Academic Journal
A Coarse-to-Fine DoubleUNet Framework with Synergistic Loss for Accurate Fetal Head Circumference Measurement.
| Τίτλος: | A Coarse-to-Fine DoubleUNet Framework with Synergistic Loss for Accurate Fetal Head Circumference Measurement. |
|---|---|
| Συγγραφείς: | Liu X; School of AI & Innovative Design, Beijing Institute of Fashion Technology, Beijing, China., Hu X; School of AI & Innovative Design, Beijing Institute of Fashion Technology, Beijing, China., Liu H; School of AI & Innovative Design, Beijing Institute of Fashion Technology, Beijing, China. Electronic address: gxyliuh@bift.edu.cn. |
| Πηγή: | Ultrasound in medicine & biology [Ultrasound Med Biol] 2026 Sep; Vol. 52 (9), pp. 1922-1932. Date of Electronic Publication: 2026 Jun 07. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Pergamon Press Country of Publication: England NLM ID: 0410553 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-291X (Electronic) Linking ISSN: 03015629 NLM ISO Abbreviation: Ultrasound Med Biol Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Oxford, New York, Pergamon Press. |
| Ιατρικοί όροι (MeSH): | Ultrasonography, Prenatal*/methods , Head*/diagnostic imaging , Head*/embryology , Head*/anatomy & histology , Cephalometry*/methods , Deep Learning*, Humans ; Female ; Pregnancy ; Reproducibility of Results ; Algorithms |
| Περίληψη: | Objective: Fetal head circumference (HC) measurement is a routine and indispensable examination during pregnancy, closely associated with fetal health and maternal delivery planning. To reduce the manual workload of sonographers, deep learning has been increasingly applied to this task, with promising outcomes. In this study, we propose a coarse-to-fine deep learning framework for the automatic segmentation and measurement of fetal HC from ultrasound images. Methods: We propose SDUNet, a DoubleUNet-based framework enhanced with a tailored synergistic loss for fetal HC segmentation. The synergistic loss integrates multiple complementary loss terms and dynamically balances their contributions during training. This adaptive mechanism encourages physiologically plausible head shapes while reducing errors caused by speckle noise and boundary ambiguity in ultrasound images. SDUNet was trained on the publicly available HC18 data set and further validated on an independent external data set, without applying any post-processing. Results: The proposed method achieved superior segmentation and measurement performance. Specifically, it obtained a Dice coefficient of 98.60%, Jaccard index of 97.24%, Hausdorff distance of 0.70 mm, average symmetric surface distance of 0.17 mm, boundary F Conclusions: Experimental results demonstrate that the SDUNet framework can effectively segment fetal head regions and provide highly accurate HC measurements. (Copyright © 2026 World Federation for Ultrasound in Medicine and Biology. Published by Elsevier Inc. All rights reserved.) |
| Competing Interests: | Conflict of interest The authors declare no competing interests. |
| Contributed Indexing: | Keywords: Deep learning; Fetal head circumference; Segmentation; Synergistic loss; Ultrasound image |
| Entry Date(s): | Date Created: 20260606 Date Completed: 20260801 Latest Revision: 20260801 |
| Update Code: | 20260802 |
| DOI: | 10.1016/j.ultrasmedbio.2026.05.010 |
| PMID: | 42250993 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1879-291X |
|---|---|
| DOI: | 10.1016/j.ultrasmedbio.2026.05.010 |