D'Souza Gavin, Siddalingaswamy P C, Pandya Mayur Anand
Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka 576104 India.
Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka 576104 India.
Biomed Eng Lett. 2023 Jul 30;14(1):23-33. doi: 10.1007/s13534-023-00307-6. eCollection 2024 Jan.
Glaucoma is one of the leading causes of permanent blindness in the world. It is caused due to an increase in the intraocular pressure within the eye that harms the optic nerve. People suffering from Glaucoma often do not notice any changes in their vision in the early stages. However, as it progresses, Glaucoma usually leads to vision loss that is irreversible in many cases. Thus, early diagnosis of this eye disease is of critical importance. The fundus image is one of the most used diagnostic tools for glaucoma detection. However, drawing accurate insights from these images requires them to be manually analyzed by medical experts, which is a time-consuming process. In this work, we propose a parameter-efficient AlterNet-K model based on an alternating design pattern, which combines ResNets and multi-head self-attention (MSA) to leverage their complementary properties to improve the generalizability of the overall model. The model was trained on the Rotterdam EyePACS AIROGS dataset, comprising 113,893 colour fundus images from 60,357 subjects. The AlterNet-K model outperformed transformer models such as ViT, DeiT-S, and Swin transformer, standard DCNN models including ResNet, EfficientNet, MobileNet and VGG with an accuracy of 0.916, AUROC of 0.968 and F1 score of 0.915. The results indicate that smaller CNN models combined with self-attention mechanisms can achieve high classification accuracies. Small and compact Resnet models combined with MSA outperform their larger counterparts. The models in this work can be extended to handle classification tasks in other medical imaging domains.
青光眼是全球永久性失明的主要原因之一。它是由眼内眼压升高导致的，眼压升高会损害视神经。青光眼患者在早期通常不会注意到视力有任何变化。然而，随着病情发展，青光眼通常会导致视力丧失，在许多情况下这种视力丧失是不可逆的。因此，这种眼部疾病的早期诊断至关重要。眼底图像是青光眼检测中最常用的诊断工具之一。然而，要从这些图像中得出准确的见解，需要医学专家对其进行人工分析，这是一个耗时的过程。在这项工作中，我们基于交替设计模式提出了一种参数高效的AlterNet-K模型，该模型结合了残差网络（ResNets）和多头自注意力机制（MSA），以利用它们的互补特性来提高整个模型的泛化能力。该模型在鹿特丹EyePACS AIROGS数据集上进行训练，该数据集包含来自60357名受试者的113893张彩色眼底图像。AlterNet-K模型的表现优于诸如视觉Transformer（ViT）、数据高效图像Transformer（DeiT-S）和Swin Transformer等Transformer模型，以及包括ResNet、高效神经网络（EfficientNet）、移动神经网络（MobileNet）和VGG在内的标准深度卷积神经网络（DCNN）模型，其准确率为0.916，曲线下面积（AUROC）为0.968，F1分数为0.915。结果表明，较小的卷积神经网络模型与自注意力机制相结合可以实现较高的分类准确率。小型紧凑的Resnet模型与MSA相结合的表现优于更大的同类模型。这项工作中的模型可以扩展到处理其他医学成像领域的分类任务。
