A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information
Pathological image classification is of great importance in various biomedical applications, such as for lesion detection, cancer subtype identification, and pathological grading. To this end, this paper proposed a novel classification framework using the multispace image reconstruction inputs and t...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2019-01-01
|
Series: | BioMed Research International |
Online Access: | http://dx.doi.org/10.1155/2019/3530903 |
id |
doaj-2e83b407ed6144d8b37537fe177756e0 |
---|---|
record_format |
Article |
spelling |
doaj-2e83b407ed6144d8b37537fe177756e02020-11-24T21:57:49ZengHindawi LimitedBioMed Research International2314-61332314-61412019-01-01201910.1155/2019/35309033530903A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural InformationHonglin Zhu0Huiyan Jiang1Siqi Li2Haoming Li3Yan Pei4Department of Software College, Northeastern University, Shenyang 110819, ChinaDepartment of Software College, Northeastern University, Shenyang 110819, ChinaDepartment of Software College, Northeastern University, Shenyang 110819, ChinaDepartment of Software College, Northeastern University, Shenyang 110819, ChinaSchool of Computer Science and Engineering, the University of Aizu, Aizuwakamatsu 965-8580, JapanPathological image classification is of great importance in various biomedical applications, such as for lesion detection, cancer subtype identification, and pathological grading. To this end, this paper proposed a novel classification framework using the multispace image reconstruction inputs and the transfer learning technology. Specifically, a multispace image reconstruction method was first developed to generate a new image containing three channels composed of gradient, gray level cooccurrence matrix (GLCM) and local binary pattern (LBP) spaces, respectively. Then, the pretrained VGG-16 net was utilized to extract the high-level semantic features of original images (RGB) and reconstructed images. Subsequently, the long short-term memory (LSTM) layer was used for feature selection and refinement while increasing its discrimination capability. Finally, the classification task was performed via the softmax classifier. Our framework was evaluated on a publicly available microscopy image dataset of IICBU malignant lymphoma. Experimental results demonstrated the performance advantages of our proposed classification framework by comparing with the related works.http://dx.doi.org/10.1155/2019/3530903 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Honglin Zhu Huiyan Jiang Siqi Li Haoming Li Yan Pei |
spellingShingle |
Honglin Zhu Huiyan Jiang Siqi Li Haoming Li Yan Pei A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information BioMed Research International |
author_facet |
Honglin Zhu Huiyan Jiang Siqi Li Haoming Li Yan Pei |
author_sort |
Honglin Zhu |
title |
A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information |
title_short |
A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information |
title_full |
A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information |
title_fullStr |
A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information |
title_full_unstemmed |
A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information |
title_sort |
novel multispace image reconstruction method for pathological image classification based on structural information |
publisher |
Hindawi Limited |
series |
BioMed Research International |
issn |
2314-6133 2314-6141 |
publishDate |
2019-01-01 |
description |
Pathological image classification is of great importance in various biomedical applications, such as for lesion detection, cancer subtype identification, and pathological grading. To this end, this paper proposed a novel classification framework using the multispace image reconstruction inputs and the transfer learning technology. Specifically, a multispace image reconstruction method was first developed to generate a new image containing three channels composed of gradient, gray level cooccurrence matrix (GLCM) and local binary pattern (LBP) spaces, respectively. Then, the pretrained VGG-16 net was utilized to extract the high-level semantic features of original images (RGB) and reconstructed images. Subsequently, the long short-term memory (LSTM) layer was used for feature selection and refinement while increasing its discrimination capability. Finally, the classification task was performed via the softmax classifier. Our framework was evaluated on a publicly available microscopy image dataset of IICBU malignant lymphoma. Experimental results demonstrated the performance advantages of our proposed classification framework by comparing with the related works. |
url |
http://dx.doi.org/10.1155/2019/3530903 |
work_keys_str_mv |
AT honglinzhu anovelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT huiyanjiang anovelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT siqili anovelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT haomingli anovelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT yanpei anovelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT honglinzhu novelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT huiyanjiang novelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT siqili novelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT haomingli novelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation AT yanpei novelmultispaceimagereconstructionmethodforpathologicalimageclassificationbasedonstructuralinformation |
_version_ |
1725853343942705152 |