早产儿视网膜病变诊断的观察者及特征分析
OBSERVER AND FEATURE ANALYSIS ON DIAGNOSIS OF RETINOPATHY OF PREMATURITY.
作者信息
Ataer-Cansizoglu E, You S, Kalpathy-Cramer J, Keck K, Chiang M F, Erdogmus D
机构信息
Cognitive Systems Laboratory, Northeastern University, Boston, MA.
Martinos Center for Biomedical Imaging, Charlestown, MA.
出版信息
IEEE Int Workshop Mach Learn Signal Process. 2012:1-6. doi: 10.1109/MLSP.2012.6349809.
Abstract
Retinopathy of prematurity (ROP) is a disease affecting low-birth weight infants and is a major cause of childhood blindness. However, human diagnoses is often subjective and qualitative. We propose a method to analyze the variability of expert decisions and the relationship between the expert diagnoses and features. The analysis is based on Mutual Information and Kernel Density Estimation on features. The experiments are carried out on a dataset of 34 retinal images diagnosed by 22 experts. The results show that a group of observers decide consistently with each other and there are popular features that have a high correlation with labels.
摘要
早产儿视网膜病变（ROP）是一种影响低体重婴儿的疾病，是儿童失明的主要原因。然而，人工诊断往往具有主观性和定性性。我们提出了一种方法来分析专家决策的可变性以及专家诊断与特征之间的关系。该分析基于特征的互信息和核密度估计。实验是在由22位专家诊断的34张视网膜图像的数据集上进行的。结果表明，一组观察者之间的决策一致，并且存在与标签高度相关的常见特征。
相似文献
1
OBSERVER AND FEATURE ANALYSIS ON DIAGNOSIS OF RETINOPATHY OF PREMATURITY.早产儿视网膜病变诊断的观察者及特征分析
IEEE Int Workshop Mach Learn Signal Process. 2012:1-6. doi: 10.1109/MLSP.2012.6349809.
2
Analysis of underlying causes of inter-expert disagreement in retinopathy of prematurity diagnosis. Application of machine learning principles.早产儿视网膜病变诊断中专家间分歧的潜在原因分析。机器学习原理的应用。
Methods Inf Med. 2015;54(1):93-102. doi: 10.3414/ME13-01-0081. Epub 2014 Dec 1.
3
Dealing with inter-expert variability in retinopathy of prematurity: A machine learning approach.应对早产儿视网膜病变专家间的差异：一种机器学习方法。
Comput Methods Programs Biomed. 2015 Oct;122(1):1-15. doi: 10.1016/j.cmpb.2015.06.004. Epub 2015 Jun 16.
4
Toward a severity index for ROP: An unsupervised approach.迈向ROP严重程度指数：一种无监督方法。
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:1312-1315. doi: 10.1109/EMBC.2016.7590948.
5
Plus disease in retinopathy of prematurity: qualitative analysis of diagnostic process by experts.早产儿视网膜病变中的 Plus 病：专家对诊断过程的定性分析。
JAMA Ophthalmol. 2013 Aug;131(8):1026-32. doi: 10.1001/jamaophthalmol.2013.135.
6
[Reliability of retinal imaging screening in retinopathy of prematurity].[早产儿视网膜病变视网膜成像筛查的可靠性]
An Pediatr (Barc). 2014 Sep;81(3):149-54. doi: 10.1016/j.anpedi.2013.10.055. Epub 2013 Dec 7.
7
[Telemedicine correlation in retinopathy of prematurity between experts and non-expert observers].[早产儿视网膜病变中专家与非专家观察者之间的远程医疗相关性]
Arch Soc Esp Oftalmol. 2015 Jan;90(1):9-13. doi: 10.1016/j.oftal.2014.06.007. Epub 2014 Nov 15.
8
Automated Detection and Classification of Telemedical Retinopathy of Prematurity Images.自动化检测和分类早产儿视网膜病变的远程医疗图像。
Telemed J E Health. 2020 Mar;26(3):354-358. doi: 10.1089/tmj.2019.0004. Epub 2019 May 14.
9
Plus Disease in Retinopathy of Prematurity: A Continuous Spectrum of Vascular Abnormality as a Basis of Diagnostic Variability.早产儿视网膜病变中的附加病变：作为诊断变异性基础的连续血管异常谱。
Ophthalmology. 2016 Nov;123(11):2338-2344. doi: 10.1016/j.ophtha.2016.07.026. Epub 2016 Aug 31.
10
A computer-aided diagnosis system for plus disease in retinopathy of prematurity with structure adaptive segmentation and vessel based features.基于结构自适应分割和血管特征的早产儿视网膜病变中“+”病的计算机辅助诊断系统。
Comput Med Imaging Graph. 2019 Jun;74:72-94. doi: 10.1016/j.compmedimag.2019.04.003. Epub 2019 Apr 18.
引用本文的文献
1
Optical coherence tomography angiography reveals progressive worsening of retinal vascular geometry in diabetic retinopathy and improved geometry after panretinal photocoagulation.光学相干断层扫描血管造影显示糖尿病视网膜病变的视网膜血管几何形状进行性恶化，全视网膜光凝治疗后几何形状改善。
PLoS One. 2019 Dec 30;14(12):e0226629. doi: 10.1371/journal.pone.0226629. eCollection 2019.
2
Expert Diagnosis of Plus Disease in Retinopathy of Prematurity From Computer-Based Image Analysis.基于计算机图像分析的早产儿视网膜病变中 Plus 病的专家诊断。
JAMA Ophthalmol. 2016 Jun 1;134(6):651-7. doi: 10.1001/jamaophthalmol.2016.0611.
3
Computer-Based Image Analysis for Plus Disease Diagnosis in Retinopathy of Prematurity: Performance of the "i-ROP" System and Image Features Associated With Expert Diagnosis.基于计算机的早产儿视网膜病变中增值性病变诊断的图像分析：“i-ROP”系统的性能及与专家诊断相关的图像特征
Transl Vis Sci Technol. 2015 Nov 30;4(6):5. doi: 10.1167/tvst.4.6.5. eCollection 2015 Nov.
4
Dealing with inter-expert variability in retinopathy of prematurity: A machine learning approach.应对早产儿视网膜病变专家间的差异：一种机器学习方法。
Comput Methods Programs Biomed. 2015 Oct;122(1):1-15. doi: 10.1016/j.cmpb.2015.06.004. Epub 2015 Jun 16.
5
Aggressive posterior retinopathy of prematurity: a pilot study of quantitative analysis of vascular features.侵袭性早产儿视网膜病变：血管特征定量分析的初步研究
Graefes Arch Clin Exp Ophthalmol. 2015 Feb;253(2):181-7. doi: 10.1007/s00417-014-2857-2. Epub 2014 Nov 21.
6
Manifold Learning by Preserving Distance Orders.通过保持距离顺序进行流形学习。
Pattern Recognit Lett. 2014 Mar 1;38:120-131. doi: 10.1016/j.patrec.2013.11.022.
本文引用的文献
1
Semiautomated digital image analysis of posterior pole vessels in retinopathy of prematurity.早产儿视网膜病变后极部血管的半自动数字图像分析
J AAPOS. 2009 Oct;13(5):504-6. doi: 10.1016/j.jaapos.2009.06.007.
2
Computerized analysis of retinal vessel width and tortuosity in premature infants.早产儿视网膜血管宽度和迂曲度的计算机分析
Invest Ophthalmol Vis Sci. 2008 Aug;49(8):3577-85. doi: 10.1167/iovs.07-1353. Epub 2008 Apr 11.
3
Agreement among pediatric ophthalmologists in diagnosing plus and pre-plus disease in retinopathy of prematurity.小儿眼科医生在诊断早产儿视网膜病变中的加病变和前期加病变方面的一致性。
J AAPOS. 2008 Aug;12(4):352-6. doi: 10.1016/j.jaapos.2007.11.022. Epub 2008 Mar 10.
4
Evaluation of a computer-based system for plus disease diagnosis in retinopathy of prematurity.基于计算机系统对早产儿视网膜病变中加病诊断的评估。
Ophthalmology. 2007 Dec;114(12):e59-67. doi: 10.1016/j.ophtha.2007.10.006.
5
Plus disease in retinopathy of prematurity: pilot study of computer-based and expert diagnosis.早产儿视网膜病变中的附加病变：基于计算机和专家诊断的初步研究
J AAPOS. 2007 Dec;11(6):532-40. doi: 10.1016/j.jaapos.2007.09.005. Epub 2007 Oct 29.
6
Accuracy of ROPtool vs individual examiners in assessing retinal vascular tortuosity.ROPtool与个体检查者在评估视网膜血管迂曲方面的准确性。
Arch Ophthalmol. 2007 Nov;125(11):1523-30. doi: 10.1001/archopht.125.11.1523.
7
Neonatologists' practices and experiences in arranging retinopathy of prematurity screening services.新生儿科医生在安排早产儿视网膜病变筛查服务方面的做法与经验。
Pediatrics. 2007 Sep;120(3):527-31. doi: 10.1542/peds.2007-0378.
8
Interexpert agreement of plus disease diagnosis in retinopathy of prematurity.早产儿视网膜病变中加病诊断的专家间一致性
Arch Ophthalmol. 2007 Jul;125(7):875-80. doi: 10.1001/archopht.125.7.875.
9
Subvoxel precise skeletons of volumetric data based on fast marching methods.基于快速行进法的体数据亚体素精确骨架
Med Phys. 2007 Feb;34(2):627-38. doi: 10.1118/1.2409238.
10
Diagnosis of plus disease in retinopathy of prematurity using Retinal Image multiScale Analysis.使用视网膜图像多尺度分析诊断早产儿视网膜病变中的附加病变
Invest Ophthalmol Vis Sci. 2005 Dec;46(12):4734-8. doi: 10.1167/iovs.05-0646.
Zotero 插件