Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation
Deep convolutional neural networks (CNNs) have become one of the state-of-the-art methods for image classification in various domains. For biomedical image classification where the number of training images is generally limited, transfer learning using CNNs is often applied. Such technique extracts...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/136682 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-136682 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1366822020-01-10T03:55:55Z Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation Nguyen, Long D. Lin, Dongyun Lin, Zhiping Cao, Jiuwen School of Electrical and Electronic Engineering 2018 IEEE International Symposium on Circuits and Systems (ISCAS) Engineering::Computer science and engineering Engineering::Electrical and electronic engineering Feature Concatenation Microscopic Image Deep convolutional neural networks (CNNs) have become one of the state-of-the-art methods for image classification in various domains. For biomedical image classification where the number of training images is generally limited, transfer learning using CNNs is often applied. Such technique extracts generic image features from nature image datasets and these features can be directly adopted for feature extraction in smaller datasets. In this paper, we propose a novel deep neural network architecture based on transfer learning for microscopic image classification. In our proposed network, we concatenate the features extracted from three pretrained deep CNNs. The concatenated features are then used to train two fully-connected layers to perform classification. In the experiments on both the 2D-Hela and the PAP-smear datasets, our proposed network architecture produces significant performance gains comparing to the neural network structure that uses only features extracted from single CNN and several traditional classification methods. Accepted version 2020-01-10T03:55:55Z 2020-01-10T03:55:55Z 2018 Conference Paper Nguyen, L. D., Lin, D., Lin, Z., & Cao, J. (2018). 2018 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5. doi:10.1109/ISCAS.2018.8351550 9781538648810 https://hdl.handle.net/10356/136682 10.1109/ISCAS.2018.8351550 2-s2.0-85054291841 1 5 en © 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/ISCAS.2018.8351550 application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Engineering::Electrical and electronic engineering Feature Concatenation Microscopic Image |
spellingShingle |
Engineering::Computer science and engineering Engineering::Electrical and electronic engineering Feature Concatenation Microscopic Image Nguyen, Long D. Lin, Dongyun Lin, Zhiping Cao, Jiuwen Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation |
description |
Deep convolutional neural networks (CNNs) have become one of the state-of-the-art methods for image classification in various domains. For biomedical image classification where the number of training images is generally limited, transfer learning using CNNs is often applied. Such technique extracts generic image features from nature image datasets and these features can be directly adopted for feature extraction in smaller datasets. In this paper, we propose a novel deep neural network architecture based on transfer learning for microscopic image classification. In our proposed network, we concatenate the features extracted from three pretrained deep CNNs. The concatenated features are then used to train two fully-connected layers to perform classification. In the experiments on both the 2D-Hela and the PAP-smear datasets, our proposed network architecture produces significant performance gains comparing to the neural network structure that uses only features extracted from single CNN and several traditional classification methods. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Nguyen, Long D. Lin, Dongyun Lin, Zhiping Cao, Jiuwen |
format |
Conference or Workshop Item |
author |
Nguyen, Long D. Lin, Dongyun Lin, Zhiping Cao, Jiuwen |
author_sort |
Nguyen, Long D. |
title |
Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation |
title_short |
Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation |
title_full |
Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation |
title_fullStr |
Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation |
title_full_unstemmed |
Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation |
title_sort |
deep cnns for microscopic image classification by exploiting transfer learning and feature concatenation |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/136682 |
_version_ |
1681036592865607680 |