Classification of melanoma lesions using sparse coded features and random forests

Abstract

Malignant melanoma is the most dangerous type of skin cancer, yet it is the most treatable kind of cancer, conditioned by its early diagnosis which is a challenging task for clinicians and dermatologists. In this regard, CAD systems based on machine learning and image processing techniques are developed to differentiate melanoma lesions from benign and dysplastic nevi using dermoscopic images. Generally, these frameworks are composed of sequential processes: pre-processing, segmentation, and classification. This architecture faces mainly two challenges: (i) each process is complex with the need to tune a set of parameters, and is specific to a given dataset; (ii) the performance of each process depends on the previous one, and the errors are accumulated throughout the framework. In this paper, we propose a framework for melanoma classification based on sparse coding which does not rely on any pre-processing or lesion segmentation. Our framework uses Random Forests classifier and sparse representation of three features: SIFT, Hue and Opponent angle histograms, and RGB intensities. The experiments are carried out on the public PH 2 dataset using a 10-fold cross-validation. The results show that SIFT sparse-coded feature achieves the highest performance with sensitivity and specificity of 100% and 90.3% respectively, with a dictionary size of 800 atoms and a sparsity level of 2. Furthermore, the descriptor based on RGB intensities achieves similar results with sensitivity and specificity of 100% and 71.3%, respectively for a smaller dictionary size of 100 atoms. In conclusion, dictionary learning techniques encode strong structures of dermoscopic images and provide discriminant descriptors.

Melanoma Is Skin Deep: A 3D Reconstruction Technique for Computerized Dermoscopic Skin Lesion Classification

“…All images in the PH2 dataset are 8-bit RGB color images. The PH2 dataset is also used to evaluate the performance in [19] , [22] , and [57] – [59] .…”

“…Barata et al [58] report performance measures of SE = 98%, SP = 90% on PH2 dataset and SE = 83%, SP = 76% on EDRA datasets considering a fusion of features. A recent work [59] , introduces sparse coding of the Scale-Invariant Feature Transform (SIFT) features for melanoma classification. Reference [59] reports a performance of SE = 100%, SP = 90.3% on the PH2 dataset.…”

“…A recent work [59] , introduces sparse coding of the Scale-Invariant Feature Transform (SIFT) features for melanoma classification. Reference [59] reports a performance of SE = 100%, SP = 90.3% on the PH2 dataset.…”

Sparse Coded Handcrafted and Deep Features for Colon Capsule Video Summarization

“…These features can be efficiently represented by using sparse coding techniques. Sparse signal representation has become very popular in the past decades and lead to state-of-the-art results in various applications such as face recognition [24], image denoising [25], and image classification [26]. The main goal of sparse modeling is to efficiently represent the images as a linear combination of a few typical patterns, called atoms, selected from a dictionary.…”

Machine learning–based diagnosis of melanoma using macro images

“…Abbas et al have discussed the improved versions of random forest (RF), logistic model tree, and hidden naive Bayes classifiers. However, the RF algorithm is found to be the most effective algorithm for classification of dermatological images with a 0.948 AUC . Li et al proposed a melanoma diagnostic model using spectroscopic images of a lesion .…”