Comparison different vessel segmentation methods in automated microaneurysms detection in retinal images using convolutional neural networks

Abstract

Image processing techniques provide important assistance to physicians and relieve their workload in different tasks. In particular, identifying objects of interest such as lesions and anatomical structures from the image is a challenging and iterative process that can be done by computerized approaches in a successful manner. Microaneurysms (MAs) detection is a crucial step in retinal image analysis algorithms. The goal of MAs detection is to find the progress and at last identification of diabetic retinopathy (DR) in the retinal images. The objective of this study is to apply three retinal vessel segmentation methods, Laplacian-of-Gaussian (LoG), Canny edge detector, and Matched filter to compare results of MAs detection using combination of unsupervised and supervised learning either in the normal images or in the presence of DR. The steps for the algorithm are as following: 1) Preprocessing and Enhancement, 2) vessel segmentation and masking, 3) MAs detection and Localization using combination of Matching based approach and Convolutional Neural Networks. To evaluate the accuracy of our proposed method, we compared the output of our method with the ground truth that collected by ophthalmologists. By using the LoG vessel segmentation, our algorithm found sensitivity of more than 85% in detection of MAs for 100 color images in a local retinal database and 40 images of a public dataset (DRIVE). For the Canny vessel segmentation, our automated algorithm found sensitivity of more than 80% in detection of MAs for all 140 images of two databases. And lastly, using Matched filter, our algorithm found sensitivity of more than 87% in detection of MAs in both local and DRIVE datasets. arXiv:2005.09097v1 [physics.med-ph] 18 Apr 2020

Medical image registration using unsupervised deep neural network: A scoping literature review

“…In general, from training process viewpoint, deep learning-based medical image registration methods can be classified into two main classes, supervised, and unsupervised methods [58,59]. In the supervised learning, neural network learns to do a certain work by minimizing a predefined loss function via optimization [2].…”

Hybrid Graph Convolutional Network for Semi-Supervised Retinal Image Classification

“…Besides automatic DR grading mentioned above, several DR detection/segmentation works [31]- [33] are proposed recently. Tavakoli et al [31] compared effects of two preprocessing methods, illumination equalization and top-hat transformation on retinal images to detect microaneurysms using combination of matching based approach and deep learning methods either in the normal fundus images or in the presence of DR; Tavakoli and Nazar [32] applied three retinal vessel segmentation methods including Laplacian-of-Gaussian, Canny edge detector, and Matched filter to compare results of microaneurysms detection using combination of unsupervised and supervised learning either in the normal images or in the presence of DR; Tavakoli et al [33] did microaneurysms detection step using combination of Laplacian-of-Gaussian and convolutional neural networks, and the experiments evaluate the accuracy of this work.…”

A comprehensive survey on computer-aided diagnostic systems in diabetic retinopathy screening

“…Many DL-based approaches have been introduced for detection and classification of different types of DR lesions such as MAs, and HEs [2,6,16,112,115,275,276,[297][298][299][300][301].…”

“…Next, they used CNN classification to classify between MAs and non-MAs. In their study, the authors compared effect of two preprocessing methods, Illumination Equalization, and Top-hat transformation, on retinal images to detect MAs using combination of Matching based approach and CNN methods [6].…”

“…In the same direction, in the time between 2000 to 2030 another source anticipates the spread of the DM population worldwide to increase from 2.8% to 4.4% [5]. The real catch is that just half of the diabetic people are noticed about the disease [6]. From medical aspect viewpoint, DM leads to serious late complications such as macro and micro vascular changes which cause Diabetic Retinopathy (DR), heart disease, and renal problems [7,8].…”