Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning
Optical coherence tomography (OCT) technology enables experts to analyze coronary lesions from high-resolution intravascular images. Studies have shown a relationship between vascular bifurcation and a higher occurrence of wall thickening and lesions in these areas. Some level of automation could be...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8718587/ |
| _version_ | 1818737292585467904 |
|---|---|
| author | Makoto Miyagawa Marly Guimaraes Fernandes Costa Marco Antonio Gutierrez Joao Pedro Guimaraes Fernandes Costa Cicero Ferreira Fernandes Costa Filho |
| author_facet | Makoto Miyagawa Marly Guimaraes Fernandes Costa Marco Antonio Gutierrez Joao Pedro Guimaraes Fernandes Costa Cicero Ferreira Fernandes Costa Filho |
| author_sort | Makoto Miyagawa |
| collection | DOAJ |
| description | Optical coherence tomography (OCT) technology enables experts to analyze coronary lesions from high-resolution intravascular images. Studies have shown a relationship between vascular bifurcation and a higher occurrence of wall thickening and lesions in these areas. Some level of automation could benefit experts since the visual analysis of pullback frames is a laborious and time-consuming task. Although convolutional neural networks (CNNs) have shown promising results in classifying medical images, in this paper, we found no studies using CNNs in IVOCT images to classify the vascular bifurcation. In this paper, we evaluated four different CNN architectures in the bifurcation classification task trained with the IVOCT images from nine pullbacks from nine different patients. We used data augmentation to balance the dataset, due to the small number of bifurcation-labeled frames, and also applied transfer learning methods to incorporate the knowledge from a lumen segmentation task into some of the evaluated networks. Our classification outperforms other works in this literature, presenting AUC = 99.72%, obtained by a CNN with transferred knowledge. |
| first_indexed | 2024-12-18T00:50:44Z |
| format | Article |
| id | doaj.art-28a99d185c464abfb98d94ee1fd51d83 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:50:44Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-28a99d185c464abfb98d94ee1fd51d832022-12-21T21:26:41ZengIEEEIEEE Access2169-35362019-01-017661676617510.1109/ACCESS.2019.29180178718587Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer LearningMakoto Miyagawa0Marly Guimaraes Fernandes Costa1Marco Antonio Gutierrez2Joao Pedro Guimaraes Fernandes Costa3Cicero Ferreira Fernandes Costa Filho4https://orcid.org/0000-0003-3325-5715Eldorado Research Institute, Manaus, BrazilFederal University of Amazonas, Manaus, BrazilHeart Institute, University of São Paulo, São Paulo, BrazilFederal University of Amazonas, Manaus, BrazilFederal University of Amazonas, Manaus, BrazilOptical coherence tomography (OCT) technology enables experts to analyze coronary lesions from high-resolution intravascular images. Studies have shown a relationship between vascular bifurcation and a higher occurrence of wall thickening and lesions in these areas. Some level of automation could benefit experts since the visual analysis of pullback frames is a laborious and time-consuming task. Although convolutional neural networks (CNNs) have shown promising results in classifying medical images, in this paper, we found no studies using CNNs in IVOCT images to classify the vascular bifurcation. In this paper, we evaluated four different CNN architectures in the bifurcation classification task trained with the IVOCT images from nine pullbacks from nine different patients. We used data augmentation to balance the dataset, due to the small number of bifurcation-labeled frames, and also applied transfer learning methods to incorporate the knowledge from a lumen segmentation task into some of the evaluated networks. Our classification outperforms other works in this literature, presenting AUC = 99.72%, obtained by a CNN with transferred knowledge.https://ieeexplore.ieee.org/document/8718587/Cardiovascular diseasesintravascular optical coherence tomographybifurcation detectionconvolutional neural networks |
| spellingShingle | Makoto Miyagawa Marly Guimaraes Fernandes Costa Marco Antonio Gutierrez Joao Pedro Guimaraes Fernandes Costa Cicero Ferreira Fernandes Costa Filho Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning IEEE Access Cardiovascular diseases intravascular optical coherence tomography bifurcation detection convolutional neural networks |
| title | Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning |
| title_full | Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning |
| title_fullStr | Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning |
| title_full_unstemmed | Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning |
| title_short | Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning |
| title_sort | detecting vascular bifurcation in ivoct images using convolutional neural networks with transfer learning |
| topic | Cardiovascular diseases intravascular optical coherence tomography bifurcation detection convolutional neural networks |
| url | https://ieeexplore.ieee.org/document/8718587/ |
| work_keys_str_mv | AT makotomiyagawa detectingvascularbifurcationinivoctimagesusingconvolutionalneuralnetworkswithtransferlearning AT marlyguimaraesfernandescosta detectingvascularbifurcationinivoctimagesusingconvolutionalneuralnetworkswithtransferlearning AT marcoantoniogutierrez detectingvascularbifurcationinivoctimagesusingconvolutionalneuralnetworkswithtransferlearning AT joaopedroguimaraesfernandescosta detectingvascularbifurcationinivoctimagesusingconvolutionalneuralnetworkswithtransferlearning AT ciceroferreirafernandescostafilho detectingvascularbifurcationinivoctimagesusingconvolutionalneuralnetworkswithtransferlearning |