Utilização de Redes Neurais Completamente Convolucionais para identificação e medição de crânios fetais
Resumo
A ultrassonografia é uma técnica de diagnóstico por imagem não invasiva e não radioativa frequentemente utilizada no acompanhamento do desenvolvimento fetal durante a gestação. A avaliação precisa é importante para a análise do crescimento do feto, diagnóstico de malformações e de possíveis doenças congênitas, garantindo assim o bem-estar da mãe e do feto durante a gravidez. Porém, para uma medição precisa de estruturas anatômicas do feto é necessário conhecimento especializado do médico obstetra. Além de ser um processo tedioso e demorado, a extração do contorno é influenciada pela sua experiência. Neste sentido, o objetivo do trabalho é propor a adaptação da rede neural completamente convolucional V-Net para segmentação de crânios fetais presentes em imagens de ultrassonografia bidimensional, além da construção de um algoritmo para o cálculo da circunferência dos mesmos. Resultados preliminares sugerem que a metodologia pode ser utilizada de forma automática como ferramenta auxiliar no acompanhamento do desenvolvimento fetal.
Palavras-chave:
Redes Neurais Completamente Convolucionais, Segmentação, Crânios Fetais
Referências
RUEDA, S.; et al. Evaluation and comparison of current fetal ultrasound image segmentation methods for biometric measurements: a grand challenge. IEEE Transactions on medical imaging, v. 33, n. 4, p. 797-813, 2013. https://doi.org/10.1109/TMI.2013.2276943
WU, L.; et al. FUIQA: Fetal ultrasound image quality assessment with deep convolutional networks. IEEE transactions on cybernetics, v. 47, n. 5, p. 1336-1349, 2017. https://doi.org/10.1109/TCYB.2017.2671898
AL-KARMI, A. M.; et al. Calcium and the effects of ultrasound on frog skin. Ultrasound in medicine & biology, v. 20, n. 1, p. 73-81, 1994. https://doi.org/10.1016/0301-5629(94)90019-1
ZAYED, N. M.;et al. Wavelet segmentation for fetal ultrasound images. In: Proceedings of the 44th IEEE 2001 Midwest Symposium on Circuits and Systems. MWSCAS 2001 (Cat. No. 01CH37257). IEEE, 2001. p. 501-504. https://doi.org/10.1109/MWSCAS.2001.986220
CARNEIRO, G.; et al. Detection and measurement of fetal anatomies from ultrasound images using a constrained probabilistic boosting tree. IEEE transactions on medical imaging, v. 27, n. 9, p. 1342-1355, 2008. https://doi.org/10.1109/TMI.2008.928917
JARDIM, S. MGVB; FIGUEIREDO, M. A. Segmentation of fetal ultrasound images. Ultrasound in medicine & biology, v. 31, n. 2, p. 243-250, 2005. https://doi.org/10.1016/j.ultrasmedbio.2004.11.003
LU, W.; TAN, J.; FLOYD, R. Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform. Ultrasound in medicine & biology, v. 31, n. 7, p. 929-936, 2005. https://doi.org/10.1016/j.ultrasmedbio.2005.04.002
GIRSHICK, R.; et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. p. 580-587. https://doi.org/10.1109/CVPR.2014.81
REN, S.; et al. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems. 2015. p. 91-99. https://doi.org/10.1109/TPAMI.2016.2577031
SZEGEDY, C.; et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 1-9. https://doi.org/10.1109/CVPR.2015.7298594
LONG, J.; SHELHAMER, E.; DARRELL, T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 3431-3440. https://doi.org/10.1109/CVPR.2015.7298965
LI, Y.; et al. Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers. In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2017. p. 1485-1488. https://doi.org/10.1109/CVPR.2015.7298965
SUNDARESAN, V.; et al. Automated characterization of the fetal heart in ultrasound images using fully convolutional neural networks. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). IEEE, 2017. p. 671-674. https://doi.org/10.1109/ISBI.2017.7950609
SINCLAIR, M.; et al. Human-level performance on automatic head biometrics in fetal ultrasound using fully convolutional neural networks. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2018. p. 714-717. https://doi.org/10.1109/EMBC.2018.8512278
MILLETARI, F.; NAVAB, N.; AHMADI, S. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). IEEE, 2016. p. 565-571. https://doi.org/10.1109/3DV.2016.79
VAN DEN HEUVEL, Thomas LA et al. Automated measurement of fetal head circumference using 2D ultrasound images. PloS one, v. 13, n. 8, p. e0200412, 2018. https://doi.org/10.5281/zenodo.1322001
VESAL, S.; RAVIKUMAR, N.; MAIER, A. A 2D dilated residual U-Net for multi-organ segmentation in thoracic CT. arXiv preprint arXiv:1905.07710, 2019.
WU, L.; et al. FUIQA: Fetal ultrasound image quality assessment with deep convolutional networks. IEEE transactions on cybernetics, v. 47, n. 5, p. 1336-1349, 2017. https://doi.org/10.1109/TCYB.2017.2671898
AL-KARMI, A. M.; et al. Calcium and the effects of ultrasound on frog skin. Ultrasound in medicine & biology, v. 20, n. 1, p. 73-81, 1994. https://doi.org/10.1016/0301-5629(94)90019-1
ZAYED, N. M.;et al. Wavelet segmentation for fetal ultrasound images. In: Proceedings of the 44th IEEE 2001 Midwest Symposium on Circuits and Systems. MWSCAS 2001 (Cat. No. 01CH37257). IEEE, 2001. p. 501-504. https://doi.org/10.1109/MWSCAS.2001.986220
CARNEIRO, G.; et al. Detection and measurement of fetal anatomies from ultrasound images using a constrained probabilistic boosting tree. IEEE transactions on medical imaging, v. 27, n. 9, p. 1342-1355, 2008. https://doi.org/10.1109/TMI.2008.928917
JARDIM, S. MGVB; FIGUEIREDO, M. A. Segmentation of fetal ultrasound images. Ultrasound in medicine & biology, v. 31, n. 2, p. 243-250, 2005. https://doi.org/10.1016/j.ultrasmedbio.2004.11.003
LU, W.; TAN, J.; FLOYD, R. Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform. Ultrasound in medicine & biology, v. 31, n. 7, p. 929-936, 2005. https://doi.org/10.1016/j.ultrasmedbio.2005.04.002
GIRSHICK, R.; et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. p. 580-587. https://doi.org/10.1109/CVPR.2014.81
REN, S.; et al. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems. 2015. p. 91-99. https://doi.org/10.1109/TPAMI.2016.2577031
SZEGEDY, C.; et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 1-9. https://doi.org/10.1109/CVPR.2015.7298594
LONG, J.; SHELHAMER, E.; DARRELL, T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 3431-3440. https://doi.org/10.1109/CVPR.2015.7298965
LI, Y.; et al. Automatic fetal body and amniotic fluid segmentation from fetal ultrasound images by encoder-decoder network with inner layers. In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2017. p. 1485-1488. https://doi.org/10.1109/CVPR.2015.7298965
SUNDARESAN, V.; et al. Automated characterization of the fetal heart in ultrasound images using fully convolutional neural networks. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). IEEE, 2017. p. 671-674. https://doi.org/10.1109/ISBI.2017.7950609
SINCLAIR, M.; et al. Human-level performance on automatic head biometrics in fetal ultrasound using fully convolutional neural networks. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2018. p. 714-717. https://doi.org/10.1109/EMBC.2018.8512278
MILLETARI, F.; NAVAB, N.; AHMADI, S. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). IEEE, 2016. p. 565-571. https://doi.org/10.1109/3DV.2016.79
VAN DEN HEUVEL, Thomas LA et al. Automated measurement of fetal head circumference using 2D ultrasound images. PloS one, v. 13, n. 8, p. e0200412, 2018. https://doi.org/10.5281/zenodo.1322001
VESAL, S.; RAVIKUMAR, N.; MAIER, A. A 2D dilated residual U-Net for multi-organ segmentation in thoracic CT. arXiv preprint arXiv:1905.07710, 2019.
Publicado
28/10/2019
Como Citar
SKEIKA, Everton Leonardo; ANDRADE, Mauren Louise Sguario Coelho de; SIQUEIRA, Hugo.
Utilização de Redes Neurais Completamente Convolucionais para identificação e medição de crânios fetais. In: WORKSHOP DE TRABALHOS EM ANDAMENTO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 32. , 2019, Rio de Janeiro.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 180-183.
DOI: https://doi.org/10.5753/sibgrapi.est.2019.8324.
