Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss

Deep learning techniques are recently being used in fundus image analysis and diabetic retinopathy detection. Microaneurysms are an important indicator of diabetic retinopathy progression. We introduce a two-stage deep learning approach for microaneurysms segmentation using multiple scales of the input with selective sampling and embedding triplet loss. The model first segments on two scales and then the segmentations are refined with a classification model. To enhance the discriminative power of the classification model, we incorporate triplet embedding loss with a selective sampling routine. The model is evaluated quantitatively to assess the segmentation performance and qualitatively to analyze the model predictions. This approach introduces a 30.29% relative improvement over the fully convolutional neural network.

[1]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[2]  Vincent Lepetit,et al.  Learning descriptors for object recognition and 3D pose estimation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Rishab Gargeya,et al.  Automated Identification of Diabetic Retinopathy Using Deep Learning. , 2017, Ophthalmology.

[4]  Matthew B. Blaschko,et al.  Learning to Detect Red Lesions in Fundus Photographs: An Ensemble Approach based on Deep Learning , 2017, ArXiv.

[5]  T. Wong,et al.  Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss , 2015, Eye and Vision.

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

[7]  Daniel Rubin,et al.  Retinal Lesion Detection With Deep Learning Using Image Patches , 2018, Investigative ophthalmology & visual science.

[8]  Mrinal Haloi,et al.  Improved Microaneurysm Detection using Deep Neural Networks , 2015, ArXiv.

[9]  Bram van Ginneken,et al.  Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images , 2016, IEEE Transactions on Medical Imaging.

[10]  Charless C. Fowlkes,et al.  Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation , 2016, ECCV.

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

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

[13]  Matthew B. Blaschko,et al.  An ensemble deep learning based approach for red lesion detection in fundus images , 2017, Comput. Methods Programs Biomed..

[14]  Keith A Goatman,et al.  Automated measurement of microaneurysm turnover. , 2003, Investigative ophthalmology & visual science.

[15]  Bastian Leibe,et al.  Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[17]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).