Automatic linear measurements of the fetal brain on MRI with deep neural networks.
Deep learning
Fetal brain MRI analysis
Fetal brain development
Fetal brain linear measurements
Journal
International journal of computer assisted radiology and surgery
ISSN: 1861-6429
Titre abrégé: Int J Comput Assist Radiol Surg
Pays: Germany
ID NLM: 101499225
Informations de publication
Date de publication:
Sep 2021
Sep 2021
Historique:
received:
12
01
2021
accepted:
17
06
2021
pubmed:
30
6
2021
medline:
20
8
2021
entrez:
29
6
2021
Statut:
ppublish
Résumé
Timely, accurate and reliable assessment of fetal brain development is essential to reduce short and long-term risks to fetus and mother. Fetal MRI is increasingly used for fetal brain assessment. Three key biometric linear measurements important for fetal brain evaluation are cerebral biparietal diameter (CBD), bone biparietal diameter (BBD), and trans-cerebellum diameter (TCD), obtained manually by expert radiologists on reference slices, which is time consuming and prone to human error. The aim of this study was to develop a fully automatic method computing the CBD, BBD and TCD measurements from fetal brain MRI. The input is fetal brain MRI volumes which may include the fetal body and the mother's abdomen. The outputs are the measurement values and reference slices on which the measurements were computed. The method, which follows the manual measurements principle, consists of five stages: (1) computation of a region of interest that includes the fetal brain with an anisotropic 3D U-Net classifier; (2) reference slice selection with a convolutional neural network; (3) slice-wise fetal brain structures segmentation with a multi-class U-Net classifier; (4) computation of the fetal brain midsagittal line and fetal brain orientation, and; (5) computation of the measurements. Experimental results on 214 volumes for CBD, BBD and TCD measurements yielded a mean [Formula: see text] difference of 1.55 mm, 1.45 mm and 1.23 mm, respectively, and a Bland-Altman 95% confidence interval ([Formula: see text] of 3.92 mm, 3.98 mm and 2.25 mm, respectively. These results are similar to the manual inter-observer variability, and are consistent across gestational ages and brain conditions. The proposed automatic method for computing biometric linear measurements of the fetal brain from MR imaging achieves human-level performance. It has the potential of being a useful method for the assessment of fetal brain biometry in normal and pathological cases, and of improving routine clinical practice.
Identifiants
pubmed: 34185253
doi: 10.1007/s11548-021-02436-8
pii: 10.1007/s11548-021-02436-8
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1481-1492Subventions
Organisme : Israel Innovation Authority, Kamin
ID : 63418
Informations de copyright
© 2021. CARS.
Références
Kyriakopoulou V, Vatansever D, Davidson A, Patkee P, Elkommos S, Chew A, Martinez-Biarge M, Hagberg B, Damodaram M, Allsop J (2017) Normative biometry of the fetal brain using magnetic resonance imaging. Brain Struct Funct 222(5):2295–2307
doi: 10.1007/s00429-016-1342-6
Tilea B, Alberti C, Adamsbaum C, Armoogum P, Oury J, Cabrol D, Sebag G, Kalifa G, Garel C (2009) Cerebral biometry in fetal magnetic resonance imaging: new reference data. Ultrasound Obstet Gynecol 33(2):173–181
doi: 10.1002/uog.6276
Prayer D, Malinger G, Brugger P, Cassady C, De Catte L, De Keersmaecker B, Fernandes G, Glanc P, Gonçalves L, Gruber G (2017) ISUOG Practice Guidelines: performance of fetal magnetic resonance imaging. Ultrasound Obstet Gynecol 49(5):671–680
doi: 10.1002/uog.17412
Garel C, Garel C (2004) MRI of the Fetal Brain. Springer
doi: 10.1007/978-3-642-18747-6
Joskowicz L, Cohen D, Caplan N, Sosna J (2019) Inter-observer variability of manual contour delineation of structures in CT. Eur Radiol 29(3):1391–1399
doi: 10.1007/s00330-018-5695-5
Warrander LK, Ingram E, Heazell AE, Johnstone ED (2020) Evaluating the accuracy and precision of sonographic fetal weight estimation models in extremely early-onset fetal growth restriction. Acta Obstet Gynecol Scand 99(3):364–373
doi: 10.1111/aogs.13745
Torrents-Barrena J, Piella G, Masoller N, Gratacós E, Eixarch E, Ceresa M, Ballester MÁG (2019) Segmentation and classification in MRI and US fetal imaging: recent trends and future prospects. Med Image Anal 51:61–88
doi: 10.1016/j.media.2018.10.003
Dudovitch G, Link-Sourani D, Sira LB, Miller E, Bashat DB, Joskowicz L (2020) Deep learning automatic fetal structures segmentation in MRI scans with few annotated datasets. In: Proc. int. conf. on medical image computing and computer-assisted intervention. Springer, pp 365–374
Baumgartner CF, Kamnitsas K, Matthew J, Fletcher TP, Smith S, Koch LM, Kainz B, Rueckert D (2017) SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans Med Imaging 36(11):2204–2215
doi: 10.1109/TMI.2017.2712367
Pallenberg R, Fleitmann M, Soika K, Stroth AM, Gerlach J, Fürschke A, Barkhausen J, Bischof A, Handels H (2020) Automatic quality measurement of aortic contrast-enhanced CT angiographies for patient-specific dose optimization. Int J Comput Assist Radiol Surg 15(10):1611–1617
doi: 10.1007/s11548-020-02238-4
Li Y, Khanal B, Hou B, Alansary A, Cerrolaza JJ, Sinclair M, Matthew J, Gupta C, Knight C, Kainz B (2018) Standard plane detection in 3d fetal ultrasound using an iterative transformation network. In: Proc. int. conf. on medical image computing and computer-assisted intervention. Springer, pp 392–400
Ryou H, Yaqub M, Cavallaro A, Papageorghiou AT, Noble JA (2019) Automated 3D ultrasound image analysis for first trimester assessment of fetal health. Phys Med Biol 64(18):185010
doi: 10.1088/1361-6560/ab3ad1
Despotović I, Goossens B, Philips W (2015) MRI segmentation of the human brain: challenges, methods, and applications. Comput Math Methods Med
Fischl B (2012) FreeSurfer. Neuroimage 62(2):774–781
doi: 10.1016/j.neuroimage.2012.01.021
Gholipour A, Rollins CK, Velasco-Annis C, Ouaalam A, Akhondi-Asl A, Afacan O, Ortinau CM, Clancy S, Limperopoulos C, Yang E (2017) A normative spatiotemporal MRI atlas of the fetal brain for automatic segmentation and analysis of early brain growth. Sci Rep 7(1):1–13
doi: 10.1038/s41598-017-00525-w
Bohland JW, Bokil H, Allen CB, Mitra PP (2009) The brain atlas concordance problem: quantitative comparison of anatomical parcellations. PloS One 4(9):e7200
doi: 10.1371/journal.pone.0007200
Khalili N, Lessmann N, Turk E, Claessens N, de Heus R, Kolk T, Viergever MA, Benders MJ, Išgum I (2019) Automatic brain tissue segmentation in fetal MRI using convolutional neural networks. Magn Reson Imaging 64:77–89
doi: 10.1016/j.mri.2019.05.020
Kalavathi P, Senthamilselvi M, Prasath V (2017) Review of computational methods on brain symmetric and asymmetric analysis from neuroimaging techniques. Technologies 5(2):16
doi: 10.3390/technologies5020016
Rehman HZU, Lee S (2018) An efficient automatic midsagittal plane extraction in brain MRI. Appl Sci 8(11):2203
doi: 10.3390/app8112203
Ruppert GC, Teverovskiy L, Yu C-P, Falcao AX, Liu Y (2011) A new symmetry-based method for mid-sagittal plane extraction in neuroimages. In: Proc. IEEE international symposium on biomedical imaging, pp 285–288
Khan NH, Tegnander E, Dreier JM, Eik-Nes S, Torp H, Kiss G (2017) Automatic detection and measurement of fetal biparietal diameter and femur length: feasibility on a portable ultrasound device. Open J Obstet Gynecol 7(3):334–350
doi: 10.4236/ojog.2017.73035
Williams BM, Zheng Y (2019) Improving fetal head contour detection by object localisation with deep learning. In: Proc. 23rd conf. medical image understanding and analysis. Springer Nature, p 142
van den Heuvel TL, de Bruijn D, de Korte CL, van Ginneken B (2018) Automated measurement of fetal head circumference using 2D ultrasound images. PloS ONE 13 (8)
He K, Zhang X, Ren S, Sun J Deep residual learning for image recognition. In: Proc. IEEE conf. on computer vision and pattern recognition, 2016. pp 770–778
Zhang L, Wang X, Yang D, Sanford T, Harmon S, Turkbey B, Roth H, Myronenko A, Xu D, Xu Z (2019) When unseen domain generalization is unnecessary? Rethinking data augmentation. arXiv preprint arXiv:190603347
Berman M, Rannen Triki A, Blaschko MB The Lovász-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proc. IEEE conf. on computer vision and pattern recognition, 2018. pp 4413–4421
Pizer SM, Amburn EP, Austin JD, Cromartie R, Geselowitz A, Greer T, ter Haar RB, Zimmerman JB, Zuiderveld K (1987) Adaptive histogram equalization and its variations. Comput Vis Gr Image Process 39(3):355–368
doi: 10.1016/S0734-189X(87)80186-X
Yushkevich PA, Gao Y, Gerig G ITK-SNAP: An interactive tool for semi-automatic segmentation of multi-modality biomedical images. In: Proc. 38th Int. conf. of the engineering in medicine and biology society (EMBC), 2016 2016. IEEE, pp 3342–3345
Stella XY, Shi J (2003) Multiclass spectral clustering. In: Proc. IEEE int. conf. on computer vision. IEEE, pp 313–319
Bland JM, Altman DG (1986) Statistical methods for assessing agreement between two methods of clinical measurement. The Lancet 327(8476):307–310
doi: 10.1016/S0140-6736(86)90837-8
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proc. IEEE conf. on computer vision and pattern recognition. pp 4700–4708
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556