EUVIMEDObjevte EUVIMED
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 ↗

At a glance

Journal article in Prenatal Diagnosis, published online on 2026-02-27. Written by Moska Aliasi and 6 co-authors. Institution: Department of Obstetrics and Fetal Medicine, Leiden University Medical Center, Leiden, the Netherlands. Major MEDLINE topics: Deep Learning, Brain, Imaging, Three-Dimensional, Ultrasonography, Prenatal. 54 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Canon Medical Systems Nederland.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

Deep LearningBrainImaging, Three-DimensionalUltrasonography, PrenatalNeuroimagingHumansFemalePregnancyArtificial IntelligenceCohort StudiesGestational AgeFetus

Authors and institutions

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

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

Funding

  • Canon Medical Systems Nederland

Cite

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}
}
Start for free →