Bálint Antal

An Ensemble-Based System for Microaneurysm Detection and Diabetic Retinopathy Grading

Reliable microaneurysm detection in digital fundus images is still an open issue in medical image processing. We propose an ensemble-based framework to improve microaneurysm detection. Unlike the well-known approach of considering the output of multiple classifiers, we propose a combination of internal components of microaneurysm detectors, namely preprocessing methods and candidate extractors. We have evaluated our approach for microaneurysm detection in an online competition, where this algorithm is currently ranked as first, and also on two other databases. Since microaneurysm detection is decisive in diabetic retinopathy (DR) grading, we also tested the proposed method for this task on the publicly available Messidor database, where a promising AUC 0.90 ± 0.01 is achieved in a “DR/non-DR”-type classification based on the presence or absence of the microaneurysms.

An ensemble-based system for automatic screening of diabetic retinopathy

In this paper, an ensemble-based method for the screening of diabetic retinopathy (DR) is proposed. This approach is based on features extracted from the output of several retinal image processing algorithms, such as image-level (quality assessment, pre-screening, AM/FM), lesion-specific (microaneurysms, exudates) and anatomical (macula, optic disk) components. The actual decision about the presence of the disease is then made by an ensemble of machine learning classifiers. We have tested our approach on the publicly available Messidor database, where 90% sensitivity, 91% specificity and 90% accuracy and 0.989 AUC are achieved in a disease/no-disease setting. These results are highly competitive in this field and suggest that retinal image processing is a valid approach for automatic DR screening.

Improving microaneurysm detection using an optimally selected subset of candidate extractors and preprocessing methods

In this paper, we present an approach to improve microaneurysm detection in digital color fundus images. Instead of following the standard process which considers preprocessing, candidate extraction and classification, we propose a novel approach that combines several preprocessing methods and candidate extractors before the classification step. We ensure high flexibility by using a modular model and a simulated annealing-based search algorithm to find the optimal combination. Our experimental results show that the proposed method outperforms the current state-of-the-art individual microaneurysm candidate extractors.

Improving microaneurysm detection in color fundus images by using context-aware approaches

In this paper, we present two approaches to improve microaneurysm detector ensembles. First, we provide an approach to select a set of preprocessing methods for a microaneurysm candidate extractor to enhance its detection performance in color fundus images. The performance of the candidate extractor with each preprocessing method is measured in six microaneurysm categories. The best performing preprocessing method for each category is selected and organized into an ensemble-based method. We tested our approach on the publicly available DiaretDB1 database, where the proposed approach led to an improvement regarding the individual approaches. Second, an adaptive weighting approach for microaneurysm detector ensembles is presented.The basis of the adaptive weighting approach is the spatial location and contrast of the detected microaneurysm. During training, the performance of ensemble members is measured with respect to these contextual information, which serves as a basis for the optimal weights assigned to the detectors. We have tested this approach on two publicly available datasets, where it showed its competitiveness compared without previously published ensemble-based approach for microaneurysm detection. Moreover, the proposed approach outperformed all the investigated individual detectors.

Automatic exudate detection with improved Naïve-bayes classifier

Nowadays diabetic retinopathy is one of the most common reasons of blindness in the world. Exudates are the primary sign of this disease so the proper detection of these lesions is an essential task in an automatic screening system. In this paper, we propose a method for exudate detection which performs with high accuracy. First, we identify possible regions containing exudates using grayscale morphology. Then, we extract more than 50 descriptors for each candidate pixel to classify them. We analyzed the information content of the descriptors and selected the most relevant ones. The selected features are used to train a boosted naïve Bayes classifier. We tested this approach on the publicly available DiaretDB color fundus image database, where the proposed detector outperformed the state-of-the-art ones regarding the FScore.

A multi-level ensemble-based system for detecting microaneurysms in fundus images

In this paper, we present a complex approach to improve microaneurysm detection in color fundus images. Microaneurysms are early signs of diabetic retinopathy, so it is essential to detect these lesions accurately in an automatic screening system. The recommended detection of microaneurysms is realized through several levels. First, a specific combination of different preprocessing methods for candidate extractors is found. Then, we select candidates voted by a certain number of the candidate extractor algorithms. At all these levels, optimal adjustments are determined by corresponding simulated annealing algorithms. Finally, we classify the candidates with a machine-learning based approach considering an optimal feature vector selection determined by a feature subset selection algorithm. Our framework improves the positive likelihood ratio for the microaneurysms and outperforms both the state-of-the-art individual candidate extractors and microaneurysm detectors in these measures.

A stochastic approach to improve macula detection in retinal images

In this paper, we present an approach to improve detectors used in medical image processing by fine-tuning their parameters for a certain dataset. The proposed algorithm uses a stochastic search algorithm to deal with large search spaces. We investigate the effectiveness of this approach by evaluating it on an actual clinical application. Namely, we present promising results with outperforming four state-of-the-art algorithms used for the detection of the center of the sharp vision (macula) in digital fundus images.

An adaptive weighting approach for ensemble-based detection of microaneurysms in color fundus images

In this paper, we present an adaptive weighting approach to microaneurysm detector ensembles. The basis of the adaptive weighting approach is the spatial location and contrast of the detected microaneurysm. During training, the performance of ensemble members is measured with a respect to these contextual information, which serves as a basis for the optimal weights assigned to detectors. We have tested this approach on two publicly available datasets, where it showed its competitiveness compared with out previously published ensemble-based approach for microaneurysm detection. Moreover, the proposed approach outperformed all the investigated individual detectors.

An ensemble-based microaneurysm detector for retinal images

The key to the early detection of diabetic retinopathy is to recognize microaneurysms in the fundus of the eye in time. Reliable detection of such lesions is still an open issue in medical image processing. We propose a framework which assembles several candidate extractors and preprocessing methods to strengthen the detection accuracy of the individual approaches. We use a simulated annealing based search approach to select an optimal combination from the available methods. The proposed method has proved its superiority over the individual algorithms in an online competition dedicated to the objective comparison of microaneurysm detectors.

Evaluation of the grading performance of an ensemble-based microaneurysm detector

In this paper, results of a diabetic retinopathy screening experiment are presented which is based solely on the findings of a microaneurysm detector. For this purpose, an ensemble-based algorithm developed by our research group was used; this provided promising results in our earlier experiments. At its best, the 1200 image of the Messidor database is classified by this detector with a sensitivity of 96%, a specificity of 51% and achieved an AUC of 0.87. As anticipated, larger microaneurysm counts are recognized with higher level of certainty. Therefore, this approach might be expected to have good performance in relation to the severity of the disease.