Non-Invasive Skin Cancer Diagnosis Using Hyperspectral Imaging for In-Situ Clinical Support.

Raquel Leon,Eduardo Quevedo,Beatriz Martinez-Vega,Pablo Almeida,Veronica Melian,Gustavo M Callico,Samuel Ortega,Javier A Hernandez,Irene Castaño,Gregorio Carretero,Bernardino Clavo,Aday Garcia,Himar Fabelo

doi:10.3390/jcm9061662

Abstract

Skin cancer is one of the most common forms of cancer worldwide and its early detection its key to achieve an effective treatment of the lesion. Commonly, skin cancer diagnosis is based on dermatologist expertise and pathological assessment of biopsies. Although there are diagnosis aid systems based on morphological processing algorithms using conventional imaging, currently, these systems have reached their limit and are not able to outperform dermatologists. In this sense, hyperspectral (HS) imaging (HSI) arises as a new non-invasive technology able to facilitate the detection and classification of pigmented skin lesions (PSLs), employing the spectral properties of the captured sample within and beyond the human eye capabilities. This paper presents a research carried out to develop a dermatological acquisition system based on HSI, employing 125 spectral bands captured between 450 and 950 nm. A database composed of 76 HS PSL images from 61 patients was obtained and labeled and classified into benign and malignant classes. A processing framework is proposed for the automatic identification and classification of the PSL based on a combination of unsupervised and supervised algorithms. Sensitivity and specificity results of 87.5% and 100%, respectively, were obtained in the discrimination of malignant and benign PSLs. This preliminary study demonstrates, as a proof-of-concept, the potential of HSI technology to assist dermatologists in the discrimination of benign and malignant PSLs during clinical routine practice using a real-time and non-invasive hand-held device.

Highlights

Skin cancer is categorized as non-melanoma skin cancer (NMSC) and melanoma [1]
The proposed segmentation framework has the goal to select only pigmented skin lesions (PSLs) pixels in an HS image to reduce the data that will be sent to the classification stage and, decrease the computational cost of Support Vector Machine (SVM) classifier, performing a two-class classification
10 HS validation images from 8 different patients were evaluated with two methods based on the K-means and the SAM algorithms, using different K values to find out which combination of method and number of clusters offers the best results

Summary

Introduction

NMSC (excluding basal-cell carcinomas, BCCs) was the 5th most common form of cancer worldwide in 2018, involving over 1 million of new diagnoses and 65,000 death, while melanoma was the 21th with nearly 300,000 new cases and 60,000 death [1]. The process to diagnose skin cancer is accomplished by a dermatologist who perform a preliminary diagnosis by visually examining the PSL following the ABCDE (Asymmetry of the mole, Border irregularity, Color uniformity, Diameter and Evolving size, shape or color) rule [4]. After this examination, a biopsy is performed if the dermatologist suspects that the lesion is malignant. To avoid unnecessary surgical procedures, because of the uncertainty in the current diagnoses, new methods to improve skin cancer diagnosis must be investigated

Objectives

Methods

Results

Conclusion