Texture analysis and classification in coherent anti-Stokes Raman scattering (CARS) microscopy images for automated detection of skin cancer

Basal cell carcinoma (BCC) – which originate from basal cells – is the most frequent cancer in humans [1]. The diagnostics of this tumor can be highly complicated because of its diverse morphological manifestation [2]. Currently, the skin cancer is diagnosed – additionally to visual inspection – by a punch biopsy with subsequent histopathological analysis of H&E stained tissue sections [3,4]. This procedure is invasive, time-consuming and associated with high costs. However, early tumor detection is crucial for successful medical treatment and increase of survival rates [5].

Source: Computerized Medical Imaging and Graphics - March 7, 2015 Category: Radiology Authors: Fisseha Bekele Legesse, Anna Medyukhina, Sandro Heuke, Jürgen Popp Source Type: research