Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity
Carotid plaque echogenicity in ultrasound images has been found to be closely correlated with the risk of stroke in atherosclerotic patients. The automatic and accurate classification of carotid plaque echogenicity is of great significance for clinically estimating the stability of carotid plaques a...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2021-01-01
|
Series: | Computational and Mathematical Methods in Medicine |
Online Access: | http://dx.doi.org/10.1155/2021/3425893 |
id |
doaj-59f82523b62d49aa8743557130e1107e |
---|---|
record_format |
Article |
spelling |
doaj-59f82523b62d49aa8743557130e1107e2021-08-30T00:00:31ZengHindawi LimitedComputational and Mathematical Methods in Medicine1748-67182021-01-01202110.1155/2021/3425893Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque EchogenicityWei Ma0Xinyao Cheng1Xiangyang Xu2Furong Wang3Ran Zhou4Aaron Fenster5Mingyue Ding6Medical Ultrasound LaboratoryDepartment of CardiologyDepartment of RadiologyDepartment of Ultrasound ImagingSchool of Computer ScienceImaging Research LaboratoriesMedical Ultrasound LaboratoryCarotid plaque echogenicity in ultrasound images has been found to be closely correlated with the risk of stroke in atherosclerotic patients. The automatic and accurate classification of carotid plaque echogenicity is of great significance for clinically estimating the stability of carotid plaques and predicting cardiovascular events. Existing convolutional neural networks (CNNs) can provide an automatic carotid plaque echogenicity classification; however, they require a fixed-size input image, while the carotid plaques are of varying sizes. Although cropping and scaling the input carotid plaque images is promising, it will cause content loss or distortion and hence reduce the classification accuracy. In this study, we redesign the spatial pyramid pooling (SPP) and propose multilevel strip pooling (MSP) for the automatic and accurate classification of carotid plaque echogenicity in the longitudinal section. The proposed MSP module can accept arbitrarily sized carotid plaques as input and capture a long-range informative context to improve the accuracy of classification. In our experiments, we implement an MSP-based CNN by using the visual geometry group (VGG) network as the backbone. A total of 1463 carotid plaques (335 echo-rich plaques, 405 intermediate plaques, and 723 echolucent plaques) were collected from Zhongnan Hospital of Wuhan University. The 5-fold cross-validation results show that the proposed MSP-based VGGNet achieves a sensitivity of 92.1%, specificity of 95.6%, accuracy of 92.1%, and F1-score of 92.1%. These results demonstrate that our approach provides a way to enhance the applicability of CNN by enabling the acceptance of arbitrary input sizes and improving the classification accuracy of carotid plaque echogenicity, which has a great potential for an efficient and objective risk assessment of carotid plaques in the clinic.http://dx.doi.org/10.1155/2021/3425893 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wei Ma Xinyao Cheng Xiangyang Xu Furong Wang Ran Zhou Aaron Fenster Mingyue Ding |
spellingShingle |
Wei Ma Xinyao Cheng Xiangyang Xu Furong Wang Ran Zhou Aaron Fenster Mingyue Ding Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity Computational and Mathematical Methods in Medicine |
author_facet |
Wei Ma Xinyao Cheng Xiangyang Xu Furong Wang Ran Zhou Aaron Fenster Mingyue Ding |
author_sort |
Wei Ma |
title |
Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity |
title_short |
Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity |
title_full |
Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity |
title_fullStr |
Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity |
title_full_unstemmed |
Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity |
title_sort |
multilevel strip pooling-based convolutional neural network for the classification of carotid plaque echogenicity |
publisher |
Hindawi Limited |
series |
Computational and Mathematical Methods in Medicine |
issn |
1748-6718 |
publishDate |
2021-01-01 |
description |
Carotid plaque echogenicity in ultrasound images has been found to be closely correlated with the risk of stroke in atherosclerotic patients. The automatic and accurate classification of carotid plaque echogenicity is of great significance for clinically estimating the stability of carotid plaques and predicting cardiovascular events. Existing convolutional neural networks (CNNs) can provide an automatic carotid plaque echogenicity classification; however, they require a fixed-size input image, while the carotid plaques are of varying sizes. Although cropping and scaling the input carotid plaque images is promising, it will cause content loss or distortion and hence reduce the classification accuracy. In this study, we redesign the spatial pyramid pooling (SPP) and propose multilevel strip pooling (MSP) for the automatic and accurate classification of carotid plaque echogenicity in the longitudinal section. The proposed MSP module can accept arbitrarily sized carotid plaques as input and capture a long-range informative context to improve the accuracy of classification. In our experiments, we implement an MSP-based CNN by using the visual geometry group (VGG) network as the backbone. A total of 1463 carotid plaques (335 echo-rich plaques, 405 intermediate plaques, and 723 echolucent plaques) were collected from Zhongnan Hospital of Wuhan University. The 5-fold cross-validation results show that the proposed MSP-based VGGNet achieves a sensitivity of 92.1%, specificity of 95.6%, accuracy of 92.1%, and F1-score of 92.1%. These results demonstrate that our approach provides a way to enhance the applicability of CNN by enabling the acceptance of arbitrary input sizes and improving the classification accuracy of carotid plaque echogenicity, which has a great potential for an efficient and objective risk assessment of carotid plaques in the clinic. |
url |
http://dx.doi.org/10.1155/2021/3425893 |
work_keys_str_mv |
AT weima multilevelstrippoolingbasedconvolutionalneuralnetworkfortheclassificationofcarotidplaqueechogenicity AT xinyaocheng multilevelstrippoolingbasedconvolutionalneuralnetworkfortheclassificationofcarotidplaqueechogenicity AT xiangyangxu multilevelstrippoolingbasedconvolutionalneuralnetworkfortheclassificationofcarotidplaqueechogenicity AT furongwang multilevelstrippoolingbasedconvolutionalneuralnetworkfortheclassificationofcarotidplaqueechogenicity AT ranzhou multilevelstrippoolingbasedconvolutionalneuralnetworkfortheclassificationofcarotidplaqueechogenicity AT aaronfenster multilevelstrippoolingbasedconvolutionalneuralnetworkfortheclassificationofcarotidplaqueechogenicity AT mingyueding multilevelstrippoolingbasedconvolutionalneuralnetworkfortheclassificationofcarotidplaqueechogenicity |
_version_ |
1721186093868515328 |