Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation

Retinopathy of Prematurity (ROP) is a disease affecting premature infants and may lead to childhood blindness. Due to lack of trained ophthalmologists, developing a fully automated ROP diagnostic system can significantly benefit the infants affected by ROP. Based on manually segmented features, previous work produces severity scores for ROP with excellent prediction accuracy. However, when automated segmentation employed, a significant accuracy drop is observed. In this paper, we show that U-Net segmentation, which is automated, comes at no accuracy loss.

[1]  A. Filouš,et al.  [Retinopathy of prematurity]. , 1998, Ceska a slovenska oftalmologie : casopis Ceske oftalmologicke spolecnosti a Slovenske oftalmologicke spolecnosti.

[2]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Anna L. Ells,et al.  The International Classification of Retinopathy of Prematurity revisited. , 2005, Archives of ophthalmology.

[5]  J. Javitt,et al.  Cost-effectiveness of screening and cryotherapy for threshold retinopathy of prematurity. , 1993, Pediatrics.

[6]  Stratis Ioannidis,et al.  A Severity Score for Retinopathy of Prematurity , 2019, KDD.

[7]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS THE METHOD OF PAIRED COMPARISONS , 1952 .

[8]  Deniz Erdoğmuş,et al.  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. , 2015, Translational vision science & technology.

[9]  James M. Brown,et al.  Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks , 2018, JAMA ophthalmology.

[10]  A. Fielder,et al.  Preterm-associated visual impairment and estimates of retinopathy of prematurity at regional and global levels for 2010 , 2013, Pediatric Research.

[11]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[12]  Stratis Ioannidis,et al.  Plus Disease in Retinopathy of Prematurity: Convolutional Neural Network Performance Using a Combined Neural Network and Feature Extraction Approach , 2020, Translational vision science & technology.

[13]  Deniz Erdogmus,et al.  Plus Disease in Retinopathy of Prematurity: Improving Diagnosis by Ranking Disease Severity and Using Quantitative Image Analysis. , 2016, Ophthalmology.

[14]  M. Hartnett,et al.  Mechanisms and management of retinopathy of prematurity. , 2012, The New England journal of medicine.

[15]  Stratis Ioannidis,et al.  Classification and comparison via neural networks , 2019, Neural Networks.

[16]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[17]  John A. Jones,et al.  Multicenter trial of cryotherapy for retinopathy of prematurity: preliminary results. Cryotherapy for Retinopathy of Prematurity Cooperative Group. , 1988, Pediatrics.

[18]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.