WFRF:(Wang Chunliang)
Sökning: WFRF:(Wang Chunliang) > Fusing fine-tuned d...
- 47 av 101
- Föregående post
- Nästa post
- Till träfflistan
Fusing fine-tuned deep features for skin lesion classification
- Mahbod, A. (författare)
- Schaefer, G. (författare)
- Ellinger, I. (författare)
- visa fler...
- Ecker, R. (författare)
- Pitiot, A. (författare)
- visa färre...
- (creator_code:org_t)
- Elsevier, 2019
- 2019
- Engelska.
- Ingår i: Computerized Medical Imaging and Graphics. - : Elsevier. - 0895-6111 .- 1879-0771. ; 71, s. 19-29
- Tidskriftsartikel (refereegranskat)
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Radiologi och bildbehandling (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Radiology, Nuclear Medicine and Medical Imaging (hsv//eng)
Nyckelord
- Skin cancer; Melanoma; Dermoscopy; Medical image analysis; Deep learning
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
- Computerized Medical Imaging and Graphics (Sök värdpublikationen i LIBRIS)
Till lärosätets databas
- 47 av 101
- Föregående post
- Nästa post
- Till träfflistan
Hitta mer i SwePub
- Av författaren/redakt...
- Mahbod, A.
- Schaefer, G.
- Ellinger, I.
- Ecker, R.
- Pitiot, A.
- Wang, Chunliang, ...
- Om ämnet
-
- MEDICIN OCH HÄLSOVETENSKAP
- MEDICIN OCH HÄLS ...
- och Klinisk medicin
- och Radiologi och bi ...
- Artiklar i publikationen
- Computerized Med ...
- Av lärosätet
- Kungliga Tekniska Högskolan
Sök utanför SwePub
- Sök vidare i:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - Nationella bibliotekssystem
- LIBRIS.kb.se
