Fully Connected Visual Words for the Classification of Skin Cancer Confocal Images

Athanasios Kallipolitis, Alexandros Stratigos, Alexios Zarras, Ilias Maglogiannis

Abstract

Reflectance Confocal Microscopy (RCM) is an ancillary, non-invasive method for reviewing horizontal sections from areas of interest of the skin at a high resolution. In this paper, we propose a method based on the exploitation of Bag of Visual Words (BOVW) technique, coupled with a plain neural network to classify extracted information into discrete patterns of skin cancer types. The paper discusses the technical details of implementation, while providing promising initial results that reach 90% accuracy. Automated classification of RCM images can lead to the establishment of a reliable procedure for the assessment of skin cancer cases and the training of medical personnel through the quantization of image content. Moreover, early detected benign tumours can reduce significantly the number of time and resource consuming biopsies.

Download


Paper Citation


in Harvard Style

Kallipolitis A., Stratigos A., Zarras A. and Maglogiannis I. (2020). Fully Connected Visual Words for the Classification of Skin Cancer Confocal Images.In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2, pages 853-858. DOI: 10.5220/0009328808530858


in Bibtex Style

@conference{visapp20,
author={Athanasios Kallipolitis and Alexandros Stratigos and Alexios Zarras and Ilias Maglogiannis},
title={Fully Connected Visual Words for the Classification of Skin Cancer Confocal Images},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={853-858},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009328808530858},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Fully Connected Visual Words for the Classification of Skin Cancer Confocal Images
SN - 978-989-758-402-2
AU - Kallipolitis A.
AU - Stratigos A.
AU - Zarras A.
AU - Maglogiannis I.
PY - 2020
SP - 853
EP - 858
DO - 10.5220/0009328808530858