A Novel Hierarchical Deep Learning Framework for Diagnosing Multiple Visual Impairment Diseases in the Clinical Environment.
A Novel Hierarchical Deep Learning Framework for Diagnosing Multiple Visual Impairment Diseases in the Clinical Environment.
复制标题
临床环境下诊断多种视障疾病的新的分层深度学习框架。
DOI：
10.3389/fmed.2021.654696
复制
发表时间：
2021
影响因子：
3.9
通讯作者：
Chen J
中科院分区：
文献类型：
--
作者：
Hong J;Liu X;Guo Y;Gu H;Gu L;Xu J;Lu Y;Sun X;Ye Z;Liu J;Peters BA;Chen J
早期发现和治疗视力障碍疾病对于对抗可避免的失明至关重要且不可或缺。为此，基于人工智能的疾病识别方法对于视力障碍疾病至关重要，特别是对于生活在眼科医生较少的地区的人们来说。在这项研究中，我们展示了使用从粗到细的方法来识别多种视觉障碍疾病。我们设计了一个分层深度学习网络，它由一系列多任务和多标签学习分类器组成，代表从预定义的分层眼病分类法派生的不同级别的眼病。提出了多级疾病引导损失函数来学习眼部疾病特征的细粒度变异性。所提出的框架针对眼表和视网膜图像进行了独立训练。训练数据集包含来自 1,600 名患有 100 种疾病的患者的 7,100 张临床图像。为了证明所提出的框架的可行性，我们在眼部疾病分类的前两个级别上证明了眼部疾病的识别，即7种眼部疾病在1级中具有4种眼表疾病和3种视网膜眼底疾病，以及17个亚类在2级中具有9种眼表疾病和8种视网膜眼底疾病。所提出的框架是灵活和可扩展的，本质上可以在更多级别上进行训练，每个亚型疾病都有足够的训练数据（例如， 2级17类包括定义为3级疾病的100种亚型疾病）。针对 40 名经过委员会认证的眼科医生对各种视力障碍疾病的临床病例对所提出的框架的性能进行了评估，结果表明所提出的框架在识别所有已确定的失明主要原因方面具有较高的敏感性和特异性，受试者工作特征曲线下面积范围为 0.743 至 0.989。对三级眼科中心 4,670 例病例的进一步评估也表明，与临床环境中的人类分级员相比，该框架对不同视觉障碍疾病实现了较高的识别准确率。拟议的分层深度学习框架将改善眼科临床实践并扩大可用服务范围，特别是对于生活在眼科医生较少的地区的人们。
Early detection and treatment of visual impairment diseases are critical and integral to combating avoidable blindness. To enable this, artificial intelligence–based disease identification approaches are vital for visual impairment diseases, especially for people living in areas with a few ophthalmologists. In this study, we demonstrated the identification of a large variety of visual impairment diseases using a coarse-to-fine approach. We designed a hierarchical deep learning network, which is composed of a family of multi-task & multi-label learning classifiers representing different levels of eye diseases derived from a predefined hierarchical eye disease taxonomy. A multi-level disease–guided loss function was proposed to learn the fine-grained variability of eye disease features. The proposed framework was trained for both ocular surface and retinal images, independently. The training dataset comprised 7,100 clinical images from 1,600 patients with 100 diseases. To show the feasibility of the proposed framework, we demonstrated eye disease identification on the first two levels of the eye disease taxonomy, namely 7 ocular diseases with 4 ocular surface diseases and 3 retinal fundus diseases in level 1 and 17 subclasses with 9 ocular surface diseases and 8 retinal fundus diseases in level 2. The proposed framework is flexible and extensible, which can be inherently trained on more levels with sufficient training data for each subtype diseases (e.g., the 17 classes of level 2 include 100 subtype diseases defined as level 3 diseases). The performance of the proposed framework was evaluated against 40 board-certified ophthalmologists on clinical cases with various visual impairment diseases and showed that the proposed framework had high sensitivity and specificity with the area under the receiver operating characteristic curve ranging from 0.743 to 0.989 in identifying all identified major causes of blindness. Further assessment of 4,670 cases in a tertiary eye center also demonstrated that the proposed framework achieved a high identification accuracy rate for different visual impairment diseases compared with that of human graders in a clinical setting. The proposed hierarchical deep learning framework would improve clinical practice in ophthalmology and broaden the scope of service available, especially for people living in areas with a few ophthalmologists.