ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Precise segmentation of fetal head in ultrasound images using improved U-Net model

  • Vimala Nagabotu (Department of SCOPE, VIT-AP University) ;
  • Anupama Namburu (Department of SCOPE, VIT-AP University)
  • Received : 2023.02.17
  • Accepted : 2023.05.15
  • Published : 2024.06.20
Download PDF
⟨ Previous Next ⟩

Abstract

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

Keywords

References

  1. Q. Meng, J. Matthew, V. A. Zimmer, A. Gomez, D. F. A. Lloyd, D. Rueckert, and B. Kainz, Mutual information-based disentangled neural networks for classifying unseen categories in different domains: application to fetal ultrasound imaging, IEEE Trans. Med. Imaging 40 (2021), no. 2, 722-734, DOI 10.1109/TMI.2020.3035424.
  2. Q. Meng, M. Sinclair, V. Zimmer, B. Hou, M. Rajchl, N. Toussaint, O. Oktay, J. Schlemper, A. Gomez, J. Housden, J. Matthew, D. Rueckert, J. A. Schnabel, and B. Kainz, Weakly supervised estimation of shadow confidence maps in fetal ultrasound imaging, IEEE Trans. Med. Imaging 38 (2019), no. 12, 2755-2767, DOI 10.1109/TMI.2019.2913311.
  3. K. Shozu, M. Komatsu, A. Sakai, R. Komatsu, A. Dozen, H. Machino, S. Yasutomi, T. Arakaki, K. Asada, S. Kaneko, R. Matsuoka, A. Nakashima, A. Sekizawa, and R. Hamamoto, Model-agnostic method for thoracic wall segmentation in fetal ultrasound videos, Biomol. 10 (2020), no. 12, 1691, DOI 10.3390/biom10121691.
  4. F. A. Hermawati, H. Tjandrasa, and N. Suciati, Phase-based thresholding schemes for segmentation of fetal thigh cross-sectional region in ultrasound images, J. King Saud Univ. Comput. Informat. Sci. 34 (2022), no. 7, 4448-4460, DOI 10.1016/j.jksuci.2021.02.004.
  5. Z. Sobhaninia, S. Rafiei, A. Emami, N. Karimi, K. Najarian, S. Samavi, and S. M. R. Soroushmehr, Fetal ultrasound image segmentation for measuring biometric parameters using multitask deep learning, (Proceedings of the 41st Annual International Conference of the IEEE EMBC, Berlin, Germany), 2019, 6545-6548, DOI 10.1109/EMBC.2019.8856981.
  6. X. Yang, X. Wang, Y. Wang, H. Dou, S. Li, H. Wen, Y. Lin, P.-A. Heng, and D. Ni, Hybrid attention for automatic segmentation of whole fetal head in prenatal ultrasound volumes, Comput. Methods Programs Biomed. 194 (2020), 105519, DOI 10.1016/j.cmpb.2020.105519.
  7. M. Alzubaidi, M. Agus, U. Shah, M. Makhlouf, K. Alyafei, and M. Househ, Ensemble transfer learning for fetal head analysis: from segmentation to gestational age and weight prediction, Diagnostics 12 (2022), no. 9, 2229, DOI 10.3390/diagnostics12092229.
  8. J. Perez-Gonzalez, F. A. Cosio, J. C. Huegel, and V. MedinaBanuelos, Probabilistic learning coherent point drift for 3D ultrasound fetal head registration, Comput. Math. Methods Med. 2020 (2020), 4271519, DOI 10.1155/2020/4271519.
  9. M. Amiri, R. Brooks, and H. Rivaz, Fine-tuning U-Net for ultrasound image segmentation: different layers, different outcomes, IEEE Trans. Ultrason. Ferroelectr. Freq. Control 67 (2020), no. 12, 2510-2518, DOI 10.1109/TUFFC.2020.3015081.
  10. A. I. L. Namburete, W. Xie, M. Yaqub, A. Zisserman, and J. A. Noble, Fully-automated alignment of 3D fetal brain ultrasound to a canonical reference space using multi-task learning, Med. Image Anal. 46 (2018), 1-14, DOI 10.1016/j.media.2018.02.006.
  11. A. P. Santoso and R. Sigit, Health monitoring of fetal ultrasound image using active contour models, (Proceedings of the international seminar on application for Technology of Information and Communication [iSemantic], Semarang, Indonesia), 2017, pp. 192-197, DOI 10.1109/ISEMANTIC.2017.8251868.
  12. J. Perez-Gonzalez, F. Arambula-Cosio, M. Guzman, L. Camargo, B. Gutierrez, D. Mateus, N. Navab, and V. MedinaBanuelos, Spatial compounding of 3-D fetal brain ultrasound using probabilistic maps, Ultrasound Med. Biol. 44 (2018), no. 1, 278-291, DOI 10.1016/j.ultrasmedbio.2017.09.001.
  13. J. Torrents-Barrena, G. Piella, N. Masoller, E. Gratacos, E. Eixarch, M. Ceresa, and M. A. G. Ballester, ' Segmentation and classification in MRI and US fetal imaging: recent trends and future prospects, Med. Image Anal. 51 (2019), 61-88, DOI 10.1016/j.media.2018.10.003.
  14. H. Dou, D. Karimi, C. K. Rollins, C. M. Ortinau, L. Vasung, C. Velasco-Annis, A. Ouaalam, X. Yang, D. Ni, and A. Gholipour, A deep attentive convolutional neural network for automatic cortical plate segmentation in fetal MRI, IEEE Trans. Med. Imaging 40 (2021), no. 4, 1123-1133, DOI 10.1109/TMI.2020.3046579.
  15. L. Xu, M. Liu, J. Zhang, and Y. He, Convolutional-neural-network-based approach for segmentation of apical four-chamber view from fetal echocardiography, IEEE Access 8 (2020), 80437-80446, DOI 10.1109/ACCESS.2020.2984630.
  16. P. Li, H. Zhao, P. Liu, and F. Cao, Automated measurement network for accurate segmentation and parameter modification in fetal head ultrasound images, Med. Biol. Eng. Comput. 58 (2020), no. 11, 2879-2892, DOI 10.1007/s11517-020-02242-5.
  17. Y. Zeng, P.-H. Tsui, W. Wu, Z. Zhou, and S. Wu, Fetal ultrasound image segmentation for automatic head circumference biometry using deeply supervised attention-gated V-net, J. Digital Imaging 34 (2021), no. 1, 134-148, DOI 10.1007/s10278-020-00410-5.
  18. P. Sridar, A. Kumar, A. Quinton, R. Nanan, J. Kim, and R. Krishnakumar, Decision fusion-based fetal ultrasound image plane classification using convolutional neural networks, Ultrasound Med. Biol. 45 (2019), no. 5, 1259-1273, DOI 10.1016/j.ultrasmedbio.2018.11.016.
  19. X. P. Burgos-Artizzu, D. Coronado-Gutierrez, B. ValenzuelaAlcaraz, E. Bonet-Carne, E. Eixarch, F. Crispi, and E. Gratacos, Author correction: evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes, Sci. Rep. 12 (2022), 1950, DOI 10.1038/s41598-022-06173-z.
  20. H. N. Xie, N. Wang, M. He, L. H. Zhang, H. M. Cai, J. B. Xian, M. F. Lin, J. Zheng, and Y. Z. Yang, Using deep-learning algorithms to classify fetal brain ultrasound images as normal or abnormal, Ultrasound Obstet. Gynecol. 56 (2020), no. 4, 579-587, DOI 10.1002/uog.21967.
  21. Z. Lin, S. Li, D. Ni, Y. Liao, H. Wen, J. Du, S. Chen, T. Wang, and B. Lei, Multi-task learning for quality assessment of fetal head ultrasound images, Med. Image Anal. 58 (2019), 101548, DOI 10.1016/j.media.2019.101548.
  22. R. Qu, G. Xu, C. Ding, W. Jia, and M. Sun, Deep learning-based methodology for recognition of fetal brain standard scan planes in 2D ultrasound images, IEEE Access 8 (2020), 44443-44451, DOI 10.1109/ACCESS.2019.2950387.
  23. V. Rajinikanth, N. Dey, R. Kumar, J. Panneerselvam, and N. S. M. Raja, Fetal head periphery extraction from ultrasound image using Jaya algorithm and Chan-Vese segmentation, Proc. Comput. Sci. 152 (2019), 66-73, DOI 10.1016/j.procs.2019.05.028.
  24. Z. Sobhaninia, A. Emami, N. Karimi, and S. Samavi, Localization of fetal head in ultrasound images by multiscale view and deep neural networks, (Proceedings of the 25th international CSICC, Tehran, Iran), 2020, pp. 1-5, DOI 10.1109/CSICC49403.2020.9050094.
  25. D. Qiao and F. Zulkernine, Dilated squeeze-and-excitation UNet for fetal ultrasound image segmentation, (Proceedings of the IEEE conference on CIBCB, via del mar, Chile), 2020, pp. 1-7, DOI 10.1109/CIBCB48159.2020.9277667.
  26. V. A. Chenarlogh, M. G. Oghli, A. Shabanzadeh, N. Sirjani, A. Akhavan, I. Shiri, H. Arabi, M. S. Taheri, and M. K. Tarzamni, Fast and accurate U-Net model for fetal ultrasound image segmentation, Ultrason. Imaging 44 (2022), no. 1, 25-38, DOI 10.1177/01617346211069882.
  27. R. E. Pregitha, R. S. V. Kumar, and C. E. Selvakumar, Segmentation of ultrasound fetal image using spatial fuzzy C-mean clustering method, AIP Conf. Proc. 2519 (2022), no. 1, 050020, DOI 10.1063/5.0109780.
  28. E. L. Skeika, M. R. D. Luz, B. J. T. Fernandes, H. V. Siqueira, and M. L. S. C. De Andrade, Convolutional neural network to detect and measure fetal skull circumference in ultrasound imaging, IEEE Access 8 (2020), 191519-191529, DOI 10.1109/ACCESS.2020.3032376.
  29. L. Zhang, N. J. Dudley, T. Lambrou, N. Allinson, and X. Ye, Automatic image quality assessment and measurement of fetal head in two-dimensional ultrasound image, J. Med. Imaging 4 (2017), no. 2, 024001, DOI 10.1117/1.JMI.4.2.024001.
  30. J. Li, Y. Wang, B. Lei, J.-Z. Cheng, J. Qin, T. Wang, S. Li, and D. Ni, Automatic fetal head circumference measurement in ultrasound using random forest and fast ellipse fitting, IEEE J. Biomed. Health Inform 22 (2018), no. 1, 215-223, DOI 10.1109/JBHI.2017.2703890.
  31. H. Sahli, A. Zaafouri, A. B. Slama, R. Rachdi, and M. Sayadi, Analytic approach for fetal head biometric measurements based on log Gabor features, Iranian J. Sci. Technol. Trans. A: Sci. 43 (2019), no. 3, 1049-1057, DOI 10.1007/s40995-018-0523-y.
  32. J. Jang, Y. Park, B. Kim, S. M. Lee, J.-Y. Kwon, and J. K. Seo, Automatic estimation of fetal abdominal circumference from ultrasound images, IEEE J. Biomed. Health. Inform 22 (2018), no. 5, 1512-1520, DOI 10.1109/JBHI.2017.2776116.
  33. P. Kaur, G. Singh, and P. Kaur, An intelligent validation system for diagnostic and prognosis of ultrasound fetal growth analysis using neuro-fuzzy based on genetic algorithm, Egypt. Inf. J. 20 (2019), no. 1, 55-87, DOI 10.1016/j.eij.2018.10.002.
  34. T. L. A. van den Heuvel, D. de Bruijn, C. L. de Korte, and B. van Ginneken, Automated measurement of fetal head circumference using 2D ultrasound images, Plos One 13 (2018), no. 8, e0200412, DOI 10.1371/journal.pone.0200412.
  35. M. F. Safdar, S. S. Alkobaisi, and F. T. Zahra, A comparative analysis of data augmentation approaches for magnetic resonance imaging (MRI) scan images of brain tumor, Acta Inform. Med. 28 (2020), no. 1, 29-36, DOI 10.5455/aim.2020.28.29-36.
  36. R. Hao, K. Namdar, L. Liu, M. A. Haider, and F. Khalvati, A comprehensive study of data augmentation strategies for prostate cancer detection in diffusion-weighted MRI using convolutional neural networks, J. Digital Imaging 34 (2021), no. 4, 862-876, DOI 10.1007/s10278-021-00478-7.
  37. R. Verma, N. Kumar, A. Patil, N. C. Kurian, S. Rane, S. Graham, Q. D. Vu, M. Zwager, S. E. A. Raza, N. Rajpoot, X. Wu, H. Chen, Y. Huang, L. Wang, H. Jung, T. G. Brown, Y. Liu, S. Liu, S. A. F. Jahromi, A. A. Khani, E. Montahaei, M. S. Baghshah, H. Behroozi, P. Semkin, A. Rassadin, P. Dutande, R. Lodaya, U. Baid, B. Baheti, S. Talbar, A. Mahbod, R. Ecker, I. Ellinger, Z. Luo, B. Dong, Z. Xu, Y. Yao, S. Lv, M. Feng, K. Xu, H. Zunair, A. B. Hamza, S. Smiley, T.-K. Yin, Q.-R. Fang, S. Srivastava, D. Mahapatra, L. Trnavska, H. Zhang, P. L. Narayanan, J. Law, Y. Yuan, A. Tejomay, A. Mitkari, D. Koka, V. Ramachandra, L. Kini, and A. Sethi, MoNuSAC2020: a multi-organ nuclei segmentation and classification challenge, IEEE Trans. Med. Imaging 40 (2021), no. 12, 3413-3423, DOI 10.1109/TMI.2021.3085712.
  38. N. Siddique, S. Paheding, C. P. Elkin, and V. Devabhaktuni, U-Net and its variants for medical image segmentation: a review of theory and applications, IEEE Access 9 (2021), 82031-82057, DOI 10.1109/ACCESS.2021.3086020.
  39. G. Du, X. Cao, J. Liang, X. Chen, and Y. Zhan, Medical image segmentation based on U-Net: a review, J. Imaging Sci. Technol. 64 (2020), no. 2, 020508-020501, DOI 10.2352/J.ImagingSci.Technol.2020.64.2.020508.
  40. N. Ibtehaz and M. S. Rahman, MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation, Neural Netw. 121 (2020), 74-87, DOI j.neunet.2019.08.025.  https://doi.org/10.1016/j.neunet.2019.08.025