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

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.

Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing

“…In Table 5 results from other researchers are provided. From Table 5, we can discern that most research studies have been discrimination of the aggressive melanoma PSLs, where Nagaoka et al [11] and Leon et al [8] had the highest sensitivity and specificity. Stamnes et al [17] also had high such measures; however, these were only discriminating between benign and malignant PSLs.…”

“…The system used to acquire the HS dermatologic images is described in [20], using the same database as in Leon et al [8]. The database consists of 76 images of PSLs from 61 patients: 36 cancerous and 40 noncancerous.…”

“…HSI technology has already been explored as a target technology to aid in PSLs diagnosis. A recent study by Leon et al showed promising results in discriminating PSLs by random forests and artificial neural networks [8]. Another recent study by Hosking et al used digital dermascopy HSI with machine learning methods in order to detect melanomas [9].…”

Information Extraction Techniques in Hyperspectral Imaging Biomedical Applications

“…In the context of surgical guidance, Akbari et al processed HS images from the abdomen to detect intestinal ischemia [36]. For cancer detection, SVM and HSI have been used for the identification of gastric cancer [37], prostate cancer [38], tongue cancer [39], and skin cancer [40]. Although RF and MLR have been widely used for HS information extraction, their usage in medical HSI is limited.…”

“…Pixel-wise classification SVM Intestinal ischemia identification [36] Gastric cancer detection [37] Prostate cancer [38] Tongue cancer [39] Skin cancer [40] RF In-vivo oral cancer [41] MLR Ulcerative colitis in histological slides [42] SVM, RF Brain cancer in histological slides [43] SVM, RF, LDA Head and neck tumor [44] Feature extraction and feature selection PCA Biliary trees visualization enhancement [52] PCA and false color Melanocytic lesions visualization [53] PCA and supervised classification Detection of in-vivo oral cancer [54] Prostate cancer in histological slides [55] The identification of white blood cells in blood smear slides [56] Intraoperative brain tumor delineation [57] Orthogonal projections Retina analysis for Alzheimer's detection [58] t-SNE and supervised classification…”