Pterygium-Net: a deep learning approach to pterygium detection and localization

Automatic pterygium detection is an essential screening tool for health community service groups. It allows non-expert to perform screening process without the needs of big and expensive equipment, especially for the application in rural areas. Thence, patients who have been screened as positive pterygium will be referred to the certified medical personnel for further diagnosis and treatment. Current state-of-the-art algorithms for pterygium detection rely on basic machine learning approach such as artificial neural network and support vector machine, which have not yet achieved high detection sensitivity and specificity as required in standard medical practice. Hence, a deep learning approach based on fully convolutional neural networks is proposed to detect and localize the pterygium infected tissues automatically. The input image requirement for the developed system is low as any commercial mobile phone camera is sufficient. Moreover, the developed algorithm, which we refer as Pterygium-Net works well even if the eye image is captured under low lighting condition with pupil position is not at the center location. Pterygium-Net utilizes three layers of convolutional neural networks (CNN) and three layers of fully connected networks. Two steps are implemented to overcome lacks of training data by generating synthetic images and pre-training the CNN weights and biases in a different public dataset. As for pterygium localization, an additional step of box proposal based on edges information is used to generate possible regions of the pterygium infected tissues. Hanning window is also applied to the generated regions to give more weightage to the center area. Experimental results show that Pterygium-Net produces high average detection sensitivity and specificity of 0.95 and 0.983, respectively. As for pterygium tissues localization, the algorithm achieves 0.811 accuracy with a very low failure rate of 0.053. In the future, deeper networks can be implemented to further improve pterygium localization.

[1]  Jingyang Wu,et al.  Geographical prevalence and risk factors for pterygium: a systematic review and meta-analysis , 2013, BMJ Open.

[2]  Haiyan Lu,et al.  Classification of diabetic retinopathy using textural features in retinal color fundus image , 2017, 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE).

[3]  H. Brodaty,et al.  The Sydney Multisite Intervention of LaughterBosses and ElderClowns (SMILE) study: cluster randomised trial of humour therapy in nursing homes , 2013, BMJ Open.

[4]  Gernot A. Fink,et al.  Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[5]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[6]  Somsak Choomchuay,et al.  Detection of lesions and classification of diabetic retinopathy using fundus images , 2016, 2016 9th Biomedical Engineering International Conference (BMEiCON).

[7]  Andrew Zisserman,et al.  SpineNet: Automated classification and evidence visualization in spinal MRIs , 2017, Medical Image Anal..

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[11]  Nilamani Bhoi,et al.  A thresholding based technique to extract retinal blood vessels from fundus images , 2017 .

[12]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.

[13]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[14]  Mohd Asyraf Zulkifley,et al.  Squat Angle Assessment Through Tracking Body Movements , 2019, IEEE Access.

[15]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[16]  K. Archana,et al.  Diabetic Retinopathy Detection in Fundus Image Using Cross Sectional Profiles and ANN , 2018 .

[17]  Brent Lance,et al.  EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces , 2016, Journal of neural engineering.

[18]  Aini Hussain,et al.  Automated pterygium detection method of anterior segment photographed images , 2018, Comput. Methods Programs Biomed..

[19]  Xinghao Ding,et al.  Vehicle Type Recognition in Surveillance Images From Labeled Web-Nature Data Using Deep Transfer Learning , 2018, IEEE Transactions on Intelligent Transportation Systems.

[20]  Shuicheng Yan,et al.  Automatic Feature Learning for Glaucoma Detection Based on Deep Learning , 2015, MICCAI.

[21]  Mohd Asyraf Zulkifley,et al.  Two Streams Multiple-Model Object Tracker for Thermal Infrared Video , 2019, IEEE Access.

[22]  Mohammed Ghazal,et al.  Early diabetic retinopathy diagnosis based on local retinal blood vessel analysis in optical coherence tomography angiography (OCTA) images , 2018, Medical physics.

[23]  Mohammad Nauman,et al.  Self-Driving Cars Using CNN and Q-Learning , 2018, 2018 IEEE 21st International Multi-Topic Conference (INMIC).

[24]  Mostafa Mehdipour-Ghazi,et al.  Plant identification using deep neural networks via optimization of transfer learning parameters , 2017, Neurocomputing.

[25]  Bohyung Han,et al.  Modeling and Propagating CNNs in a Tree Structure for Visual Tracking , 2016, ArXiv.

[26]  Tien Yin Wong,et al.  Automatic pterygium detection on cornea images to enhance computer-aided cortical cataract grading system , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[27]  Kenji Suzuki,et al.  A deep CNN based transfer learning method for false positive reduction , 2018, Multimedia Tools and Applications.

[28]  Jun Ma,et al.  NeuroStylist: Neural Compatibility Modeling for Clothing Matching , 2017, ACM Multimedia.

[29]  Arthur Flexer,et al.  Basic Filters for Convolutional Neural Networks: Training or Design? , 2017, ArXiv.

[30]  Aini Hussain,et al.  Local binary patterns and modified red channel for optic disc segmentation , 2015 .

[31]  Hariharan Ravishankar,et al.  Understanding the Mechanisms of Deep Transfer Learning for Medical Images , 2016, LABELS/DLMIA@MICCAI.

[32]  Sean R. Anderson,et al.  Compact Deep Neural Networks for Computationally Efficient Gesture Classification From Electromyography Signals , 2018, 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob).

[33]  Darvin Yi,et al.  Automated Detection of Diabetic Retinopathy using Deep Learning , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[34]  Hongfei Lin,et al.  Deep Transfer Learning for Modality Classification of Medical Images , 2017, Inf..

[35]  D. Mackey,et al.  Pterygia are indicators of an increased risk of developing cutaneous melanomas , 2017, British Journal of Ophthalmology.

[36]  Wei Liu,et al.  Neural Compatibility Modeling with Attentive Knowledge Distillation , 2018, SIGIR.

[37]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[38]  Niki Trigoni,et al.  Multiple-Model Fully Convolutional Neural Networks for Single Object Tracking on Thermal Infrared Video , 2018, IEEE Access.

[39]  M. Usman Akram,et al.  Automated detection of glaucoma using structural and non structural features , 2016, SpringerPlus.

[40]  K. Miyata,et al.  Detection of increase in corneal irregularity due to pterygium using Fourier series harmonic analyses with multiple diameters , 2018, Japanese Journal of Ophthalmology.

[41]  Wesley De Neve,et al.  Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).