Retinopathy of Prematurity-assist: Novel Software for Detecting Plus Disease
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: To design software with a novel algorithm, which analyzes the tortuosity and vascular dilatation infundal images of retinopathy of prematurity (ROP) patients with an acceptable accuracy for detecting plus disease. Methods: Eighty-seven well-focused fundal images taken with RetCam were classified to three groups of plus,non-plus, and pre-plus by agreement between three ROP experts. Automated algorithms in this study weredesigned based on two methods: the curvature measure and distance transform for assessment of tortuosityand vascular dilatation, respectively as two major parameters of plus disease detection. Results: Thirty-eight plus, 12 pre-plus, and 37 non-plus images, which were classified by three experts, weretested by an automated algorithm and software evaluated the correct grouping of images in comparison toexpert voting with three different classifiers, k-nearest neighbor, support vector machine and multilayer perceptronnetwork. The plus, pre-plus, and non-plus images were analyzed with 72.3%, 83.7%, and 84.4%accuracy, respectively. Conclusions: The new automated algorithm used in this pilot scheme for diagnosis and screening of patientswith plus ROP has acceptable accuracy. With more improvements, it may become particularly useful, especiallyin centers without a skilled person in the ROP field.
Abstract
Purpose: To design software with a novel algorithm, which analyzes the tortuosity and vascular dilatation infundal images of retinopathy of prematurity (ROP) patients with an acceptable accuracy for detecting plus disease. Methods: Eighty-seven well-focused fundal images taken with RetCam were classified to three groups of plus,non-plus, and pre-plus by agreement between three ROP experts. Automated algorithms in this study weredesigned based on two methods: the curvature measure and distance transform for assessment of tortuosityand vascular dilatation, respectively as two major parameters of plus disease detection. Results: Thirty-eight plus, 12 pre-plus, and 37 non-plus images, which were classified by three experts, weretested by an automated algorithm and software evaluated the correct grouping of images in comparison toexpert voting with three different classifiers, k-nearest neighbor, support vector machine and multilayer perceptronnetwork. The plus, pre-plus, and non-plus images were analyzed with 72.3%, 83.7%, and 84.4%accuracy, respectively. Conclusions: The new automated algorithm used in this pilot scheme for diagnosis and screening of patientswith plus ROP has acceptable accuracy. With more improvements, it may become particularly useful, especiallyin centers without a skilled person in the ROP field.
참고문헌 (34)
- Blencowe H, "National, regional, and worldwide estimates of preterm birth rates in the year 2010 with time trends since 1990 for selected countries: a systematic analysis and implications", Lancet, 379, pp.2162~2172 (2012)
- Gilbert C, "Childhood blindness in the context of VISION 2020: the right to sight", Bull World Health Organ, 79, pp.227~232 (2001)
- Gilbert C, "Characteristics of infants with severe retinopathy of prematurity in countries with low, moderate, and high levels of development: implications for screening programs", Pediatrics, 115, pp.e518~e525 (2005)
- Early Treatment for Retinopathy of Prematurity Cooperative Group, "Revised indications for the treatment of retinopathy of prematurity: results of the early treatment for retinopathy of prematurity randomized trial", Arch Ophthalmol, 121, pp.1684~1694 (2003)
- Davitt BV, "Plus disease", Surv Ophthalmol, 54, pp.663~670 (2009)
- Freedman SF, "Observer sensitivity to retinal vessel diameter and tortuosity in retinopathy of prematurity: a model system", J Pediatr Ophthalmol Strabismus, 33, pp.248~254 (1996)
- Chiang MF, "Interexpert agreement of plus disease diagnosis in retinopathy of prematurity", Arch Ophthalmol, 125, pp.875~880 (2007)
- Wallace DK, "Agreement among pediatric ophthalmologists in diagnosing plus and pre-plus disease in retinopathy of prematurity", J AAPOS, 12, pp.352~356 (2008)
- Wilson CM, "Digital image analysis in retinopathy of prematurity: a comparison of vessel selection methods", J AAPOS, 16, pp.223~228 (2012)
- Pourreza R, "MICAI 2008: advances in artificial intelligence", pp.948~956 (2008), Springer Berlin Heidelberg
- Guo Z, "Parallel thinning with two-subiteration algorithms", Commun ACM, 32, pp.359~373 (1989)
- Frette OI, "Estimation of the curvature of an interface from a digital 2D image", Comput Mater Sci, 44, pp.867~875 (2009)
- Maurer CR, "A linear time algorithm for computing exact Euclidean distance transforms of binary images in arbitrary dimensions", IEEE Trans Pattern Anal Mach Intell, 25, pp.265~270 (2003)
- Shah DN, "Comparison of expert graders to computer-assisted image analysis of the retina in retinopathy of prematurity", Br J Ophthalmol, 95, pp.1442~1445 (2011)
- Chiang MF, "Image analysis for retinopathy of prematurity diagnosis", J AAPOS, 13, pp.438~445 (2009)
- Chiang MF, "Plus disease in retinopathy of prematurity: an analysis of diagnostic performance", Trans Am Ophthalmol Soc, 105, pp.73~84 (2007)
- Martinez-Perez ME, "Retinal vascular tree morphology: a semi-automatic quantification", IEEE Trans Biomed Eng, 49, pp.912~917 (2002)
- Swanson C, "Semiautomated computer analysis of vessel growth in preterm infants without and with ROP", Br J Ophthalmol, 87, pp.1474~1477 (2003)
- Gelman R, "Diagnosis of plus disease in retinopathy of prematurity using retinal image multiscale analysis", Invest Ophthalmol Vis Sci, 46, pp.4734~4738 (2005)
- Thyparampil PJ, "Plus disease in retinopathy of prematurity: quantitative analysis of vascular change", Am J Ophthalmol, 150, pp.468.e2~475.e2 (2010)
- Wallace DK, "Computer-assisted quantification of vascular tortuosity in retinopathy of prematurity (an American Ophthalmological Society thesis)", Trans Am Ophthalmol Soc, 105, pp.594~615 (2007)
- Cabrera MT, "Combining ROPtool measurements of vascular tortuosity and width to quantify plus disease in retinopathy of prematurity", J AAPOS, 15, pp.40~44 (2011)
- Bullitt E, "Measuring tortuosity of the intracerebral vasculature from MRA images", IEEE Trans Med Imaging, 22, pp.1163~1171 (2003)
- Aylward S, "Intensity ridge and widths for tubular object segmentation and description", Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (1996), IEEE Computer Society Press
- Kiely AE, "Computer-assisted measurement of retinal vascular width and tortuosity in retinopathy of prematurity", Arch Ophthalmol, 128, pp.847~852 (2010)
- Wilson CM, "Computerized analysis of retinal vessel width and tortuosity in premature infants", Invest Ophthalmol Vis Sci, 49, pp.3577~3585 (2008)
- Shah DN, "Semiautomated digital image analysis of posterior pole vessels in retinopathy of prematurity", J AAPOS, 13, pp.504~506 (2009)
- Ghodasra DH, "Risk stratification of preplus retinopathy of prematurity by semiautomated analysis of digital images", Arch Ophthalmol, 128, pp.719~723 (2010)
- Wittenberg LA, "Computer-based image analysis for plus disease diagnosis in retinopathy of prematurity", J Pediatr Ophthalmol Strabismus, 49, pp.11~19 (2012)
- Wallace DK, "A pilot study using “ROPtool” to quantify plus disease in retinopathy of prematurity", J AAPOS, 11, pp.381~387 (2007)
- Grisan E, "A novel method for the automatic grading of retinal vessel tortuosity", IEEE Trans Med Imaging, 27, pp.310~319 (2008)
- Wilson CM, "The challenge of screening for retinopathy of prematurity", Clin Perinatol, 40, pp.241~259 (2013)
- Keck KM, "Plus disease diagnosis in retinopathy of prematurity: vascular tortuosity as a function of distance from optic disk", Retina, 33, pp.1700~1707 (2013)
- Cheung CS, "Computer-assisted image analysis of temporal retinal vessel width and tortuosity in retinopathy of prematurity for the assessment of disease severity and treatment outcome", J AAPOS, 15, pp.374~380 (2011)