Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/36691

Title: Fusing fine-tuned deep features for skin lesion classification
Authors: Mahbod, Amirreza
Schaefer, Gerald
Ellinger, Isabella
Ecker, Rupert
Pitiot, Alain
Wang, Chunliang
Keywords: Dermatology,
Skin cancer
Melanoma
Dermoscopy
Medical image analysis
Deep learning
Issue Date: 2019
Publisher: © Elsevier
Citation: MAHBOD, A. ... et al., 2019. Fusing fine-tuned deep features for skin lesion classification. Computerized Medical Imaging and Graphics, 71, pp. 19-29.
Abstract: © 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.
Description: This paper is in closed access until 3rd Nov 2019.
Sponsor: This work was supported by the European Union Horizon 2020 Research and Innovation Program (”CaSR Biomedicine”, 675228).
Version: Accepted for publication
DOI: 10.1016/j.compmedimag.2018.10.007
URI: https://dspace.lboro.ac.uk/2134/36691
Publisher Link: https://doi.org/10.1016/j.compmedimag.2018.10.007
ISSN: 0895-6111
Appears in Collections:Closed Access (Computer Science)

Files associated with this item:

File Description SizeFormat
cmig18.pdfAccepted version5.18 MBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.