Improved cystic hygroma detection from prenatal imaging using ultrasound-specific self-supervised representation learning

TL;DR

This study demonstrates that ultrasound-specific self-supervised pretraining significantly improves the accuracy and robustness of deep learning models for detecting cystic hygroma in prenatal ultrasound images, outperforming traditional supervised methods.

Contribution

The paper introduces USF-MAE, a self-supervised foundation model pretrained on unlabelled ultrasound images, enhancing cystic hygroma detection accuracy in first-trimester ultrasounds.

Findings

USF-MAE achieved 96% accuracy, 94% sensitivity, and 98% specificity.

Model outperformed DenseNet-169 baseline across all metrics.

Performance improvements were statistically significant (p = 0.0057).

Abstract

Cystic hygroma is a high-risk prenatal ultrasound finding that portends high rates of chromosomal abnormalities, structural malformations, and adverse pregnancy outcomes. Automated detection can increase reproducibility and support scalable early screening programs, but supervised deep learning methods are limited by small labelled datasets. This study assesses whether ultrasound-specific self-supervised pretraining can facilitate accurate, robust deep learning detection of cystic hygroma in first-trimester ultrasound images. We fine-tuned the Ultrasound Self-Supervised Foundation Model with Masked Autoencoding (USF-MAE), pretrained on over 370,000 unlabelled ultrasound images, for binary classification of normal controls and cystic hygroma cases used in this study. Performance was evaluated on the same curated ultrasound dataset, preprocessing pipeline, and 4-fold cross-validation protocol as for the DenseNet-169 baseline, using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (ROC-AUC). Model interpretability was analyzed qualitatively using Score-CAM visualizations. USF-MAE outperformed the DenseNet-169 baseline on all evaluation metrics. The proposed model yielded a mean accuracy of 0.96, sensitivity of 0.94, specificity of 0.98, and ROC-AUC of 0.98 compared to 0.93, 0.92, 0.94, and 0.94 for the DenseNet-169 baseline, respectively. Qualitative Score-CAM visualizations of model predictions demonstrated clinical relevance by highlighting expected regions in the fetal neck for both positive and negative cases. Paired statistical analysis using a Wilcoxon signed-rank test confirmed that performance improvements achieved by USF-MAE were statistically significant (p = 0.0057).