Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy.
Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy.
复制标题
DOI：
10.1371/journal.pone.0179790
复制
发表时间：
2017
期刊：
影响因子：
3.7
通讯作者：
Kawashima H
中科院分区：
文献类型：
--
作者：
Takahashi H;Tampo H;Arai Y;Inoue Y;Kawashima H
疾病分期涉及疾病严重程度或进展的评估，并用于治疗选择。在糖尿病视网膜病变中，使用宽区域的疾病分期比使用有限区域的疾病分期更可取。我们研究了深度学习人工智能（AI）是否可用于对糖尿病视网膜病变进行分级并确定治疗和预后。这项回顾性研究分析了2,740名糖尿病患者的9,939张后极照片。2011年5月至2015年6月期间，在Jichi Medical University每年对每只眼睛的四个视野拍摄非散瞳45 °视野彩色眼底照片。一个经过修改的完全随机初始化的GoogLeNet深度学习神经网络在95%的照片上进行了训练，使用手动修改的Davis对另外三张相邻照片进行分级。我们使用真实的照片对9,939张后极眼底照片中的4,709张进行了分级。此外，95%的照片是由修改后的GoogLeNet学习的。主要结果测量是剩余5%照片的患病率和AI分期的偏倚调整Fleiss 'kappa（PABAK）。PABAK对改良Davis评分为0.64（准确率为81%; 496张照片中有402张正确答案）。PABAK对真实的预后分级为0.37（准确率96%）。我们提出了一种新的AI疾病分期系统，用于对糖尿病视网膜病变进行分级，该系统涉及眼底镜检查中通常看不到的视网膜区域和另一种直接建议治疗并确定视网膜病变的AI。
Disease staging involves the assessment of disease severity or progression and is used for treatment selection. In diabetic retinopathy, disease staging using a wide area is more desirable than that using a limited area. We investigated if deep learning artificial intelligence (AI) could be used to grade diabetic retinopathy and determine treatment and prognosis. The retrospective study analyzed 9,939 posterior pole photographs of 2,740 patients with diabetes. Nonmydriatic 45° field color fundus photographs were taken of four fields in each eye annually at Jichi Medical University between May 2011 and June 2015. A modified fully randomly initialized GoogLeNet deep learning neural network was trained on 95% of the photographs using manual modified Davis grading of three additional adjacent photographs. We graded 4,709 of the 9,939 posterior pole fundus photographs using real prognoses. In addition, 95% of the photographs were learned by the modified GoogLeNet. Main outcome measures were prevalence and bias-adjusted Fleiss’ kappa (PABAK) of AI staging of the remaining 5% of the photographs. The PABAK to modified Davis grading was 0.64 (accuracy, 81%; correct answer in 402 of 496 photographs). The PABAK to real prognosis grading was 0.37 (accuracy, 96%). We propose a novel AI disease-staging system for grading diabetic retinopathy that involves a retinal area not typically visualized on fundoscopy and another AI that directly suggests treatments and determines prognoses.