Melanoma recognition in dermoscopy images via aggregated deep convolutional features
In this paper, we present a novel framework for dermoscopy image recognition via both a deep learning method and a local descriptor encoding strategy. Specifically, deep representations of a rescaled dermoscopy image are first extracted via a very deep residual neural network pretrained on a large n...
Saved in:
Main Authors: | , , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/145335 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-145335 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1453352020-12-17T07:02:19Z Melanoma recognition in dermoscopy images via aggregated deep convolutional features Yu, Zhen Jiang, Xudong Zhou, Feng Qin, Jing Ni, Dong Chen, Siping Lei, Baiying Wang, Tianfu School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Feature Extraction Medical Image Processing In this paper, we present a novel framework for dermoscopy image recognition via both a deep learning method and a local descriptor encoding strategy. Specifically, deep representations of a rescaled dermoscopy image are first extracted via a very deep residual neural network pretrained on a large natural image dataset. Then these local deep descriptors are aggregated by orderless visual statistic features based on Fisher vector (FV) encoding to build a global image representation. Finally, the FV encoded representations are used to classify melanoma images using a support vector machine with a Chi-squared kernel. Our proposed method is capable of generating more discriminative features to deal with large variations within melanoma classes, as well as small variations between melanoma and nonmelanoma classes with limited training data. Extensive experiments are performed to demonstrate the effectiveness of our proposed method. Comparisons with state-of-the-art methods show the superiority of our method using the publicly available ISBI 2016 Skin lesion challenge dataset. 2020-12-17T07:02:19Z 2020-12-17T07:02:19Z 2019 Journal Article Yu, Z., Jiang, X., Zhou, F., Qin, J., Ni, D., Chen, S., ... Wang, T. (2019). Melanoma recognition in dermoscopy images via aggregated deep convolutional features. IEEE Transactions on Biomedical Engineering, 66(4), 1006-1016. doi:10.1109/TBME.2018.2866166 1558-2531 https://hdl.handle.net/10356/145335 10.1109/TBME.2018.2866166 30130171 4 66 1006 1016 en IEEE Transactions on Biomedical Engineering © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TBME.2018.2866166 |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Feature Extraction Medical Image Processing |
spellingShingle |
Engineering::Electrical and electronic engineering Feature Extraction Medical Image Processing Yu, Zhen Jiang, Xudong Zhou, Feng Qin, Jing Ni, Dong Chen, Siping Lei, Baiying Wang, Tianfu Melanoma recognition in dermoscopy images via aggregated deep convolutional features |
description |
In this paper, we present a novel framework for dermoscopy image recognition via both a deep learning method and a local descriptor encoding strategy. Specifically, deep representations of a rescaled dermoscopy image are first extracted via a very deep residual neural network pretrained on a large natural image dataset. Then these local deep descriptors are aggregated by orderless visual statistic features based on Fisher vector (FV) encoding to build a global image representation. Finally, the FV encoded representations are used to classify melanoma images using a support vector machine with a Chi-squared kernel. Our proposed method is capable of generating more discriminative features to deal with large variations within melanoma classes, as well as small variations between melanoma and nonmelanoma classes with limited training data. Extensive experiments are performed to demonstrate the effectiveness of our proposed method. Comparisons with state-of-the-art methods show the superiority of our method using the publicly available ISBI 2016 Skin lesion challenge dataset. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Yu, Zhen Jiang, Xudong Zhou, Feng Qin, Jing Ni, Dong Chen, Siping Lei, Baiying Wang, Tianfu |
format |
Article |
author |
Yu, Zhen Jiang, Xudong Zhou, Feng Qin, Jing Ni, Dong Chen, Siping Lei, Baiying Wang, Tianfu |
author_sort |
Yu, Zhen |
title |
Melanoma recognition in dermoscopy images via aggregated deep convolutional features |
title_short |
Melanoma recognition in dermoscopy images via aggregated deep convolutional features |
title_full |
Melanoma recognition in dermoscopy images via aggregated deep convolutional features |
title_fullStr |
Melanoma recognition in dermoscopy images via aggregated deep convolutional features |
title_full_unstemmed |
Melanoma recognition in dermoscopy images via aggregated deep convolutional features |
title_sort |
melanoma recognition in dermoscopy images via aggregated deep convolutional features |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/145335 |
_version_ |
1688665360797007872 |