Loughborough University
Browse
cmig18.pdf (5.06 MB)

Fusing fine-tuned deep features for skin lesion classification

Download (5.06 MB)
journal contribution
posted on 2019-01-29, 09:43 authored by Amirreza Mahbod, Gerald SchaeferGerald Schaefer, Isabella Ellinger, Rupert Ecker, Alain Pitiot, Chunliang Wang
© 2018 Elsevier Ltd Malignant melanoma is one of the most aggressive forms of skin cancer. Early detection is important as it significantly improves survival rates. Consequently, accurate discrimination of malignant skin lesions from benign lesions such as seborrheic keratoses or benign nevi is crucial, while accurate computerised classification of skin lesion images is of great interest to support diagnosis. In this paper, we propose a fully automatic computerised method to classify skin lesions from dermoscopic images. Our approach is based on a novel ensemble scheme for convolutional neural networks (CNNs) that combines intra-architecture and inter-architecture network fusion. The proposed method consists of multiple sets of CNNs of different architecture that represent different feature abstraction levels. Each set of CNNs consists of a number of pre-trained networks that have identical architecture but are fine-tuned on dermoscopic skin lesion images with different settings. The deep features of each network were used to train different support vector machine classifiers. Finally, the average prediction probability classification vectors from different sets are fused to provide the final prediction. Evaluated on the 600 test images of the ISIC 2017 skin lesion classification challenge, the proposed algorithm yields an area under receiver operating characteristic curve of 87.3% for melanoma classification and an area under receiver operating characteristic curve of 95.5% for seborrheic keratosis classification, outperforming the top-ranked methods of the challenge while being simpler compared to them. The obtained results convincingly demonstrate our proposed approach to represent a reliable and robust method for feature extraction, model fusion and classification of dermoscopic skin lesion images.

Funding

This work was supported by the European Union Horizon 2020 Research and Innovation Program (”CaSR Biomedicine”, 675228).

History

School

  • Science

Department

  • Computer Science

Published in

Computerized Medical Imaging and Graphics

Volume

71

Pages

19 - 29

Citation

MAHBOD, A. ... et al., 2019. Fusing fine-tuned deep features for skin lesion classification. Computerized Medical Imaging and Graphics, 71, pp. 19-29.

Publisher

© Elsevier

Version

  • AM (Accepted Manuscript)

Publisher statement

This paper was accepted for publication in the journal Computerized Medical Imaging and Graphics and the definitive published version is available at https://doi.org/10.1016/j.compmedimag.2018.10.007.

Publication date

2019

ISSN

0895-6111

eISSN

1879-0771

Language

  • en