FN-OCT: Disease Detection Algorithm for Retinal Optical Coherence Tomography Based on a Fusion Network.
FN-OCT: Disease Detection Algorithm for Retinal Optical Coherence Tomography Based on a Fusion Network.
复制标题
DOI：
10.3389/fninf.2022.876927
复制
发表时间：
2022
影响因子：
3.5
通讯作者：
Lu, Yaping
中科院分区：
文献类型：
--
作者：
Ai, Zhuang;Huang, Xuan;Feng, Jing;Wang, Hui;Tao, Yong;Zeng, Fanxin;Lu, Yaping
关键词：
光学相干层析成像（OCT）是近年来发展迅速、潜力巨大的一种新型层析成像技术。它在视网膜病变的诊断中发挥着越来越重要的作用。目前，由于各地医疗资源分布不均，基层和偏远地区医生水平参差不齐，以及罕见病诊断和精准医疗的发展需求，基于深度学习的人工智能技术可以为视网膜OCT图像的识别诊断提供快速、准确、有效的解决方案。为了防止因视网膜病变的延迟发现而导致的视力损伤和失明，本文提出了一种基于融合网络（FN）的视网膜OCT分类算法（FN-OCT），以提高传统分类算法的适应性和准确性。采用InceptionV3、Inception-ResNet和Xception深度学习算法作为基分类器，在每个基分类器后加入卷积块注意机制（CBAM），并采用三种不同的融合策略对基分类器的预测结果进行合并，输出最终的预测结果（脉络膜新生血管（CNV）、糖尿病性黄斑水肿（DME）、drusen、normal）。结果表明，在涉及UCSD常见视网膜OCT数据集（来自4,686名患者的108,312张OCT图像）的分类问题中，与InceptionV3网络模型相比，FN-OCT的预测准确率提高了5.3%（准确率为98.7%，曲线下面积(AUC) = 99.1%）。在外部数据集上实现的视网膜OCT疾病分类的预测精度和AUC分别为92%和94.5%，并且使用梯度加权类激活映射（gradcam）作为可视化工具来验证所提出的FNs的有效性。这一发现表明所开发的融合算法可以显著提高分类器的性能，同时为辅助视网膜OCT的诊断提供了有力的工具和理论支持。
Optical coherence tomography (OCT) is a new type of tomography that has experienced rapid development and potential in recent years. It is playing an increasingly important role in retinopathy diagnoses. At present, due to the uneven distributions of medical resources in various regions, the uneven proficiency levels of doctors in grassroots and remote areas, and the development needs of rare disease diagnosis and precision medicine, artificial intelligence technology based on deep learning can provide fast, accurate, and effective solutions for the recognition and diagnosis of retinal OCT images. To prevent vision damage and blindness caused by the delayed discovery of retinopathy, a fusion network (FN)-based retinal OCT classification algorithm (FN-OCT) is proposed in this paper to improve upon the adaptability and accuracy of traditional classification algorithms. The InceptionV3, Inception-ResNet, and Xception deep learning algorithms are used as base classifiers, a convolutional block attention mechanism (CBAM) is added after each base classifier, and three different fusion strategies are used to merge the prediction results of the base classifiers to output the final prediction results (choroidal neovascularization (CNV), diabetic macular oedema (DME), drusen, normal). The results show that in a classification problem involving the UCSD common retinal OCT dataset (108,312 OCT images from 4,686 patients), compared with that of the InceptionV3 network model, the prediction accuracy of FN-OCT is improved by 5.3% (accuracy = 98.7%, area under the curve (AUC) = 99.1%). The predictive accuracy and AUC achieved on an external dataset for the classification of retinal OCT diseases are 92 and 94.5%, respectively, and gradient-weighted class activation mapping (Grad-CAM) is used as a visualization tool to verify the effectiveness of the proposed FNs. This finding indicates that the developed fusion algorithm can significantly improve the performance of classifiers while providing a powerful tool and theoretical support for assisting with the diagnosis of retinal OCT.
登录
查看更多内容
影响因子：
5.3
作者：
Dif, Nassima;Attaoui, Mohammed Oualid;Azzag, Hanene
通讯作者：
Azzag, Hanene
DOI：
10.1109/jbhi.2020.2982914
发表时间：
2021-01-01
影响因子：
7.7
作者：
Hassan, Taimur;Akram, Muhammad Usman;Nazir, Muhammad Noman
通讯作者：
Nazir, Muhammad Noman
DOI：
10.1016/j.chaos.2021.111310
发表时间：
2021-10
期刊：
Chaos, solitons, and fractals
影响因子：
--
作者：
Canayaz M
通讯作者：
Canayaz M
影响因子：
4.4
作者：
Bhardwaj, Charu;Jain, Shruti;Sood, Meenakshi
通讯作者：
Sood, Meenakshi
影响因子：
3.4
作者：
Karri, S. P. K.;Chakraborty, Debjani;Chatterjee, Jyotirmoy
通讯作者：
Chatterjee, Jyotirmoy