Lightweight and Real-Time Deep Learning Models for Fetal Head Segmentation: A Review of Techniques and Applications
Bibliographic record
Abstract
Accurate fetal biometric parameters, such as head circumference, biparietal diameter, and occipitofrontal diameter of the head are important for prenatal diagnosis and growth tracking. Manually measuring them from ultrasound or magnetic resonance imaging is time consuming and depends too much on the operator. This has led to the use of artificial intelligence and deep learning for automation. Recently, convolutional neural networks, encoder decoder architectures, and hybrid attention mechanisms have greatly increased segmentation accuracy and speed. This survey reviews recent advances from 2021 to 2025 in automatic fetal head and brain segmentation and biometric estimation. Different imaging methods and problem formulations are covered, including real time light weight models, advanced U net and Atrous pooling variants, multi-task methods for standard plane identification, Spatio temporal models for videos and volumes, and classical shape constrained postprocessing. This study also summarizes dataset features, evaluation metrics, and benchmark results, highlighting the lack of a standard ultrasound dataset as a key limitation. Major problems discussed include acoustic artifacts, motion induced distortion, lack of data, and variation across scanners and populations. Promising research directions include self-supervised learning, uncertainty, adaptation across domains, and whole examination AI systems tested through prospective clinical trials. Overall, it is found that deep learning based fetal biometry systems are nearing clinical use. Future work will need to focus on making them more robust, explainable, and able to be integrated into obstetric imaging workflows.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".