Simultaneous Segmentation of Multiple Retinal Pathologies Using Fully Convolutional Deep Neural Network

The segmentation of retinal pathologies is the primitive and essential step in the development of automated diagnostic system for various systemic, cardiovascular, and ophthalmic diseases. The existing state-of-the-art machine learning based retinal pathologic segmentation techniques mainly aim at delineating pathology of one kind only. In this context, we have proposed a novel end-to-end technique for simultaneous segmentation of multiple retinal pathologies (i.e., exudates, hemorrhages, and cotton-wool spots) using encoder-decoder based fully convolutional neural network architecture. Moreover, the task of retinal pathology extraction has been modeled as a semantic segmentation framework which enables us to obtain pixel-level class labels. The proposed algorithm has been evaluated on publically available Messidor dataset and achieved state-of-the-art mean accuracies of 99.24% (exudates), 97.86% (hemorrhages), and 88.65% (cotton-wool spots). The developed approach may aid in further optimization of pathology quantification module of the QUARTZ software which has been developed earlier by our research group.

[1]  Fabio A. González,et al.  Training Deep Convolutional Neural Networks with Active Learning for Exudate Classification in Eye Fundus Images , 2017, CVII-STENT/LABELS@MICCAI.

[2]  Alauddin Bhuiyan,et al.  Progress on retinal image analysis for age related macular degeneration , 2014, Progress in Retinal and Eye Research.

[3]  Ukrit Watchareeruetai,et al.  Detection of cotton wool for diabetic retinopathy analysis using neural network , 2017, 2017 IEEE 10th International Workshop on Computational Intelligence and Applications (IWCIA).

[4]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[6]  U. Rajendra Acharya,et al.  Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network , 2017, Inf. Sci..

[7]  Bunyarit Uyyanonvara,et al.  Ensemble Classification System Applied for Retinal Vessel Segmentation on Child Images Containing Various Vessel Profiles , 2012, ICIAR.

[8]  Prabir Kumar Biswas,et al.  Deep neural ensemble for retinal vessel segmentation in fundus images towards achieving label-free angiography , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[9]  Guy Cazuguel,et al.  FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE , 2014 .

[10]  Linda Drake.  Prevention of Blindness from Diabetes Mellitus - Report of a WHO ConsultationPrevention of Blindness from Diabetes Mellitus - Report of a WHO Consultation , 2007 .

[11]  Muhammad Moazam Fraz,et al.  Computer vision algorithms applied to retinal vessel segmentation and quantification of vessel caliber , 2014 .

[12]  Ibrahim Sadek,et al.  Automatic discrimination of color retinal images using the bag of words approach , 2015, Medical Imaging.

[13]  Siti Zaiton Mohd Hashim,et al.  Diabetic retinopathy lesion detection using region-based approach , 2014, 2014 8th. Malaysian Software Engineering Conference (MySEC).

[14]  Emanuele Trucco,et al.  FABC: Retinal Vessel Segmentation Using AdaBoost , 2010, IEEE Transactions on Information Technology in Biomedicine.

[15]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[16]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[17]  Desire Sidibé,et al.  Discrimination of retinal images containing bright lesions using sparse coded features and SVM , 2015, Comput. Biol. Medicine.

[18]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[19]  Bunyarit Uyyanonvara,et al.  Blood vessel segmentation methodologies in retinal images - A survey , 2012, Comput. Methods Programs Biomed..

[20]  Sven Loncaric,et al.  Detection of exudates in fundus photographs using deep neural networks and anatomical landmark detection fusion , 2016, Comput. Methods Programs Biomed..

[21]  C. Sinthanayothin,et al.  Automated detection of diabetic retinopathy on digital fundus images , 2002, Diabetic medicine : a journal of the British Diabetic Association.

[22]  QiaoLiang Li,et al.  Retinal vessel landmark detection using deep learning and hessian matrix , 2015, 2015 8th International Congress on Image and Signal Processing (CISP).

[23]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[24]  Bunyarit Uyyanonvara,et al.  Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods , 2008, Comput. Medical Imaging Graph..

[25]  J. Kanski.  Clinical Ophthalmology: A Systematic Approach , 1989 .

[26]  Muhammad Moazam Fraz,et al.  Multiscale segmentation of exudates in retinal images using contextual cues and ensemble classification , 2017, Biomed. Signal Process. Control..

[27]  Samaneh Abbasi-Sureshjani,et al.  Boosted Exudate Segmentation in Retinal Images Using Residual Nets , 2017, FIFI/OMIA@MICCAI.

[28]  M. Sonka,et al.  Retinal Imaging and Image Analysis , 2010, IEEE Reviews in Biomedical Engineering.

[29]  Pascale Massin,et al.  A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina , 2002, IEEE Transactions on Medical Imaging.

[30]  Muhammad Moazam Fraz,et al.  QUARTZ: Quantitative Analysis of Retinal Vessel Topology and size - An automated system for quantification of retinal vessels morphology , 2015, Expert Syst. Appl..