Detecting Vascular Bifurcation in IVOCT Images Using Convolutional Neural Networks With Transfer Learning
Carregando...
Citações na Scopus
17
Tipo de produção
article
Data de publicação
2019
Título da Revista
ISSN da Revista
Título do Volume
Editora
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Autores
MIYAGAWA, Makoto
COSTA, Marly Guimaraes Fernandes
COSTA, Joao Pedro Guimaraes Fernandes
COSTA FILHO, Cicero Ferreira Fernandes
Citação
IEEE ACCESS, v.7, p.66167-66175, 2019
Resumo
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.
Palavras-chave
Cardiovascular diseases, intravascular optical coherence tomography, bifurcation detection, convolutional neural networks
Referências
- Alberti M, 2012, IEEE T BIO-MED ENG, V59, P1022, DOI 10.1109/TBME.2011.2181372
- Balocco S, 2018, LECT NOTES COMPUT SC, V11047, P34, DOI 10.1007/978-3-030-01132-1_4
- Cao YH, 2017, COMPUT MATH METHOD M, DOI 10.1155/2017/4710305
- Dijkstra E. W., 1959, NUMER MATH, V1, P269, DOI 10.1007/BF01386390
- Esteva A, 2017, NATURE, V542, P115, DOI 10.1038/nature21056
- Fujii K, 2015, JACC-CARDIOVASC IMAG, V8, P451, DOI 10.1016/j.jcmg.2014.10.015
- Gessert N, 2019, IEEE T MED IMAGING, V38, P426, DOI 10.1109/TMI.2018.2865659
- Girish GN, 2019, IEEE J BIOMED HEALTH, V23, P296, DOI 10.1109/JBHI.2018.2810379
- Gulshan V, 2016, JAMA-J AM MED ASSOC, V316, P2402, DOI 10.1001/jama.2016.17216
- HANLEY JA, 1982, RADIOLOGY, V143, P29, DOI 10.1148/radiology.143.1.7063747
- He KM, 2016, PROC CVPR IEEE, P770, DOI 10.1109/CVPR.2016.90
- Kim HM, 2014, IEEE ENG MED BIO, P178, DOI 10.1109/EMBC.2014.6943558
- Macedo MMG, 2015, COMPUT MED IMAG GRAP, V46, P237, DOI 10.1016/j.compmedimag.2015.09.004
- Mendis S, 2011, GLOBAL ATLAS CARDIOV
- Miyagawa M, 2018, Conf Proc IEEE Eng Med Biol Soc, V2018, P600, DOI 10.1109/EMBC.2018.8512299
- Morbiducci U, 2016, THROMB HAEMOSTASIS, V115, P484, DOI 10.1160/TH15-07-0597
- Pan SJ, 2010, IEEE T KNOWL DATA EN, V22, P1345, DOI 10.1109/TKDE.2009.191
- Papadogiorgaki M, 2008, ULTRASOUND MED BIOL, V34, P1482, DOI 10.1016/j.ultrasmedbio.2008.01.022
- Porto C. D. N., 2017, INT SOC OPT PHOTON, V3
- Rathod Krishnaraj S, 2015, Interv Cardiol, V10, P8, DOI 10.15420/icr.2015.10.1.8
- Roleder T, 2015, POSTEP KARDIOL INTER, V11, P74, DOI 10.5114/pwki.2015.52278
- Ronneberger O, 2015, LECT NOTES COMPUT SC, V9351, P234, DOI 10.1007/978-3-319-24574-4_28
- Shin HC, 2016, IEEE T MED IMAGING, V35, P1285, DOI 10.1109/TMI.2016.2528162
- SIMONYAN K, 2014, 14091556 ARXIV, V1409, DOI 10.1016/J.INFSOF.2008.09.005
- Spanos K, 2017, ANGIOLOGY, V68, P757, DOI 10.1177/0003319716678741
- Srivastava N, 2014, J MACH LEARN RES, V15, P1929
- Szegedy C, 2015, PROC CVPR IEEE, P1, DOI 10.1109/CVPR.2015.7298594
- Tajbakhsh N, 2016, IEEE T MED IMAGING, V35, P1299, DOI 10.1109/TMI.2016.2535302
- Ughi GJ, 2012, BIOMED OPT EXPRESS, V3
- Wang AC, 2014, BIOMED OPT EXPRESS, V5, P3160, DOI 10.1364/BOE.5.003160
- WHO, 2016, HEARTS TECHN PACK CA
- Xu MD, 2017, P ANN INT IEEE EMBS, P1501, DOI 10.1109/EMBC.2017.8037120
- Yong YL, 2017, J BIOMED OPT, V22, DOI 10.1117/1.JBO.22.12.126005
- ZARINS CK, 1983, CIRC RES, V53, P502, DOI 10.1161/01.RES.53.4.502