Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Methodological review: Computerized analysis of pigmented skin lesions: A review

This chapter proposes a novel hierarchical classification system based on the K-Nearest Neighbors (K-NN) model and its application to non-melanoma skin lesion classification. Color and texture features are extracted from skin lesion images. The hierarchical structure decomposes the classification task into a set of simpler problems, one at each node of the classification. Feature selection is embedded in the hierarchical framework that chooses the most relevant feature subsets at each node of the hierarchy. The accuracy of the proposed hierarchical scheme is higher than 93 % in discriminating cancer and potential at risk lesions from benign lesions, and it reaches an overall classification accuracy of 74 % over five common classes of skin lesions, including two non-melanoma cancer types. This is the most extensive known result on non-melanoma skin cancer classification using color and texture information from images acquired by a standard camera (non-dermoscopy).

/pdf/a-color-and-texture-based-hierarchical-k-nn-approach-to-the-29ssotxwiq.pdf

A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions

Melanoma, most threatening type of skin cancer, is on the rise. In this paper an implementation of a deep-learning system on a computer server, equipped with graphic processing unit (GPU), is proposed for detection of melanoma lesions. Clinical (non-dermoscopic) images are used in the proposed system, which could assist a dermatologist in early diagnosis of this type of skin cancer. In the proposed system, input clinical images, which could contain illumination and noise effects, are preprocessed in order to reduce such artifacts. Afterward, the enhanced images are fed to a pre-trained convolutional neural network (CNN) which is a member of deep learning models. The CNN classifier, which is trained by large number of training samples, distinguishes between melanoma and benign cases. Experimental results show that the proposed method is superior in terms of diagnostic accuracy in comparison with the state-of-the-art methods.

Melanoma detection by analysis of clinical images using convolutional neural network

We develop a novel method for classifying melanocytic tumors as benign or malignant by the analysis of digital dermoscopy images. The algorithm follows three steps: first, lesions are extracted using a self-generating neural network (SGNN); second, features descriptive of tumor color, texture and border are extracted; and third, lesion objects are classified using a classifier based on a neural network ensemble model. In clinical situations, lesions occur that are too large to be entirely contained within the dermoscopy image. To deal with this difficult presentation, new border features are proposed, which are able to effectively characterize border irregularities on both complete lesions and incomplete lesions. In our model, a network ensemble classifier is designed that combines back propagation (BP) neural networks with fuzzy neural networks to achieve improved performance. Experiments are carried out on two diverse dermoscopy databases that include images of both the xanthous and caucasian races. The results show that classification accuracy is greatly enhanced by the use of the new border features and the proposed classifier model.

Melanoma Classification on Dermoscopy Images Using a Neural Network Ensemble Model

Automated prescreening of pigmented skin lesions using standard cameras.

This paper presents a new automatic method to significantly attenuate the color degradation due to shading in color images of the human skin. Shading is caused by illumination variation across the scene due to changes in local surface orientation, lighting conditions, and other factors. Our approach is to estimate the illumination variation by modeling it with a quadric function, and then relight the skin pixels with a simple operation. Therefore, the subsequent color skin image processing and analysis is simplified in several applications. We illustrate our approach in two typical color imaging problems involving human skin, namely: (a) pigmented skin lesion segmentation, and (b) face detection. Our preliminary experimental results show that our shading attenuation approach helps reducing the complexity of the color image analysis problem in these applications.

Shading attenuation in human skin color images

In this paper, we propose a new particle-filtering approach for handling partial and total occlusions in vehicular tracking situations. Our proposed method, which is named adaptive particle filter (APF), uses two different operation modes. When the tracked vehicle is not occluded, the APF uses a normal probability density function (pdf) to generate the new set of particles. Otherwise, when the tracked vehicle is under occlusion, the APF generates the new set of particles using a Normal-Rayleigh pdf. Our approach was designed to detect when a total occlusion starts and ends and to resume vehicle tracking after disocclusions. We have tested our APF approach in a number of traffic surveillance video sequences with encouraging results. Our proposed approach tends to be more accurate than comparable methods in the literature, and at the same time, it tends to be more robust to target occlusions.

A Particle-Filtering Approach for Vehicular Tracking Adaptive to Occlusions

Several pigmented skin lesion segmentation methods have been proposed for dermoscopy images, however skin lesion segmentation on macroscopic images have not received much attention. Despite the fact that dermoscopy is a very specialized technique, in some practical situations, patients do not have a fast access to an specialist. In this situations, pre-screening systems can be used to evaluate a suspect skin lesion by a non-specialist, and lesion segmentation is very important for the success of such systems. This paper proposes a new method for segmenting pigmented skin lesions on macroscopic images acquired with standard cameras. Our method is simpler than comparable methods proposed for dermoscopy, and our experiments based on publicly available datasets of pigmented skin lesion images show promising results. Our approach can achieve an average segmentation error of 24.85%, which is better than the accuracy of comparable methods available in the literature (even for illumination corrected images).

Pigmented skin lesion segmentation on macroscopic images

In this paper, we propose a novel approach to discriminate malignant melanomas and benign atypical nevi, since both types of melanocytic skin lesions have very similar characteristics. Recent studies involving the non-invasive diagnosis of melanoma indicate that the concentrations of the two main classes of melanin present in the human skin, eumelanin and pheomelanin, can potentially be used in the computation of relevant features to differentiate these lesions. So, we describe how these features can be estimated using only standard camera images. Moreover, we demonstrate that using these features in conjunction with features based on the well known ABCD rule, it is possible to achieve 100% of sensitivity and more than 99% accuracy in melanocytic skin lesion discrimination, which is a highly desirable characteristic in a prescreening system.

http://www.npsg.uwaterloo.ca/resources/docs/exp_sys_mel.pdf

Pablo G. Cavalcanti

Papers

Automated prescreening of pigmented skin lesions using standard cameras.

Shading attenuation in human skin color images

A Particle-Filtering Approach for Vehicular Tracking Adaptive to Occlusions

Pigmented skin lesion segmentation on macroscopic images

A two-stage approach for discriminating melanocytic skin lesions using standard cameras