深度学习在圆锥角膜早期诊断辅助系统中的应用实践
|
摘要
针对圆锥角膜早期病变尚未存在标准诊断的问题,同时为了辅助特检科医师、眼科医师有效地进行早期诊断,通过分析各检测仪器的优缺点,选择在角膜OCT检查上应用深度学习技术,构建圆锥角膜早期诊断辅助系统。该系统采用改良后的VGG-16实现了约68%圆锥角膜病变的识别精度,临床验证该系统能在一定程度上辅助医师下达诊断的信心,同时医师对OCT检查的再标记可以帮助系统训练出更精准的判断。
In view of the problem that there is no standard diagnosis for early stage keratoconus disease,at the same time to assist the special examiner and ophthalmologist to make the early diagnosis effectively, the advantages and disadvantages of each testing instrument were analyzed. In order to construct an assistant system for early diagnosis of keratoconus, a deep learning technique was applied in corneal OCT examination. The system used improved VGG-16 to realize the recognition accuracy of about 68% keratoconus keratopathy, and the clinical results showed that the system can help doctors to give diagnosis confidence to a certain extent. At the same time, the physician's re-marking of OCT can help train the system for more accurate judgment.
In view of the problem that there is no standard diagnosis for early stage keratoconus disease,at the same time to assist the special examiner and ophthalmologist to make the early diagnosis effectively, the advantages and disadvantages of each testing instrument were analyzed. In order to construct an assistant system for early diagnosis of keratoconus, a deep learning technique was applied in corneal OCT examination. The system used improved VGG-16 to realize the recognition accuracy of about 68% keratoconus keratopathy, and the clinical results showed that the system can help doctors to give diagnosis confidence to a certain extent. At the same time, the physician's re-marking of OCT can help train the system for more accurate judgment.
引文
[1]拉风的三藏.近视拯救行动之激光矫正术[J].课堂内外:科学fans,2017(7):26-27.
[2]王勤美.屈光手术的回顾和展望[J].中华眼视光学与视觉科学杂志,2010,12(1):2-4.
[3]胡亮,王勤美.从被动到主动--圆锥角膜诊疗思路的改变[J].中华眼视光学与视觉科学杂志,2015,17(1):4-8.
[4]杨亮,乌云,金宝泉,等.圆锥角膜早期诊断的研究进展[J].临床眼科杂志,2013,21(6):560-563.
[5]GALLETTI J G,PFORTNER T,BONTHOUX F F.Improved keratoconus detection by ocular response analyzer testing after consideration of corneal thickness as a confounding factor[J].JRefract Surg,2012,28(3):202-208.
[6]苏小连,吴文静,王雁.Optovue iVue OCT测量角膜厚度的可重复性及其与Pentacam、Visante OCT的一致性研究[J].中华实验眼科杂志,2015,33(2):135-140.
[7]SONG H A,LEE S Y.Hierarchical representation using NMF[J].2013,8226:466-473.
[8]谢培英.圆锥角膜的患病率及临床症状[J].中国眼镜科技杂志,2010(1):118-121.
[9]RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet large scale visual recognition challenge[J].Int J Comput Vis,2015,115(3):211-252.
[2]王勤美.屈光手术的回顾和展望[J].中华眼视光学与视觉科学杂志,2010,12(1):2-4.
[3]胡亮,王勤美.从被动到主动--圆锥角膜诊疗思路的改变[J].中华眼视光学与视觉科学杂志,2015,17(1):4-8.
[4]杨亮,乌云,金宝泉,等.圆锥角膜早期诊断的研究进展[J].临床眼科杂志,2013,21(6):560-563.
[5]GALLETTI J G,PFORTNER T,BONTHOUX F F.Improved keratoconus detection by ocular response analyzer testing after consideration of corneal thickness as a confounding factor[J].JRefract Surg,2012,28(3):202-208.
[6]苏小连,吴文静,王雁.Optovue iVue OCT测量角膜厚度的可重复性及其与Pentacam、Visante OCT的一致性研究[J].中华实验眼科杂志,2015,33(2):135-140.
[7]SONG H A,LEE S Y.Hierarchical representation using NMF[J].2013,8226:466-473.
[8]谢培英.圆锥角膜的患病率及临床症状[J].中国眼镜科技杂志,2010(1):118-121.
[9]RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet large scale visual recognition challenge[J].Int J Comput Vis,2015,115(3):211-252.