Share Email Print

Proceedings Paper

Pigmented skin lesion segmentation based on random forest and full convolutional neural networks
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Segmentation of pigmented lesions is often affected by factors such as hair around the skin lesions, artificial markings, etc., and the complexity of the lesion itself, such as lesions and skin boundaries is not clear, the internal color of lesions is variable, etc., resulting in segmentation difficulties. Aiming at the problem that the segmentation method of pigmented skin lesions using only random forests is not accurate, a segmentation method for pigmented skin lesion using a combination of random forest and fully convolutional neural networks (FCN) is proposed. This method firstly classifies and recognizes skin lesion images based on random forests to obtain a probability distribution of the lesions and the background. Then, the other probability distribution is obtained using FCN based on an improved loss function. Finally, the classification results of random forest and FCN are fused into the final image segmentation results. The experimental results show that the combination of random forest and FCN yields better performances than using random forest alone, in particular, can increase the sensitivity by about 20%.

Paper Details

Date Published: 23 October 2018
PDF: 7 pages
Proc. SPIE 10820, Optics in Health Care and Biomedical Optics VIII, 108203M (23 October 2018); doi: 10.1117/12.2503941
Show Author Affiliations
Tiejun Yang, Guilin Univ. of Technology (China)
Shan Peng, Guilin Univ. of Technology (China)
Ping Hu, Guilin Univ. of Technology (China)
Lin Huang, Guilin Univ. of Technology (China)

Published in SPIE Proceedings Vol. 10820:
Optics in Health Care and Biomedical Optics VIII
Qingming Luo; Xingde Li; Ying Gu; Yuguo Tang, Editor(s)

© SPIE. Terms of Use
Back to Top