DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free Ratio
Accurate iFR calculation can provide important clinical information for intracoronary functional assessment without administration of adenosine, which needs to locate object points in the pressure waveforms: peak, the dichrotic notch and the pressure nadir at the end of diastole. We propose a DFENet...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Journal of Translational Engineering in Health and Medicine |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9107210/ |
id |
doaj-d2506b8a57e342c0aa608dc8d7a397f5 |
---|---|
record_format |
Article |
spelling |
doaj-d2506b8a57e342c0aa608dc8d7a397f52021-03-29T18:41:04ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722020-01-01811110.1109/JTEHM.2020.29997259107210DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free RatioJiping Li0Liang Song1Heye Zhang2School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, ChinaInsight Lifetech Company Ltd., Shenzhen, ChinaSchool of Biomedical Engineering, Sun Yat-sen University, Guangzhou, ChinaAccurate iFR calculation can provide important clinical information for intracoronary functional assessment without administration of adenosine, which needs to locate object points in the pressure waveforms: peak, the dichrotic notch and the pressure nadir at the end of diastole. We propose a DFENet that is capable of locating object points to calculate iFR accurately. We first design a SFRA into DFENet with the idea of DenseNet. To avoid overfitting when dealing with sparse signals, we set appropriate number of network layers, growth rate of dense blocks and compression rate of transition blocks in 1D DenseNet. Then, we introduce a feature enhancement mechanism named 1D SE block for enhancing inconspicuous but vital features from SFRA, which guides DFENet to focus on these important features via feature recalibration. Finally, we prove an effective interaction mode between SFRA and 1D SE block to locate object points accurately. Adequate experiments demonstrate that DFENet reaches a high accuracy of 94.22%, error of 5.6 on object point localization of 1D pressure waveforms that include 1457 samples from 100 subjects via a cross-validation of Leave-One-Out. Comparison experiment demonstrates that the accuracy of DFENet exceeds other state-of-the-art methods by 3.35%, and ablation experiment demonstrates that the accuracy of SFRA and cSE exceed the other variations by 6.63% and 2.56% respectively. Importantly, we reveal how the DFENet enhance inconspicuous but vital feature by applying gradient-weighted class activation maps. DFENet can locate object points accurately, which is applicable to other signal processing tasks, especially in health sensing.https://ieeexplore.ieee.org/document/9107210/iFRobject point localizationSFRA1D SE block |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jiping Li Liang Song Heye Zhang |
spellingShingle |
Jiping Li Liang Song Heye Zhang DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free Ratio IEEE Journal of Translational Engineering in Health and Medicine iFR object point localization SFRA 1D SE block |
author_facet |
Jiping Li Liang Song Heye Zhang |
author_sort |
Jiping Li |
title |
DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free Ratio |
title_short |
DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free Ratio |
title_full |
DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free Ratio |
title_fullStr |
DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free Ratio |
title_full_unstemmed |
DFENet: Deep Feature Enhancement Network for Accurate Calculation of Instantaneous Wave-Free Ratio |
title_sort |
dfenet: deep feature enhancement network for accurate calculation of instantaneous wave-free ratio |
publisher |
IEEE |
series |
IEEE Journal of Translational Engineering in Health and Medicine |
issn |
2168-2372 |
publishDate |
2020-01-01 |
description |
Accurate iFR calculation can provide important clinical information for intracoronary functional assessment without administration of adenosine, which needs to locate object points in the pressure waveforms: peak, the dichrotic notch and the pressure nadir at the end of diastole. We propose a DFENet that is capable of locating object points to calculate iFR accurately. We first design a SFRA into DFENet with the idea of DenseNet. To avoid overfitting when dealing with sparse signals, we set appropriate number of network layers, growth rate of dense blocks and compression rate of transition blocks in 1D DenseNet. Then, we introduce a feature enhancement mechanism named 1D SE block for enhancing inconspicuous but vital features from SFRA, which guides DFENet to focus on these important features via feature recalibration. Finally, we prove an effective interaction mode between SFRA and 1D SE block to locate object points accurately. Adequate experiments demonstrate that DFENet reaches a high accuracy of 94.22%, error of 5.6 on object point localization of 1D pressure waveforms that include 1457 samples from 100 subjects via a cross-validation of Leave-One-Out. Comparison experiment demonstrates that the accuracy of DFENet exceeds other state-of-the-art methods by 3.35%, and ablation experiment demonstrates that the accuracy of SFRA and cSE exceed the other variations by 6.63% and 2.56% respectively. Importantly, we reveal how the DFENet enhance inconspicuous but vital feature by applying gradient-weighted class activation maps. DFENet can locate object points accurately, which is applicable to other signal processing tasks, especially in health sensing. |
topic |
iFR object point localization SFRA 1D SE block |
url |
https://ieeexplore.ieee.org/document/9107210/ |
work_keys_str_mv |
AT jipingli dfenetdeepfeatureenhancementnetworkforaccuratecalculationofinstantaneouswavefreeratio AT liangsong dfenetdeepfeatureenhancementnetworkforaccuratecalculationofinstantaneouswavefreeratio AT heyezhang dfenetdeepfeatureenhancementnetworkforaccuratecalculationofinstantaneouswavefreeratio |
_version_ |
1724196645790285824 |