A Decision Support System Based on the Semantic Analysis of Melanoma Images Using Multi-elitist PSO and SVM

Piatkowska, W.; Martyna, Jerzy; Nowak, Leszek; Przystalski, Karol

doi:10.1007/978-3-642-23199-5_27

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ballerini et al designed a hierarchical classification system based on K-NN using texture and colour features to classify different types of nonmelanoma skin lesions with 93 % malignant-versus-benign accuracy and 74 % interclass accuracy [8]. Piatkowska et al achieved 96 % classification accuracy using a multi-elitist particle swarm optimization method [44]. Thorough reviews of existing classification schemes can be found in [35,39].…”

Section: Feature Extraction and Classificationmentioning

confidence: 98%

Melanoma Decision Support Using Lighting-Corrected Intuitive Feature Models

Amelard

Glaister

Wong

et al. 2013

Series in BioEngineering

View full text Add to dashboard Cite

Skin lesion analysis using standard camera images has received limited attention from the scientific community due to its technical complexity and scarcity of data. The images are privy to lighting variations caused by uneven source lighting, and unconstrained differences in resolution, scale, and equipment. In this chapter, we propose a framework that performs illumination correction and feature extraction on photographs of skin lesions acquired using standard consumer-grade cameras. We apply a multi-stage illumination correction algorithm and define a set of high-level intuitive features (HLIF) that quantifies the level of asymmetry and border irregularity about a lesion. This lighting-corrected intuitive feature model framework can be used to classify skin lesion diagnoses with high accuracy. The framework accurately corrects the illumination variations and achieves high and precise sensitivity (95 % confidence interval (CI), 73.1-73.5 %) and specificity (95 % CI, 72.0-72.4 %) using a linear support vector machine classifier with cross-validation trials. It exhibits higher test-retest reliability than the much larger state-of-the-art low-level feature set (95 % CI,. Combining our framework with these low-level features attains sensitivity (95 % CI, 83.3-84.8 %) and specificity (95 % CI, 79.7-80.1 %), which is more accurate and reliable than classification using the low-level feature set.

show abstract

Section: Feature Extraction and Classificationmentioning

confidence: 98%

Melanoma Decision Support Using Lighting-Corrected Intuitive Feature Models

Amelard

Glaister

Wong

et al. 2013

Series in BioEngineering

View full text Add to dashboard Cite

show abstract

“…Support Vector Machines (SVM) is supervised learning model with associated learning algorithm. SVM is most commonly used in classification problems [27,31]. In the algorithm, each data element is a point in n-dimensional space (where n is the number of features), the value of each feature is a coordinate value.…”

Section: Supervised Machine Learning Algorithm In Classificationmentioning

confidence: 99%

An Overview of Classification Methods From Dermoscopy Images in Skin Lesion Diagnostic

Michalska¹,

Boyko

2020

IAPGOS

View full text Add to dashboard Cite

The article contains a review of selected classification methods of dermatoscopic images with human skin lesions, taking into account various stages of dermatological disease. The described algorithms are widely used in the diagnosis of skin lesions, such as artificial neural networks (CNN, DCNN), random forests, SVM, kNN classifier, AdaBoost MC and their modifications. The effectiveness, specificity and accuracy of classifications based on the same data sets were also compared and analyzed.

show abstract

“…There has been research done on stages like calibration [3], segmentation [4,5] geometric and colorimetric evaluation [6], and image classification [7]. Each of the stages is complex process itself while feature extraction is the most challenge rich, as there are a number of features needed to be extracted and each is unique in it own.…”

Section: -Dermoscopic Structuresmentioning

confidence: 99%

Melanocytic globules detection in skin lesion images

Nowak

Grzesiak-Kopeć

Ogorzalek

2015

12th International Symposium on Operations Research and Its Applications in Engineering, Technology and Management (ISORA 2015)

View full text Add to dashboard Cite

In this paper a method is presented for detection of melanin globules often present in melanocytic skin lesions images. The detection is done by performing image analysis similar to the one used in clinical evaluation. The method uses multi-stage image filtering to extract objects present in the dermoscopic image that match globule structure pattern. Classification of the found objects is made based on shape and size of globule structure. The classification is problematic task due to color and scale differences between dermatologic images and is related to differences between image acquisition equipment used in dermatoscopy. First we describe characteristic of globule structure needed for correct classification, along with method for calculating those characteristic. Next we presented a method for globules detection that is a part of computer-aided diagnostic process of melanocytic skin lesions. Evaluation of such lesions is a basis for early detection of malignant lesions.

show abstract

A Decision Support System Based on the Semantic Analysis of Melanoma Images Using Multi-elitist PSO and SVM

Cited by 4 publications

References 19 publications

Melanoma Decision Support Using Lighting-Corrected Intuitive Feature Models

Melanoma Decision Support Using Lighting-Corrected Intuitive Feature Models

An Overview of Classification Methods From Dermoscopy Images in Skin Lesion Diagnostic

Melanocytic globules detection in skin lesion images

Contact Info

Product

Resources

About