Abstract
Malignant melanoma is among the fastest increasing malignancies in many countries. Due to its propensity to metastasize and lack of effective therapies for most patients with advanced disease, early detection of melanoma is a clinical imperative. In non-Caucasian populations, melanomas are frequently located in acral volar areas and their dermoscopic appearance differs from the non-acral ones. Although lesion segmentation is a natural preliminary step towards its further analysis, so far virtually no acral skin lesion segmentation method has been proposed. Our goal was to develop an effective segmentation algorithm dedicated for acral lesions. We obtain a superpixel oversegmentation of a lesion image by performing clustering in a joint color-spatial 5d space defined by coordinates of CIELAB color space and spatial coordinates of the image. We then construct a region adjacency graph based on this superpixel representation. We obtain the ultimate segmentation result by performing a hierarchical region merging. The proposed segmentation method has been tested on 134 color dermoscopic images of different types of acral melanocytic lesions (including melanoma) from various sources. It achieved an average Dice index value of 0.85, accuracy 0.91, precision 0.89, sensitivity 0.87, and specificity 0.88. Experimental results suggest the effectiveness of the proposed method, which would help improve the accuracy of other diagnostic algorithms for acral melanoma detection. The results also suggest that the computational approach towards lesion segmentation yields more stable output than manual segmentation by dermatologists.
Highlights
Human cutaneous melanoma is the deadliest type of skin cancer, characterized by a swiftly rising incidence rate [1]
The proposed segmentation method has been tested on color dermoscopic images from a widely used Interactive Atlas of Dermoscopy [2]
We presented an acral skin lesion segmentation algorithm based on a region adjacency graph
Summary
Human cutaneous melanoma is the deadliest type of skin cancer, characterized by a swiftly rising incidence rate [1]. It is among the most aggressive neoplasms, rapidly metastasizing to distant organs. ALM has four patterns considering pigmentation: parallel-furrow, lattice-like, fibrillar, and parallel-ridge pattern [4]. Among these patterns, ALM lesions with the furrow and ridge patterns occurs most frequently [3]. The examination of pigmentation patterns is possible through a digital epiluminescence microscopy (ELM, dermoscopy or dermatoscopy) which is a non-invasive, in vivo technique that makes subsurface structures of the skin accessible for examination in an
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.