Efficient fetal ultrasound image segmentation for automatic head circumference measurement using a lightweight deep convolutional neural network
Abstract
PURPOSE: Fetal head circumference (HC) is an important biometric parameter that can be used to assess fetal development in obstetric clinical practice. Most of the existing methods use deep neural network to accomplish the task of automatic fetal HC measurement from two-dimensional ultrasound images, and some of them achieved relatively high prediction accuracy. However, few of these methods focused on optimizing model efficiency performance. Our purpose is to develop a more efficient approach for this task, which could help doctors measure HC faster and would be more suitable for deployment on devices with scarce computing resources. METHODS: In this paper, we present a very lightweight deep convolutional neural network to achieve automatic fetal head segmentation from ultrasound images. By using sequential prediction network architecture, the proposed model could perform much faster inference while maintaining a high prediction accuracy. In addition, we used depthwise separable convolution to replace part of the standard convolution in the network and shrunk the input image to further improve model efficiency. After getting fetal head segmentation results, post-processing, including morphological processing and least-squares ellipse fitting, was applied to obtain the fetal HC. All experiments in this work were performed on a public dataset, HC18, with 999 fetal ultrasound images for training and 335 for testing. The dataset is publicly available on https://hc18.grand-challenge.org/ and the code for our method is also publicly available on https://github.com/ApeMocker/CSM-for-fetal-HC-measurement. RESULTS: Our model has only 0.13 million [M] parameters and can achieve an inference speed of 28 [ms] per frame on a CPU and 0.194 [ms] per frame on a GPU, which far exceeds all existing deep learning-based models as far as we know. Experimental results showed that the method achieved a mean absolute difference of 1.97( ± 1.89) [mm] and a Dice similarity coefficient of 97.61( ± 1.72) [%] on HC18 test set, which were comparable to the state of the art. CONCLUSION: We presented a very lightweight deep learning-based model to realize fast and accurate fetal head segmentation from two-dimensional ultrasound image, which is then used for calculating the fetal HC. The proposed method could help obstetricians measure the fetal HC more efficiently with high accuracy, and has the potential to be applied to the situations where computing resources are relatively scarce.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Five studies used the freely available 'HC18' data set for training and testing algorithms, which contained 1334 2D images from 551 women of the standard fetal head plane.
“Five studies used the freely available ‘HC18’ data set [45] for training and testing the algorithms, which contained 1334 2D images from 551 women of the standard fetal head plane [18,34,37,38,40].”
AI usage in standard plane acquisition has the benefit of application of a lightweight algorithm in point-of-care devices.
“the application of a lightweight algorithm in point-of-care devices [18,34,37]”
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931 · see citing works
Fully convolutional networks for semantic segmentation
Shelhamer, E., Long, J., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2572683 · Cited by 11,898 · see citing works
Wei, S.-E., Ramakrishna, V., Kanade, T., & Sheikh, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.511 · Cited by 2,966 · see citing works
Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening
Wu, N., Phang, J., Park, J., Shen, Y., Huang, Z., Zorin, M., Jastrzȩbski, S., Févry, T., Katsnelson, J., Kim, E. S., et al. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2945514 · Cited by 695 · see citing works
Automated measurement of fetal head circumference using 2D ultrasound images
van den Heuvel, T. L. A., de Bruijn, D., de Korte, C. L., & Ginneken, B. V. (2018) · PLOS ONE · doi:10.1371/journal.pone.0200412 · Cited by 280 · see citing works
Carneiro, G., Georgescu, B., Good, S., & Comaniciu, D. (2008) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2008.928917 · Cited by 205 · see citing works
Rueda, S., Fathima, S., Knight, C. L., Yaqub, M. K., Papageorghiou, A. T., Rahmatullah, B., Foi, A., Maggioni, M., Pepe, A., Tohka, J., et al. (2013) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2276943 · Cited by 177 · see citing works
ElliFit: An unconstrained, non-iterative, least squares based geometric Ellipse Fitting method
Prasad, D. K., Leung, M. K. H., & Quek, C. H. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.11.007 · Cited by 170 · see citing works
Lü, W., & Tan, J. (2007) · Pattern Recognition · doi:10.1016/j.patcog.2007.09.006 · Cited by 162 · see citing works
Sobhaninia, Z., Rafiei, S., Emami, A., Karimi, N., Najarian, K., Samavi, S., & Soroushmehr, S. M. R. (2019) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2019.8856981 · Cited by 141 · see citing works
Cascaded Fully Convolutional Networks for automatic prenatal ultrasound image segmentation
Wu, L., Yang, X., Li, S., Wang, T., Heng, P., & Ni, D. (2017) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2017.7950607 · Cited by 126 · see citing works
Li, J., Wang, Y., Lei, B., Cheng, J.-Z., Qin, J., Wang, T., Li, S., & Ni, D. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2703890 · Cited by 120 · see citing works
Self-citationZeng, Y., Tsui, P.-H., Wu, W., Zhou, Z., & Wu, S. (2021) · Journal of Digital Imaging · doi:10.1007/s10278-020-00410-5 · Cited by 113 · see citing works
Lü, W., Tan, J., & Floyd, R. C. (2005) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2005.04.002 · Cited by 106 · see citing works
Onishi, Y., Teramoto, A., Tsujimoto, M., Tsukamoto, T., Saito, K., Toyama, H., Imaizumi, K., & Fujita, H. (2019) · BioMed Research International · doi:10.1155/2019/6051939 · Cited by 87 · see citing works
Segmentation of fetal ultrasound images
Jardim, S., & Figueiredo, M. A. T. (2005) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2004.11.003 · Cited by 84 · see citing works
Sinclair, M. D., Baumgartner, C. F., Matthew, J., Bai, W., Martinez, J. C., Li, Y., Smith, S., Knight, C. L., Kainz, B., Hajnal, J. V., et al. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512278 · Cited by 78 · see citing works
Computer-Aided Diagnosis (CAD) of Pulmonary Nodule of Thoracic CT Image Using Transfer Learning
Zhang, S., Sun, F., Wang, N., Zhang, C., Yu, Q., Zhang, M., Babyn, P., & Zhong, H. (2019) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-019-00204-4 · Cited by 71 · see citing works
Sonographic large fetal head circumference and risk of cesarean delivery
Lipschuetz, M., Cohen, S. M., Israel, A., Baron, J., Porat, S., Valsky, D. V., Yagel, O., Amsalem, H., Kabiri, D., Gilboa, Y., et al. (2018) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2017.12.230 · Cited by 70 · see citing works
A regression framework to head-circumference delineation from US fetal images
Fiorentino, M. C., Moccia, S., Capparuccini, M., Giamberini, S., & Frontoni, E. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105771 · Cited by 54 · see citing works
Localization of Fetal Head in Ultrasound Images by Multiscale View and Deep Neural Networks
Sobhaninia, Z., Emami, A., Karimi, N., & Samavi, S. (2020) · International Computer Conference, Computer Society of Iran (CSICC) · doi:10.1109/csicc49403.2020.9050094 · Cited by 44 · see citing works
A multiple‐channel and atrous convolution network for ultrasound image segmentation
Zhang, L., Zhang, J., Li, Z., & Song, Y. (2020) · Medical Physics · doi:10.1002/mp.14512 · Cited by 35 · see citing works
Finding the most accurate method to measure head circumference for fetal weight estimation
Schmidt, U., Temerinac, D., Bildstein, K., Tuschy, B., Mayer, J., Sütterlin, M., Siemer, J., & Kehl, S. (2014) · European Journal of Obstetrics & Gynecology and Reproductive Biology · doi:10.1016/j.ejogrb.2014.03.047 · Cited by 34 · see citing works
Zhang, L., Ye, X., Lambrou, T., Duan, W., Allinson, N., & Dudley, N. J. (2016) · Physics in Medicine & Biology · doi:10.1088/0031-9155/61/3/1095 · Cited by 34 · see citing works
3D Inception U‐net with Asymmetric Loss for Cancer Detection in Automated Breast Ultrasound
Wang, Y., Qin, C., Lin, C., Lin, D., Xu, M., Luo, X., Wang, T., Li, A., & Ni, D. (2020) · Medical Physics · doi:10.1002/mp.14389 · Cited by 34 · see citing works
Does the Use of Automated Fetal Biometry Improve Clinical Work Flow Efficiency?
Espinoza, J., Good, S., Russell, E., et al. (2013) · Journal of Ultrasound in Medicine · doi:10.7863/ultra.32.5.847 · Cited by 31 · see citing works
Pérez-González, J., Muñoz, J., Porras, M. C. R., Cosı́o, F. A., & Medina-Bañuelos, V. (2015) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-319-13117-7_85 · Cited by 29 · see citing works
Anto, E. A., Amoah, B., & Crimi, A. (2015) · doi:10.1109/embc.2015.7318481 · Cited by 15 · see citing works
Retinopathy Analysis Based on Deep Convolution Neural Network
Hatanaka, Y. (2020) · Advances in experimental medicine and biology · doi:10.1007/978-3-030-33128-3_7 · Cited by 12 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Jost, E., Kosian, P., Jimenez Cruz, J., Albarqouni, S., Gembruch, U., Strizek, B., & Recker, F. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12216833 · Cited by 44 · see citing works
- Authors
- Zeng, W., Luo, J., Cheng, J., & Lu, Y.
- Affiliations
- Sun Yat-sen University (CN)
- Corresponding author
- Luo, Jie
- Venue
- Medical Physics
- Publisher
- Wiley
- Published
- 2022-05-24
- Volume
- 49
- Issue
- 8
- Pages
- 5081-5092
- ISSN
- 0094-2405 (ISSN-L)
- 2473-4209
- OpenAlex
- W4229446944
- Cited by
- 31
- References
- 30
- Citations by year
- 2026: 10 · 2025: 10 · 2024: 3 · 2023: 7 · 2022: 1
- FWCI
- 1.72
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Medical Physics (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (U1801265)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- fetal head circumference, fetal head segmentation, fetal ultrasound images, depthwise separable convolution, inference efficiency, ellipse fitting, morphological processing, fetal biometry
- MeSH terms
- Female, Head, Humans, Image Processing, Computer-Assisted, Pregnancy, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
