Classifier learning with data-sets that suffer from imbalanced class distributions is a challenging problem in data mining community. This issue occurs when the number of examples that represent one class is much lower than the ones of the other classes. Its presence in many real-world applications has brought along a growth of attention from researchers. In machine learning, the ensemble of classifiers are known to increase the accuracy of single classifiers by combining several of them, but neither of these learning techniques alone solve the class imbalance problem, to deal with this issue the ensemble learning algorithms have to be designed specifically. In this paper, our aim is to review the state of the art on ensemble techniques in the framework of imbalanced data-sets, with focus on two-class problems. We propose a taxonomy for ensemble-based methods to address the class imbalance where each proposal can be categorized depending on the inner ensemble methodology in which it is based. In addition, we develop a thorough empirical comparison by the consideration of the most significant published approaches, within the families of the taxonomy proposed, to show whether any of them makes a difference. This comparison has shown the good behavior of the simplest approaches which combine random undersampling techniques with bagging or boosting ensembles. In addition, the positive synergy between sampling techniques and bagging has stood out. Furthermore, our results show empirically that ensemble-based algorithms are worthwhile since they outperform the mere use of preprocessing techniques before learning the classifier, therefore justifying the increase of complexity by means of a significant enhancement of the results.

A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches

Automated melanoma recognition in dermoscopy images is a very challenging task due to the low contrast of skin lesions, the huge intraclass variation of melanomas, the high degree of visual similarity between melanoma and non-melanoma lesions, and the existence of many artifacts in the image. In order to meet these challenges, we propose a novel method for melanoma recognition by leveraging very deep convolutional neural networks (CNNs). Compared with existing methods employing either low-level hand-crafted features or CNNs with shallower architectures, our substantially deeper networks (more than 50 layers) can acquire richer and more discriminative features for more accurate recognition. To take full advantage of very deep networks, we propose a set of schemes to ensure effective training and learning under limited training data. First, we apply the residual learning to cope with the degradation and overfitting problems when a network goes deeper. This technique can ensure that our networks benefit from the performance gains achieved by increasing network depth. Then, we construct a fully convolutional residual network (FCRN) for accurate skin lesion segmentation, and further enhance its capability by incorporating a multi-scale contextual information integration scheme. Finally, we seamlessly integrate the proposed FCRN (for segmentation) and other very deep residual networks (for classification) to form a two-stage framework. This framework enables the classification network to extract more representative and specific features based on segmented results instead of the whole dermoscopy images, further alleviating the insufficiency of training data. The proposed framework is extensively evaluated on ISBI 2016 Skin Lesion Analysis Towards Melanoma Detection Challenge dataset. Experimental results demonstrate the significant performance gains of the proposed framework, ranking the first in classification and the second in segmentation among 25 teams and 28 teams, respectively. This study corroborates that very deep CNNs with effective training mechanisms can be employed to solve complicated medical image analysis tasks, even with limited training data.

Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks

The increasing incidence of melanoma has recently promoted the development of computer-aided diagnosis systems for the classification of dermoscopic images. Unfortunately, the performance of such systems cannot be compared since they are evaluated in different sets of images by their authors and there are no public databases available to perform a fair evaluation of multiple systems. In this paper, a dermoscopic image database, called PH2, is presented. The PH2 database includes the manual segmentation, the clinical diagnosis, and the identification of several dermoscopic structures, performed by expert dermatologists, in a set of 200 dermoscopic images. The PH2 database will be made freely available for research and benchmarking purposes.

/pdf/ph-2-a-dermoscopic-image-database-for-research-and-4b4mbp3ym8.pdf

PH 2 - A dermoscopic image database for research and benchmarking

Automatic skin lesion segmentation in dermoscopic images is a challenging task due to the low contrast between lesion and the surrounding skin, the irregular and fuzzy lesion borders, the existence of various artifacts, and various imaging acquisition conditions. In this paper, we present a fully automatic method for skin lesion segmentation by leveraging 19-layer deep convolutional neural networks that is trained end-to-end and does not rely on prior knowledge of the data. We propose a set of strategies to ensure effective and efficient learning with limited training data. Furthermore, we design a novel loss function based on Jaccard distance to eliminate the need of sample re-weighting, a typical procedure when using cross entropy as the loss function for image segmentation due to the strong imbalance between the number of foreground and background pixels. We evaluated the effectiveness, efficiency, as well as the generalization capability of the proposed framework on two publicly available databases. One is from ISBI 2016 skin lesion analysis towards melanoma detection challenge, and the other is the PH2 database. Experimental results showed that the proposed method outperformed other state-of-the-art algorithms on these two databases. Our method is general enough and only needs minimum pre- and post-processing, which allows its adoption in a variety of medical image segmentation tasks.

Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance

Melanoma is the deadliest form of skin cancer. While curable with early detection, only highly trained specialists are capable of accurately recognizing the disease. As expertise is in limited supply, automated systems capable of identifying disease could save lives, reduce unnecessary biopsies, and reduce costs. Toward this goal, we propose a system that combines recent developments in deep learning with established machine learning approaches, creating ensembles of methods that are capable of segmenting skin lesions, as well as analyzing the detected area and surrounding tissue for melanoma detection. The system is evaluated using the largest publicly available benchmark dataset of dermoscopic images, containing 900 training and 379 testing images. New state-of-the-art performance levels are demonstrated, leading to an improvement in the area under receiver operating characteristic curve of 7.5% (0.843 versus 0.783), in average precision of 4% (0.649 versus 0.624), and in specificity measured at the clinically relevant 95% sensitivity operating point 2.9 times higher than the previous state of the art (36.8% specificity compared to 12.5%). Compared to the average of eight expert dermatologists on a subset of 100 test images, the proposed system produces a higher accuracy (76% versus 70.5%), and specificity (62% versus 59%) evaluated at an equivalent sensitivity (82%).

Deep learning ensembles for melanoma recognition in dermoscopy images

A Methodological Approach to the Classification of Dermoscopy Images

In this paper, we present a fast switching filter for impulsive noise removal from color images. The filter exploits the HSL color space, and is based on the peer group concept, which allows for the fast detection of noise in a neighborhood without resorting to pairwise distance computations between each pixel. Experiments on large set of diverse images demonstrate that the proposed approach is not only extremely fast, but also gives excellent results in comparison to various state-of-the-art filters.

A Fast Switching Filter for Impulsive Noise Removal from Color Images

In this article, we present a fast switching filter for impulsive noise removal from color images. The filter exploits the hue, saturation, and lightness color space and is based on the peer group concept, which allows for the fast detection of noise in a neighborhood without resorting to pairwise distance computations between each pixel. Experiments on large set of diverse images demonstrate that the proposed approach is not only extremely fast, but also gives excellent results in comparison to various state-of-the-art filters.

Fast switching filter for impulsive noise removal from color images

Microarrays are massively parallel biosensors that can simultaneously detect and quantify a large number of different genomic particles. A DNA microarray is a nucleic acid-based microarray that contains probe spots testing a multitude of targets in one experiment. Ideas from compressive sensing have been utilized in different ways in the analysis of DNA microarrays. One of the proposed methods is compressed microarrays, where each spot contains copies of several probes and the total number of spots is lower, resulting in significantly reduced costs due to cheaper array manufacturing. In this paper, we perform compressed microarray experiments with real aCGH data and demonstrate the accuracy of various recovery methods. Our experimental results suggest that the measurements that can be captured by compressed microarrays can be recovered accurately using the proposed norm-minimization methods.

Accurate genomic signal recovery using compressed sensing

In this paper, we present a fast switching filter for impulsive noise removal from color images. The filter exploits the HSL color space, and is based on the peer group concept, which allows for the fast detection of noise in a neighborhood without resorting to pairwise distance computations between each pixel. Experiments on large set of diverse images demonstrate that the proposed approach is not only extremely fast, but also gives excellent results in comparison to various state-of-the-art filters. Keywords : color image processing, nonlinear vector filter, impulsive noise, HSL color space, switching filter, peer group, S - CIELAB 1. Introduction The growing use of color images in diverse applications such as content-based image retrieval, medical image analysis, biometrics, remote sensing, watermarking, and visual quality inspection has led to an increasing interest in color image processing. These applications need to perform many of the same tasks as their grayscale counterparts, such as edge detection, segmentation and feature extraction [1]. However, images are often contaminated with noise which is often introduced during acquisition or transmission. In particular, the introduction of bit errors and impulsive noise into an image not only lowers its perceptual

Bakhtiyar Uddin

Papers

A Methodological Approach to the Classification of Dermoscopy Images

A Fast Switching Filter for Impulsive Noise Removal from Color Images

Fast switching filter for impulsive noise removal from color images

Accurate genomic signal recovery using compressed sensing

Noise removal from color images