Skip to main content

Research Repository

Advanced Search

Recovering skin reflectance and geometry for diagnosis of melanoma

Sun, Jiuai; Liu, Zhao; Ding, Yi; Smith, Melvyn

Authors

Jiuai Sun

Zhao Liu

Yi Ding

Profile Image

Melvyn Smith Melvyn.Smith@uwe.ac.uk
Research Centre Director Vision Lab/Prof



Contributors

Jacob Scharcanski
Editor

Emre Celebi
Editor

Abstract

In order to achieve an early detection of skin cancers, various state-of-the-art imaging modalities have been investigated from optical, impedance, biomechanical and physiological perspectives to find out the potential biomarkers. However multilayered skin microstructure and a wide spectrum of dynamical chromophores embedded underneath skin make it very challenging to quantify this mostly accessible, but very complex and heterogeneous largest organ of the human body. Rather than concentrating on characterizing those internal features in a microscopic level, both lesion reflectance (colour) and 3D geometry have been suggested to recover through a relative easy and cost effective way towards an improved diagnosis of melanoma. The reflectance recovered can be used as a good replacement for conventional photograph for the measurement of the ABCD criteria, while the geometry of lesion surface provides extra dimension for characterizing the topography disruption of lesion region. As both the reflectance and geometry of skin surface generally reflect the growth of chromophore cells under the skin, any external abnormalities indicating the change of skin conditions must accompany with some irregular evolvement and change with these cells. For example, a blurred and asymmetrical border possibly reveals an abnormal growth of melanocytes in the horizontal phase; whiles 3D surface

Citation

Sun, J., Liu, Z., Ding, Y., & Smith, M. (2013). Recovering skin reflectance and geometry for diagnosis of melanoma. In J. Scharcanski, & E. Celebi (Eds.), Computer Vision Techniques for the Diagnosis of Skin Cancer (243-265). UK: Springer

Publication Date Jan 1, 2013
Publicly Available Date Mar 29, 2024
Peer Reviewed Peer Reviewed
Pages 243-265
Series Title Series in BioEngineering
Book Title Computer Vision Techniques for the Diagnosis of Skin Cancer
ISBN 978-3-642-39607-6
Keywords malanoma, skin surface, reflectance, profile, chromophore index, skin analyzer, topography distribution, photometric stereo, segmentation
Public URL https://uwe-repository.worktribe.com/output/940511
Publisher URL http://www.springer.com/engineering/biomedical+engineering/book/978-3-642-39607-6