Band selection in spectral imaging for non-invasive melanoma diagnosis

Ianisse Quinzán,Pedro Latorre-Carmona,Pedro García-Sevilla,Enrique Boldó,Filiberto Pla,José M Sotoca

doi:10.1364/boe.4.000514

Abstract

A method consisting of the combination of the Synthetic Minority Over-Sampling TEchnique (SMOTE) and the Sequential Forward Floating Selection (SFFS) technique is used to do band selection in a highly imbalanced, small size, two-class multispectral dataset of melanoma and non-melanoma lesions. The aim is to improve classification rate and help to identify those spectral bands that have a more important role in melanoma detection. All the processing steps were designed taking into account the low number of samples in the dataset, situation that is quite common in medical cases. The training/test sets are built using a Leave-One-Out strategy. SMOTE is applied in order to deal with the imbalance problem, together with the Qualified Majority Voting scheme (QMV). Support Vector Machines (SVM) is the classification method applied over each balanced set. Results indicate that all melanoma lesions are correctly classified, using a low number of bands, reaching 100% sensitivity and 72% specificity when considering nine (out of a total of 55) spectral bands.

Highlights

Cutaneous melanoma is one of the most common malignant skin cancers
A method consisting of the combination of the Synthetic Minority Over-Sampling TEchnique
All the processing steps were designed taking into account the low number of samples

Summary

Introduction

Cutaneous melanoma is one of the most common malignant skin cancers. The ABCD rule (A, Asymmetry, B, irregular Border, C, variety of Colors, and D, Diameter) helps in lesion diagnosis. Multispectral images acquired in the visible to near-infrared spectrum may help experts to differentiate benign from malignant lesions. Patwardhan, Dhawan et al [5] selected bands in the range from 350 to 700nm simulating light propagation using a Monte Carlo modeling approach. D‘Alessandro and Dhawan have analyzed melanoma lesions using a nevoscope, but in different sets in the infra-red spectral range [2, 7]. Other authors apply feature reduction methods over a group of features generated from the images, and not over the set of bands [8,9]

Objectives

Results

Conclusion