Learning sweep embeddings from blind obstetric ultrasound for gestational age prediction
| dc.contributor.advisor | Dang, Vien Ngoc | |
| dc.contributor.author | Hristov, Christin | |
| dc.date.accessioned | 2026-10-23T12:40:57Z | |
| dc.date.available | 2026-10-23T12:40:57Z | |
| dc.date.issued | 2026-06-28 | |
| dc.description | Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Any: 2026. Tutor: Vien Ngoc Dang | |
| dc.description.abstract | Gestational age (GA) prediction from blind-sweep obstetric ultrasound could help extend fetal dating to settings with limited access to trained sonographers. However, GA labels for training predictive models are harder to obtain than unlabeled sweep videos. This thesis studies whether a frozen self-supervised ultrasound encoder, combined with a lightweight sweep-level aggregator, can support label-efficient GA prediction when only a subset of training sweeps has GA labels. Using 1,314 blind-sweep videos from two acquisition sites, Spain and Kenya, three frame-encoder pretraining conditions and four sweep aggregators are compared. The resulting sweep embeddings are evaluated for GA prediction under full and reduced label budgets. Encoder pretraining quality appears to be the dominant factor among those tested. The best-performing encoder, which combines general ultrasound pretraining with continued pretraining on in-domain sweep data, outperforms a from-scratch encoder by 5.1 days mean absolute error. Aggregator choice and frozen versus trainable aggregation, by contrast, show much smaller effects, spanning only 1.14 days once the encoder is fixed, with frozen aggregators reaching similar performance to aggregators trained jointly with the prediction head. This encoder advantage also appears to carry over to label efficiency: continued pretraining at only 10% of training labels already reaches a weaker encoder’s accuracy at 100% of labels. Aggregator choice and training regime remain secondary across the label budgets tested. A gap of approximately 5 days remains to a fully supervised reference at full label availability, which may be associated with keeping the encoder frozen. For this dataset and fixed frame-selection pipeline, the results suggest prioritizing encoder pretraining over aggregator complexity, since aggregators pretrained without GA labels showed no consistent MAE drop compared with trainable aggregators. | |
| dc.format.extent | 24 p. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | https://hdl.handle.net/2445/232300 | |
| dc.language.iso | eng | |
| dc.rights | cc-by-nc-nd (c) Hristov, Christin, 2026 | |
| dc.rights.accessRights | info:eu-repo/semantics/openAccess | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | |
| dc.subject.classification | Ecografia obstètrica | |
| dc.subject.classification | Diagnòstic prenatal | |
| dc.subject.classification | Aprenentatge automàtic | |
| dc.subject.classification | Treballs de fi de màster | |
| dc.subject.other | Obstetrical ultrasound | |
| dc.subject.other | Prenatal diagnosis | |
| dc.subject.other | Machine learning | |
| dc.subject.other | Master's thesis | |
| dc.title | Learning sweep embeddings from blind obstetric ultrasound for gestational age prediction | |
| dc.type | info:eu-repo/semantics/masterThesis |
Fitxers
Paquet original
1 - 1 de 1
Carregant...
- Nom:
- TFM_Hristov_Christin.pdf
- Mida:
- 3.58 MB
- Format:
- Adobe Portable Document Format