Cargando…

Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation

BACKGROUND: Dermoscopy imaging has been a routine examination approach for skin lesion diagnosis. Accurate segmentation is the first step for automatic dermoscopy image assessment. OBJECTIVE: The main challenges for skin lesion segmentation are numerous variations in viewpoint and scale of skin lesi...

Descripción completa

Detalles Bibliográficos
Autores principales: He, Xinzi, Yu, Zhen, Wang, Tianfu, Lei, Baiying, Shi, Yiyan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: IOS Press 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6004941/
https://www.ncbi.nlm.nih.gov/pubmed/29758959
http://dx.doi.org/10.3233/THC-174633
_version_ 1783332614187253760
author He, Xinzi
Yu, Zhen
Wang, Tianfu
Lei, Baiying
Shi, Yiyan
author_facet He, Xinzi
Yu, Zhen
Wang, Tianfu
Lei, Baiying
Shi, Yiyan
author_sort He, Xinzi
collection PubMed
description BACKGROUND: Dermoscopy imaging has been a routine examination approach for skin lesion diagnosis. Accurate segmentation is the first step for automatic dermoscopy image assessment. OBJECTIVE: The main challenges for skin lesion segmentation are numerous variations in viewpoint and scale of skin lesion region. METHODS: To handle these challenges, we propose a novel skin lesion segmentation network via a very deep dense deconvolution network based on dermoscopic images. Specifically, the deep dense layer and generic multi-path Deep RefineNet are combined to improve the segmentation performance. The deep representation of all available layers is aggregated to form the global feature maps using skip connection. Also, the dense deconvolution layer is leveraged to capture diverse appearance features via the contextual information. Finally, we apply the dense deconvolution layer to smooth segmentation maps and obtain final high-resolution output. RESULTS: Our proposed method shows the superiority over the state-of-the-art approaches based on the public available 2016 and 2017 skin lesion challenge dataset and achieves the accuracy of 96.0% and 93.9%, which obtained a 6.0% and 1.2% increase over the traditional method, respectively. CONCLUSIONS: By utilizing Dense Deconvolution Net, the average time for processing one testing images with our proposed framework was 0.253 s.
format Online
Article
Text
id pubmed-6004941
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher IOS Press
record_format MEDLINE/PubMed
spelling pubmed-60049412018-07-05 Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation He, Xinzi Yu, Zhen Wang, Tianfu Lei, Baiying Shi, Yiyan Technol Health Care Research Article BACKGROUND: Dermoscopy imaging has been a routine examination approach for skin lesion diagnosis. Accurate segmentation is the first step for automatic dermoscopy image assessment. OBJECTIVE: The main challenges for skin lesion segmentation are numerous variations in viewpoint and scale of skin lesion region. METHODS: To handle these challenges, we propose a novel skin lesion segmentation network via a very deep dense deconvolution network based on dermoscopic images. Specifically, the deep dense layer and generic multi-path Deep RefineNet are combined to improve the segmentation performance. The deep representation of all available layers is aggregated to form the global feature maps using skip connection. Also, the dense deconvolution layer is leveraged to capture diverse appearance features via the contextual information. Finally, we apply the dense deconvolution layer to smooth segmentation maps and obtain final high-resolution output. RESULTS: Our proposed method shows the superiority over the state-of-the-art approaches based on the public available 2016 and 2017 skin lesion challenge dataset and achieves the accuracy of 96.0% and 93.9%, which obtained a 6.0% and 1.2% increase over the traditional method, respectively. CONCLUSIONS: By utilizing Dense Deconvolution Net, the average time for processing one testing images with our proposed framework was 0.253 s. IOS Press 2018-05-29 /pmc/articles/PMC6004941/ /pubmed/29758959 http://dx.doi.org/10.3233/THC-174633 Text en © 2018 – IOS Press and the authors. All rights reserved https://creativecommons.org/licenses/by-nc/4.0/ This article is published online with Open Access and distributed under the terms of the Creative Commons Attribution Non-Commercial License (CC BY-NC 4.0).
spellingShingle Research Article
He, Xinzi
Yu, Zhen
Wang, Tianfu
Lei, Baiying
Shi, Yiyan
Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation
title Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation
title_full Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation
title_fullStr Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation
title_full_unstemmed Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation
title_short Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation
title_sort dense deconvolution net: multi path fusion and dense deconvolution for high resolution skin lesion segmentation
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6004941/
https://www.ncbi.nlm.nih.gov/pubmed/29758959
http://dx.doi.org/10.3233/THC-174633
work_keys_str_mv AT hexinzi densedeconvolutionnetmultipathfusionanddensedeconvolutionforhighresolutionskinlesionsegmentation
AT yuzhen densedeconvolutionnetmultipathfusionanddensedeconvolutionforhighresolutionskinlesionsegmentation
AT wangtianfu densedeconvolutionnetmultipathfusionanddensedeconvolutionforhighresolutionskinlesionsegmentation
AT leibaiying densedeconvolutionnetmultipathfusionanddensedeconvolutionforhighresolutionskinlesionsegmentation
AT shiyiyan densedeconvolutionnetmultipathfusionanddensedeconvolutionforhighresolutionskinlesionsegmentation