A Novel Approach for the Shape Characterisation of Non-Melanoma Skin Lesions Using Elliptic Fourier Analyses and Clinical Images

Abstract

The early detection of Non-Melanoma Skin Cancer (NMSC) is crucial to achieve the best treatment outcomes. Shape is considered one of the main parameters taken for the detection of some types of skin cancer such as melanoma. For NMSC, the importance of shape as a visual detection parameter is not well-studied. A dataset of 993 standard camera images containing different types of NMSC and benign skin lesions was analysed. For each image, the lesion boundaries were extracted. After an alignment and scaling, Elliptic Fourier Analysis (EFA) coefficients were calculated for the boundary of each lesion. The asymmetry of lesions was also calculated. Then, multivariate statistics were employed for dimensionality reduction and finally computational learning classification was employed to evaluate the separability of the classes. The separation between malignant and benign samples was successful in most cases. The best-performing approach was the combination of EFA coefficients and asymmetry. The combination of EFA and asymmetry resulted in a balanced accuracy of 0.786 and an Area Under Curve of 0.735. The combination of EFA and asymmetry for lesion classification resulted in notable success rates when distinguishing between benign and malignant lesions. In light of these results, skin lesions’ shape should be integrated as a fundamental part of future detection techniques in clinical screening.

Near-infrared hyperspectral imaging and robust statistics for in vivo non-melanoma skin cancer and actinic keratosis characterisation

“…While IR light attains a greater depth of penetration, and thus offers information about both internal and external features undetectable to the naked eye, other variables such as symmetry, size, and border regularity, are also considered important diagnostic criteria. Considering the geometric resolution of these types of sensors, it would be interesting to see how multimodal datasets, combining both hyperspectral as well as morphological information [ 57 ], can aid in fine-tuning diagnostic tools.…”

Normalization of Snai1-mediated vessel dysfunction increases drug response in cancer

“…A challenge is the quantitative assessment of the morphological changes. Elliptic Fourier analysis has been successfully used for shape classi cation in a number of diagnostic settings: e.g., in the evaluation of non-melanoma skin lesions, the analysis of nuclei shapes in myeloproliferative diseases, or the tracking of changes in collagen spindle shapes in breast cancer progression [48][49][50]. It has also been employed in vessel analysis, namely the post-surgery follow-up in aortic remodeling [51,52].…”

A Convolutional Neural Network based system for classifying malignant and benign skin lesions using mobile-device images

“…Therefore, a lot of attention in the medical field has shifted toward the early detection and diagnosis of skin cancer. Various techniques have been adopted including the visual and manual inspection of the skin lesion using various methodologies, such as using the ABCDE lesion characterization rule when inspecting dermoscopic images [3]. Dermoscopic images are photographed using magnification and lighting using a dermatoscope, which can capture detailed skin structures in the epidermis that are not visible to the naked eye.…”

“…[3] proposed a framework for NMSC (Non-Melanoma Skin Cancer) detection based on camera images. First, the Elliptic Fourier Analysis (EFA) coefficients were obtained based on the skin lesion boundary.…”