EUVIMEDEUVIMED entdecken
Crossref

Prenatal diagnosis of cerebellar hypoplasia in fetal ultrasound using deep learning under the constraint of the anatomical structures of the cerebellum and cistern

Xiaoxiao Wu, Fu Liu, Guoping Xu, Yiling Ma, Chen Cheng, Ruifan He, Aoxiang Yang, Jiayi Gan, Jiajun Liang, Xinglong Wu, Sheng Zhao

Pediatric Radiology · 05.09.2025 · 55 (12) · 2550-2565

DOI: 10.1007/s00247-025-06376-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Radiology, online erschienen am 05.09.2025. Verfasst von Xiaoxiao Wu und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430205, China. Hauptthemen laut MEDLINE: Ultrasonography, Prenatal, Cerebellum, Nervous System Malformations, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hubei Province Natural Science Foundation, Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: The objective of this retrospective study is to develop and validate an artificial intelligence model constrained by the anatomical structure of the brain with the aim of improving the accuracy of prenatal diagnosis of fetal cerebellar hypoplasia using ultrasound imaging. BACKGROUND: Fetal central nervous system dysplasia is one of the most prevalent congenital malformations, and cerebellar hypoplasia represents a significant manifestation of this anomaly. Accurate clinical diagnosis is of great importance for the purpose of prenatal screening of fetal health. Although ultrasound has been extensively utilized to assess fetal development, the accurate assessment of cerebellar development remains challenging due to the inherent limitations of ultrasound imaging, including low resolution, artifacts, and acoustic shadowing of the skull. MATERIALS AND METHODS: This retrospective study included 302 cases diagnosed with cerebellar hypoplasia and 549 normal pregnancies collected from Maternal and Child Health Hospital of Hubei Province between September 2019 and September 2023. For each case, experienced ultrasound physicians selected appropriate brain ultrasound images to delineate the boundaries of the skull, cerebellum, and cerebellomedullary cistern. These cases were divided into one training set and two test sets, based on the examination dates. This study then proposed a dual-branch deep learning classification network, anatomical structure-constrained network (ASC-Net), which took ultrasound images and anatomical structure masks as separate inputs. The performance of the ASC-Net was extensively evaluated and compared with several state-of-the-art deep learning networks. The impact of anatomical structures on the performance of ASC-Net was carefully examined. RESULTS: ASC-Net demonstrated superior performance in the diagnosis of cerebellar hypoplasia, achieving classification accuracies of 0.9778 and 0.9222, as well as areas under the receiver operating characteristic curve of 0.9986 and 0.9265 on the two test sets. These results significantly outperformed several state-of-the-art networks on the same dataset. In comparison to other studies on cerebellar hypoplasia auxiliary diagnosis, ASC-Net also demonstrated comparable or even better performance. A subgroup analysis revealed that ASC-Net was more capable of distinguishing cerebellar hypoplasia in cases with gestational weeks greater than 30 weeks. Furthermore, when constrained by anatomical structures of both the cerebellum and cistern, ASC-Net exhibited the best performance compared to other kinds of structural constraint. CONCLUSIONS: The development and validation of ASC-Net have significantly enhanced the accuracy of prenatal diagnosis of cerebellar hypoplasia using ultrasound images. This study highlights the importance of anatomical structures of the fetal cerebellum and cistern on the performance of the diagnostic artificial intelligence model in ultrasound. This might provide new insights for clinical diagnosis of cerebellar hypoplasia, assist clinicians in providing more targeted advice and treatment during pregnancy, and contribute to improved perinatal healthcare. ASC-Net is open-sourced and publicly available in a GitHub repository at https://github.com/Wwwwww111112/ASC-Net .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ultrasonography, PrenatalCerebellumNervous System MalformationsDeep LearningHumansFemalePregnancyRetrospective StudiesDevelopmental Disabilities

Stichwörter der Autor:innen

Anatomical structureCerebellar hypoplasiaCerebellomedullary cisternDeep learningFetal ultrasound

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430205, China.
  • Maternal and Child Health Hospital of Hubei Province, Wuhan, China.
  • School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430205, China. xwu@wit.edu.cn.
  • Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis, Kashi, 844000, China. xwu@wit.edu.cn.
  • Maternal and Child Health Hospital of Hubei Province, Wuhan, China. zhao1015568495@163.com.

Förderung

  • National Natural Science Foundation of China
  • Hubei Province Natural Science Foundation
  • Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis Fund
  • Hubei Provincial Health Commission

Zitieren

APA

Wu, X., Liu, F., Xu, G., Ma, Y., Cheng, C., He, R., Yang, A., Gan, J., Liang, J., Wu, X., & Zhao, S. (2025). Prenatal diagnosis of cerebellar hypoplasia in fetal ultrasound using deep learning under the constraint of the anatomical structures of the cerebellum and cistern. Pediatric Radiology, 55(12), 2550-2565. https://doi.org/10.1007/s00247-025-06376-2

Vancouver

Wu X, Liu F, Xu G, Ma Y, Cheng C, He R, et al. Prenatal diagnosis of cerebellar hypoplasia in fetal ultrasound using deep learning under the constraint of the anatomical structures of the cerebellum and cistern. Pediatric Radiology. 2025;55(12):2550-2565. doi:10.1007/s00247-025-06376-2

BibTeX
@article{Wu2025,
  author = {Wu, Xiaoxiao and Liu, Fu and Xu, Guoping and Ma, Yiling and Cheng, Chen and He, Ruifan and Yang, Aoxiang and Gan, Jiayi and Liang, Jiajun and Wu, Xinglong and Zhao, Sheng},
  title = {Prenatal diagnosis of cerebellar hypoplasia in fetal ultrasound using deep learning under the constraint of the anatomical structures of the cerebellum and cistern},
  journal = {Pediatric Radiology},
  year = {2025},
  volume = {55},
  number = {12},
  pages = {2550--2565},
  doi = {10.1007/s00247-025-06376-2}
}
Kostenlos starten →