×

Probabilistic learning coherent point drift for 3D ultrasound fetal head registration. (English) Zbl 1431.92096

Summary: Quantification of brain growth is crucial for the assessment of fetal well being, for which ultrasound (US) images are the chosen clinical modality. However, they present artefacts, such as acoustic occlusion, especially after the \(18^{\text{th}}\) gestational week, when cranial calcification appears. Fetal US volume registration is useful in one or all of the following cases: to monitor the evolution of fetometry indicators, to segment different structures using a fetal brain atlas, and to align and combine multiple fetal brain acquisitions. This paper presents a new approach for automatic registration of real 3D US fetal brain volumes, volumes that contain a considerable degree of occlusion artefacts, noise, and missing data. To achieve this, a novel variant of the coherent point drift method is proposed. This work employs supervised learning to segment and conform a point cloud automatically and to estimate their subsequent weight factors. These factors are obtained by a random forest-based classification and are used to appropriately assign nonuniform membership probability values of a Gaussian mixture model. These characteristics allow for the automatic registration of 3D US fetal brain volumes with occlusions and multiplicative noise, without needing an initial point cloud. Compared to other intensity and geometry-based algorithms, the proposed method achieves an error reduction of 7.4% to 60.7%, with a target registration error of only \(6.38 \pm 3.24\) mm. This makes the herein proposed approach highly suitable for 3D automatic registration of fetal head US volumes, an approach which can be useful to monitor fetal growth, segment several brain structures, or even compound multiple acquisitions taken from different projections.

MSC:

92C55 Biomedical imaging and signal processing
92C20 Neural biology

Software:

SIFT
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Timor, I. E.; Monteagudo, A.; Cohen, H. L., Neuroecografia prenatal y neonatal, 1 (2004), Mexico City, Mexico: MARBAN, Mexico City, Mexico
[2] International Society of Ultrasound in Obstetrics and Gynecology, Sonographic examination of the fetal central nervous system: guidelines for performing the “basic examination” and the “fetal neurosonogram”, Ultrasound in Obstetrics & Gynecology, 29, 1, 109-116 (2007) · doi:10.1002/uog.3909
[3] Jardim, S. M. G. V. B.; Figueiredo, M. A. T., Segmentation of fetal ultrasound images, Ultrasound in Medicine & Biology, 31, 2, 243-250 (2005) · doi:10.1016/j.ultrasmedbio.2004.11.003
[4] Perez-Gonzalez, J.; Arambula-Cosío, F.; Guzman, M., Spatial compounding of 3-D fetal brain ultrasound using probabilistic maps, Ultrasound in Medicine & Biology, 44, 1, 278-291 (2018) · doi:10.1016/j.ultrasmedbio.2017.09.001
[5] Sotiras, A.; Davatzikos, C.; Paragios, N., Deformable medical image registration: a survey, IEEE Transactions on Medical Imaging, 32, 7, 1153-1190 (2013) · doi:10.1109/tmi.2013.2265603
[6] Maes, F.; Vandermeulen, D.; Suetens, P., Medical image registration using mutual information, Proceedings of the IEEE, 91, 10, 1699-1722 (October 2003) · doi:10.1109/jproc.2003.817864
[7] Buzug, T.; Weese, J., Voxel-based similarity measures for medical image registration in radiological diagnosis and image guided surgery, Journal of Computing and Information Technology, 6, 2, 165-179 (1998)
[8] Maes, F.; Collignon, A.; Vandermeulen, D.; Marchal, G.; Suetens, P., Multimodality image registration by maximization of mutual information, IEEE Transactions on Medical Imaging, 16, 2, 187-198 (April 1997) · doi:10.1109/42.563664
[9] Krücker, J. F.; Meyer, C. R.; LeCarpentier, G. L.; Fowlkes, J. B.; Carson, P. L., 3D Spatial compounding of ultrasound images using image-based nonrigid registration, Ultrasound in Medicine & Biology, 26, 9, 1475-1488 (2000) · doi:10.1016/s0301-5629(00)00286-6
[10] Maiseli, B.; Gu, Y.; Gao, H., Recent developments and trends in point set registration methods, Journal of Visual Communication and Image Representation, 46, 95-106 (2017) · doi:10.1016/j.jvcir.2017.03.012
[11] Savva, A. D.; Economopoulos, T. L.; Matsopoulos, G. K., Geometry-based vs. intensity-based medical image registration: a comparative study on 3D CT data, Computers in Biology and Medicine, 69, 120-133 (2016) · doi:10.1016/j.compbiomed.2015.12.013
[12] Besl, P. J.; McKay, N. D., A method for registration of 3-D shapes, IEEE Transactions on Pattern Analysis and Machine Intelligence, 14, 2, 239-256 (1992) · doi:10.1109/34.121791
[13] Zhang, Z., Iterative point matching for registration of free-form curves and surfaces, International Journal of Computer Vision, 13, 2, 119-152 (1994) · doi:10.1007/bf01427149
[14] Fischler, M. A.; Bolles, R. C., Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, 24, 6, 381-395 (1981) · doi:10.1145/358669.358692
[15] Lowe, D. G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60, 2, 91-110 (2004) · doi:10.1023/b:visi.0000029664.99615.94
[16] Myronenko, A.; Song, X., Point set registration: coherent point drift, IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 12, 2262-2275 (2010) · doi:10.1109/tpami.2010.46
[17] Wang, P.; Wang, P.; Qu, Z.; Gao, Y.; Shen, Z., A refined coherent point drift (CPD) algorithm for point set registration, Science China Information Sciences, 54, 12, 2639-2646 (2011) · doi:10.1007/s11432-011-4465-7
[18] Gao, Y.; Ma, J.; Zhao, J.; Tian, J.; Zhang, D., A robust and outlier-adaptive method for non-rigid point registration, Pattern Analysis and Applications, 17, 2, 379-388 (2014) · Zbl 1328.62395 · doi:10.1007/s10044-013-0324-z
[19] Liu, S.; Sun, G.; Niu, Z.; Li, N.; Chen, Z., Robust rigid coherent point drift algorithm based on outlier suppression and its application in image matching, Journal of Applied Remote Sensing, 9, 1 (2015) · doi:10.1117/1.jrs.9.095085
[20] de Sousa, S.; Kropatsch, W. G., Graph-based point drift: graph centrality on the registration of point-sets, Pattern Recognition, 48, 2, 368-379 (2015) · Zbl 1373.68363 · doi:10.1016/j.patcog.2014.06.011
[21] Zhang, H.; Ni, W.; Yan, W.; Wu, J.; Li, S., Robust sar image registration based on edge matching and refined coherent point drift, IEEE Geoscience and Remote Sensing Letters, 12, 10, 2115-2119 (2015) · doi:10.1109/lgrs.2015.2451396
[22] Lu, M.; Zhao, J.; Guo, Y.; Ma, Y., Accelerated coherent point drift for automatic three-dimensional point cloud registration, IEEE Geoscience and Remote Sensing Letters, 13, 2, 162-166 (2016) · doi:10.1109/lgrs.2015.2504268
[23] Zhang, P.; Qiao, Y.; Wang, S.; Yang, J.; Zhu, Y., A robust coherent point drift approach based on rotation invariant shape context, Neurocomputing, 219, 455-473 (2017) · doi:10.1016/j.neucom.2016.09.058
[24] Golyanik, V.; Taetz, B.; Reis, G.; Stricker, D., Extended coherent point drift algorithm with correspondence priors and optimal subsampling, Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
[25] Peng, L.; Li, G.; Xiao, M.; Xie, L., Robust cpd algorithm for non-rigid point set registration based on structure information, PLoS One, 11, 2 (2016) · doi:10.1371/journal.pone.0148483
[26] Saval-Calvo, M.; Azorin-Lopez, J.; Fuster-Guillo, A.; Villena-Martinez, V.; Fisher, R. B., 3D non-rigid registration using color: color coherent point drift, Computer Vision and Image Understanding, 169, 119-135 (2018) · doi:10.1016/j.cviu.2018.01.008
[27] Cen, F.; Jiang, Y.; Zhang, Z.; Tsui, H. T., Shape and pixel-property based automatic affine registration between ultrasound images of different fetal head, Lecture Notes in Computer Science, 261-269 (2004), Berlin, Germany: Springer, Berlin, Germany
[28] Cen, F.; Jiang, Y.; Zhang, Z.; Tsui, H. T.; Lau, T. K.; Xie, H., Robust registration of 3-D ultrasound images based on Gabor filter and mean-shift method, Lecture Notes in Computer Science, 304-316 (2004), Berlin, Germany: Springer, Berlin, Germany
[29] Fathima, S.; Rueda, S.; Aris, P.; Noble, A., A novel local-phase method of automatic atlas construction in fetal ultrasound, Proceedings of the Medical Imaging 2011: Image Processing
[30] Chen, H.-C.; Tsai, P.-Y.; Huang, H.-H., Registration-based segmentation of three-dimensional ultrasound images for quantitative measurement of fetal craniofacial structure, Ultrasound in Medicine & Biology, 38, 5, 811-823 (2012) · doi:10.1016/j.ultrasmedbio.2012.01.025
[31] Kuklisova-Murgasova, M.; Cifor, A.; Napolitano, R., Registration of 3d fetal neurosonography and MRI, Medical Image Analysis, 17, 8, 1137-1150 (2013) · doi:10.1016/j.media.2013.07.004
[32] Che, C.; Mathai, T. S.; Galeotti, J., Ultrasound registration: a review, Methods, 115, 128-143 (2017) · doi:10.1016/j.ymeth.2016.12.006
[33] Perez, J.; Arambula, F.; Guzman, M., Ultrasound fetal brain registration using weighted coherent point drift, Proceedings of the 12th International Symposium on Medical Information Processing and Analysis SPIE 10160 · doi:10.1117/12.2255776
[34] Karamalis, A.; Wein, W.; Klein, T.; Navab, N., Ultrasound confidence maps using random walks, Medical Image Analysis, 16, 6, 1101-1112 (2012) · doi:10.1016/j.media.2012.07.005
[35] Criminisi, A.; Shotton, J., Decision Forests for Computer Vision and Medical Image Analysis (2013), Berlin, Germany: Springer Publishing Company, Incorporated, Berlin, Germany
[36] Gonzalez, R., Digital Image Processing (2002), Upper Saddle River, NJ, USA: Prentice-Hall, Inc., Upper Saddle River, NJ, USA
[37] Canny, J., A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8, 6, 679-698 (1986) · doi:10.1109/tpami.1986.4767851
[38] Fang, Q.; Boas, D. A., Tetrahedral mesh generation from volumetric binary and grayscale images, Proceedings of the 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
[39] Prados, F.; Ashburner, J.; Blaiotta, C., Spinal cord grey matter segmentation challenge, NeuroImage, 152, 312-329 (2017) · doi:10.1016/j.neuroimage.2017.03.010
[40] Fitzpatrick, J., Fiducial registration error and target registration error are uncorrelated, Proceedings of the Medical Imaging 2009: Visualization, Image-Guided Procedures, and Modeling SPIE 7261
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.