|Table of Contents|

Automatic measurement of fetal lung volume by 3D ultrasound based on 3D-nnUnet(PDF)

Journal of Shenzhen University Science and Engineering[ISSN:1000-2618/CN:44-1401/N]

Issue:
2022 Vol.39 No.3(237-362)
Page:
324-333
Research Field:
Electronics and Information Science

Info

Title:
Automatic measurement of fetal lung volume by 3D ultrasound based on 3D-nnUnet
Author(s):
WANG Lin1 CAO Yan2 DENG Ziwei2 HU Jiongtong2 LIANG Jiamin2 CAO Xiaoyan1 PAN Wenxiong1 YAN Yuling1 SUN Zhiwei1 YANG Xin2 and NI Dong2
1) Medical Image Department, Futian Women and Children Hospital, Shenzhen 518016, Guangdong Province, P. R. China
2) School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518071, Guangdong Province, P. R. China
Keywords:
artificial intelligence fetal lung maturity three-dimensional ultrasound semantic segmentation deep learning network adaptation medical image
PACS:
R318;TP751
DOI:
10.3724/SP.J.1249.2022.03324
Abstract:
Fetal lung dysplasia often causes the severe respiratory distress and even neonatal death at birth. Fetal lung volume measurement is an important method for clinical non-invasive assessment of lung maturity. However, the existing methods for measuring fetal lung volume suffer from huge errors, tedious and time-consuming operations, and poor clinical practicability. For this reason, we first propose an efficient and stable automatic segmentation and measurement method for fetal lung volume based on 3D-nnUnet, which uses the network adaptation to effectively overcome the problems of low tissue contrast and blurred edges and achieves accurate segmentation of 3-dimensional (3D) fetal lung ultrasound images. In addition, to solve the problem of large difference and extremely uneven distribution of sample numbers at different gestational weeks, we innovatively propose a hard-mining and easy-penalized (HMEP) loss to improve the model generalization ability. Compared with the segmentation results of 2-dimension optimal DeepLab V3+ and 3D-Unet, our network model has the best segmentation performance, and the accuracy is as high as 85.7%. In addition, HMEP loss enables the 3D-nnUnet model to focus on learning a few difficult samples, which increases the segmentation accuracy by nearly 2%. There is no significant statistical difference between the fetal lung volumes measured by our network and gold standard using the consistency test in different gestational weeks. The experimental results show that our method can efficiently realize the automatic and accurate segmentation and volume measurement of 3D ultrasound fetal lung, and has the good stability and generalization ability, which can avoid the problems of cumbersome, time-consuming operations and large errors in the previous fetal lung volume measurement methods. Our method has the promising application prospects in diagnosing fetal lung dysplasia and assessing fetal lung maturity.

References:

[1] 张波.产前超声在评估胎儿肺发育中的应用及研究进展[J].中华妇幼临床医学杂志电子版,2015,11(1):101-104.
ZHANG Bo. Research progress of prenatal ultrasound in assessing fetal lung development [J]. Chinese Journal of Obstetrics & Gyecology and Pediatrics Electronic Edition, 2015, 11(1): 101-104.(in Chinese)
[2] THOMAS M A. Clinical chemistry’s 2016 special issue: clinical mass spectrometry-achieving prominence in laboratory medicine [J]. Clinical Chemistry, 2015, 61(12): 1553.
[3] HIROYUKI T, TOMOMI K, TOMOKO N, et al. Lipocalin 2 as a new biomarker for fetal lung hypoplasia in congenital diaphragmmatic hernia [J]. Clinica Chimica Acta, 2016, 462: 71-76.
[4] HILDE K, CARLSEN K C L, BAINS K E S, et al. Fetal thoracic circumference and lung volume and their relation to fetal size and pulmonary artery blood flow [J]. Journal of Ultrasound in Medicine, 2022, 41(4): 985-993.
[5] USUI N, OKUYAMA H, SAWAI T, et al. Relationship between L/T ratio and LHR in the prenatal assessment of pulmonary hypoplasia in congenital diaphragmatic hernia [J]. Pediatric Surgery International, 2007, 23(10): 971-976.
[6] VERGANI P, ANDREANI M, GRECO M, et al. Two- or three-dimensional ultrasonography: which is the best predictor of pulmonary hypoplasia? [J]. Prenatal Diagnosis, 2010, 30(9): 834-838.
[7] MELO J, BRAVO-VALENZUELA N J, NARDOZZA L M M, et al. References values of fetal heart myocardial volume by three-dimensional ultrasound using spatiotemporal Image correlation and virtual organ computer-aided analysis methods and their applicability in pregestational diabetic women [J]. American Journal of Perinatology, 2019, 38(7): 721-727.
[8] 王琳玲,周启昌,汤小康.三维VOCAL旋转技术在胎儿肺发育不良临床诊断的运用研究[J].浙江中西医结合杂志,2017,27(9):776-780.
WANG Linling, ZHOU Qichang, TANG Xiaokang. Application of three-dimensional VOCAL rotation technology in clinical diagnosis of fetal lung dysplasia [J]. Zhejiang Journal of Integrated Traditional Chinese and Western Medicine, 2017, 27(9): 776-780.(in Chinese)
[9] MOEGLIN D, TALMANT C, DUYME M, et al. Fetal lung volumetry using two- and three-dimensional ultrasound [J]. Ultrasound in Obstetrics and Gynecology, 2005, 25(2): 119-127.
[10] KALACHE K D, ESPINOZA J, CHAIWORAPONGSA T, et al. Three-dimensional ultrasound fetal lung volume measurement: a systmatic study comparing the multiplanar method with the rotational (VOCAL) technique [J]. Ultrasound in Obstetrics & Gynecology, 2003, 21(2): 111.
[11] YANG Xin, YU Lequan, LI Shengli, et al. Towards automated semantic segmentation in prenatal volumetric ultrasound [J]. IEEE Transactions on Medical Imaging, 2018, 38(1): 180-193.
[12] YANG Xin, LI Haoming, WANG Yi, et al. Contrastive rendering with semi-supervised learning for ovary and follicle segmentation from 3D ultrasound [J]. Medical Image Analysis, 2021, 73: 102134.
[13] ISENSEE F, JAEGER P F, KOHL S A A, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation [J]. Nature Methods, 2021(18): 203-211.
[14] ?I?EK ?, ABDULKADIR A, LIENKAMP S S, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 2016: 424-432.
[15] MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation [C]// The 4th International Conference on 3D Vision. Stanford, USA: IEEE, 2016: 424-432.
[16] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection [C]// IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 2999-3007.
[17] WU Zifeng, SHEN Chunhua, HENGEL A. Bridging category-level and instance-level semantic image segmentation [EB/OL]. (2016-05-23) [2021-12-20]. https://arxiv.org/abs/1605.06885.
[18] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.
[19] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 2015: 234-241.
[20] ZHAO Hengshuang, SHI Jianping, QI Xiaojuan, et al. Pyramid scene parsing network [C]// Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 6230-6239.
[21] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation [C]// Proceedings of the European Conference on Computer Vision. Berlin: Springer, 2018: 833-851.

Memo

Memo:
-