaches. For improved segmentation of the pupil and tear meniscus areas, the convolutional neural network Inceptionv3 was first implemented as an image quality assessment model, effectively identifying higher-quality images with an accuracy of 98.224%. Subsequently, by using the generated labels, various algorithms, including Unet, ResUnet, Deeplabv3+FcnResnet101, Deeplabv3+FcnResnet50, FcnResnet50, and FcnResnet101 were trained, with Unet demonstrating the best performance. Finally, Unet was used for automatic pupil and tear meniscus segmentation to locate the center of the pupil and calculate TMH,respectively. An evaluation of the mask quality predicted by Unet indicated a Mean Intersection over Union of 0.9362, a recall of 0.9261, a precision of 0.9423, and an F1-Score of 0.9326. Additionally, the TMH predicted by the model was assessed, with the fitting curve represented as y= 0.982x-0.862, an overall correlation coefficient of r^2=0.961 , and an accuracy of 94.80% (237/250). In summary, the algorithm can automatically screen images based on their quality,segment the pupil and tear meniscus areas, and automatically measure TMH. Measurement results using the AI algorithm demonstrate a high level of consistency with manual measurements, offering significant support to clinical doctors in diagnosing dry eye disease.
Abstract (translated)
通过使用深度学习技术实现对 tears meniscus height (TMH) 的自动测量;然而,注释受到主观因素的影响,并且耗时且劳动密集。在本文中,我们介绍了一种基于深度学习框架的自动 TMH 测量技术。与之前注释方法相比,该方法生成的掩码标签受到主观因素的影响较小,效率更高。为了提高对瞳孔和泪液 meniscus 区域的分割,我们首先将卷积神经网络 Inceptionv3 实现为图像质量评估模型,有效识别出准确率高达 98.224% 的更高质量图像。接着,通过生成的标签,对各种算法进行训练,包括 Unet、ResUnet、Deeplabv3+FcnResnet101、Deeplabv3+FcnResnet50、FcnResnet50 和 FcnResnet101。其中,Unet 的表现最佳。最后,我们使用 Unet 对自动瞳孔和泪液 meniscus 区域进行分割,分别计算 TMH。使用 Unet 的预测掩码质量评估表明平均交集 over Union 为 0.9362,召回率为 0.9261,精确率为 0.9423,F1- 分数为 0.9326。此外,对模型的 TMH 预测进行评估,拟合曲线表示为 y = 0.982x - 0.862,相关系数 r^2 = 0.961,准确率高达 94.80%(237/250)。总之,该算法可以根据图像质量自动筛选图像,分割瞳孔和泪液 meniscus 区域,并自动测量 TMH。使用 AI 算法进行的测量结果与手动测量结果一致,为临床医生在诊断干眼病方面提供了有力的支持。
URL
https://arxiv.org/abs/2403.15853