EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Clinical Grading of Artificial Intelligence‐Based 3D Fetal Brain Segmentations: A Cross‐Vendor Evaluation of Deep Learning in Fetal Neuroimaging

Moska Aliasi iD, Linde S Hesse, Madeleine K Wyburd iD, Maartje C Snoep iD, Renee M Smit, Ana I L Namburete, Monique C Haak iD

Prenatal Diagnosis · 2026-04 · 46 (4) · 503-513

DOI: 10.1002/pd.70103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Prenatal Diagnosis, online erschienen am 27.02.2026. Verfasst von Moska Aliasi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics and Fetal Medicine, Leiden University Medical Center, Leiden, the Netherlands. Hauptthemen laut MEDLINE: Deep Learning, Brain, Imaging, Three-Dimensional, Ultrasonography, Prenatal. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Canon Medical Systems Nederland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To evaluate the performance of automated (sub)cortical fetal brain segmentation methods on a novel 3D ultrasound dataset acquired from a different vendor, and to introduce a clinician‐focused visual evaluation framework complementary to the widely used Dice Similarity Coefficient (DSC).

Method

This cohort study included 270 volumes (141 fetuses, 19–26 + 6 weeks gestation). Deep learning models were applied to segment the cavum septum pellucidum et vergae (CSPV), lateral posterior ventricle horn (LPVH), choroid plexus (ChP), cerebellum (CBM) and cortical plate (CoP) on a new dataset acquired by a different ultrasound vendor. Segmentations were visually graded (1–4 = high to poor quality) based on predefined criteria. Grades were analyzed as “adequate” (1 + 2) or “inadequate” (3 + 4).

Results

CSPV, ChP and CBM showed the best segmentation grades (> 83.1% grade 1, > 90.5% adequate) and were robust across gestation. LPVH showed the lowest performance (73.9% adequate). Overall segmentation quality across all structures was high (87.2% adequate). Intra‐ and interobserver agreement was 90.1% and 82.1%–92.7%, respectively.

Conclusion

These deep‐learning methods can reliably segment (sub)cortical structures when applied to a novel dataset acquired with a different ultrasound vendor, demonstrating robustness. Incorporating visual assessment alongside quantitative metrics provides insight into anatomical accuracy and clinical usability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBrainImaging, Three-DimensionalUltrasonography, PrenatalNeuroimagingHumansFemalePregnancyArtificial IntelligenceCohort StudiesGestational AgeFetus

Autor:innen und Institutionen

  • Department of Obstetrics and Fetal Medicine, Leiden University Medical Center, Leiden, the Netherlands.
  • Department of Computer Science, University of Oxford, Oxford, UK.

ORCID-Profile: Moska Aliasi, Madeleine K Wyburd, Maartje C Snoep, Monique C Haak

Förderung

  • Canon Medical Systems Nederland

Zitieren

APA

Aliasi, M., Hesse, L. S., Wyburd, M. K., Snoep, M. C., Smit, R. M., Namburete, A. I. L., & Haak, M. C. (2026). Clinical Grading of Artificial Intelligence‐Based 3D Fetal Brain Segmentations: A Cross‐Vendor Evaluation of Deep Learning in Fetal Neuroimaging. Prenatal Diagnosis, 46(4), 503-513. https://doi.org/10.1002/pd.70103

Vancouver

Aliasi M, Hesse LS, Wyburd MK, Snoep MC, Smit RM, Namburete AIL, et al. Clinical Grading of Artificial Intelligence‐Based 3D Fetal Brain Segmentations: A Cross‐Vendor Evaluation of Deep Learning in Fetal Neuroimaging. Prenatal Diagnosis. 2026;46(4):503-513. doi:10.1002/pd.70103

BibTeX
@article{Aliasi2026,
  author = {Aliasi, Moska and Hesse, Linde S and Wyburd, Madeleine K and Snoep, Maartje C and Smit, Renee M and Namburete, Ana I L and Haak, Monique C},
  title = {Clinical Grading of Artificial Intelligence‐Based 3D Fetal Brain Segmentations: A Cross‐Vendor Evaluation of Deep Learning in Fetal Neuroimaging},
  journal = {Prenatal Diagnosis},
  year = {2026},
  volume = {46},
  number = {4},
  pages = {503--513},
  doi = {10.1002/pd.70103}
}
Kostenlos starten →