Deep Retinal Diseases Detection and Explainability Using OCT Images

Retinal disease classification is an important challenge in computer aided diagnosis (CAD) for medical applications. Eye diseases can cause different symptoms from mild vision problems to complete blindness if it is not timely treated. The early diagnosis is crucial to prevent blindness. In this work, we use deep Convolutional Neural Networks (CNN) on a 4-class classification problem to automatically detect choroidal neovascularization (CNV), diabetic macular edema (DME), drusen, and normal cases using Optical Coherence Tomography (OCT) images. The obtained results achieve state-of-the-art performance and show that the proposed network leads to higher classification rates with an accuracy of 98.46%, and an Area Under Curve (AUC) of 0.998. An explainability algorithm was also developed and shows the efficiency of the proposed approach in detecting retinal disease signs.

[1]  Fabrice Mériaudeau,et al.  Transfer learning for Diabetic Macular Edema (DME) detection on Optical Coherence Tomography (OCT) images , 2017, 2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[2]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Fabio A. González,et al.  OCT-NET: A convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[4]  Zhizheng Wu,et al.  Deep learning-based automated detection of retinal diseases using optical coherence tomography images. , 2019, Biomedical optics express.

[5]  Quoc V. Le,et al.  GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism , 2018, ArXiv.

[6]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[7]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

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

[9]  Yue Yu,et al.  Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images , 2018, Translational vision science & technology.

[10]  Fabrice Mériaudeau,et al.  Fusing Results of Several Deep Learning Architectures for Automatic Classification of Normal and Diabetic Macular Edema in Optical Coherence Tomography , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[11]  Michael H. Goldbaum,et al.  Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification , 2018 .

[12]  Feng Li,et al.  Fully automated detection of retinal disorders by image-based deep learning , 2019, Graefe's Archive for Clinical and Experimental Ophthalmology.

[13]  Martin Fleury,et al.  Data Driven Approach for Eye Disease Classification with Machine Learning , 2019, Applied Sciences.

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

[15]  Muhammad Awais,et al.  Classification of SD-OCT images using a Deep learning approach , 2017, 2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[16]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[17]  Moustapha Kardouchi,et al.  Diabetic Retinopathy Detection Using Machine Learning and Texture Features , 2018, 2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE).

[18]  Bo Chen,et al.  MnasNet: Platform-Aware Neural Architecture Search for Mobile , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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