[论文解读] Comparative Performance Analysis of Transformer-Based Pre-Trained Models for Detecting Keratoconus Disease

Nayeem Ahmed, Md Maruf Rahman+4 more|arXiv (Cornell University)|Aug 16, 2024

Corneal surgery and disorders被引用 5

一句话总结

本文将八种预训练的CNN用于角膜圆锥检测进行比较，确定 MobileNetV2 为最准确模型，InceptionV3 与 DenseNet121 也表现良好，而部分模型在边界样本上存在挑战。

ABSTRACT

This study compares eight pre-trained CNNs for diagnosing keratoconus, a degenerative eye disease. A carefully selected dataset of keratoconus, normal, and suspicious cases was used. The models tested include DenseNet121, EfficientNetB0, InceptionResNetV2, InceptionV3, MobileNetV2, ResNet50, VGG16, and VGG19. To maximize model training, bad sample removal, resizing, rescaling, and augmentation were used. The models were trained with similar parameters, activation function, classification function, and optimizer to compare performance. To determine class separation effectiveness, each model was evaluated on accuracy, precision, recall, and F1-score. MobileNetV2 was the best accurate model in identifying keratoconus and normal cases with few misclassifications. InceptionV3 and DenseNet121 both performed well in keratoconus detection, but they had trouble with questionable cases. In contrast, EfficientNetB0, ResNet50, and VGG19 had more difficulty distinguishing dubious cases from regular ones, indicating the need for model refining and development. A detailed comparison of state-of-the-art CNN architectures for automated keratoconus identification reveals each model's benefits and weaknesses. This study shows that advanced deep learning models can enhance keratoconus diagnosis and treatment planning. Future research should explore hybrid models and integrate clinical parameters to improve diagnostic accuracy and robustness in real-world clinical applications, paving the way for more effective AI-driven ophthalmology tools.

研究动机与目标

• 利用深度学习推动角膜圆锥自动诊断，并在一个经过筛选的数据集上评估多种预训练的 CNN 架构。
• 在标准化的训练设置下，评估每个模型区分角膜圆锥、正常和可疑病例的能力。
• 识别最先进的 CNN 在角膜圆锥识别方面的优点与局限，以指导未来的模型开发。

提出的方法

• 在一个含有三类的角膜圆锥数据集上评估八种预训练 CNN：角膜圆锥、正常和可疑。
• 在模型之间应用一致的训练配置，包括移除异常样本、调整大小、重新缩放和数据增强。
• 使用准确率、精确度、召回率和 F1 分数来衡量性能，以比较类别分离能力。

实验结果

研究问题

• RQ1 在所选数据集上，哪些预训练的 CNN 架构在角膜圆锥检测中提供最高的准确性？
• RQ2 与明确的角膜圆锥或正常病例相比，不同模型在模糊/可疑病例上的表现如何？
• RQ3 在自动化角膜圆锥诊断中，流行的 CNN 主干网络各自的优点与不足是什么？

主要发现

• MobileNetV2 在识别角膜圆锥和正常病例方面取得了最佳准确性，误判很少。
• InceptionV3 和 DenseNet121 在角膜圆锥检测方面表现良好，但在可疑/疑似病例上显示出困难。
• EfficientNetB0、ResNet50 和 VGG19 在区分可疑病例与常规病例方面存在更多困难，需进一步改进。
• 本研究强调了最先进的 CNN 架构在自动化角膜圆锥识别方面的不同优点和弱点。