Self-Supervised Ultrasound Representation Learning for Renal Anomaly Prediction in Prenatal Imaging

2025-12-15

AI Summary

Prenatal ultrasound diagnosis of fetal renal abnormalities—such as hydronephrosis and multicystic dysplastic kidney—is limited by operator dependency and variable image quality. To address this, we propose USF-MAE, the first ultrasound-specific self-supervised foundation model adapting the Masked Autoencoder (MAE) framework to obstetric ultrasound: it learns robust spatiotemporal representations by reconstructing masked ultrasound video frames. After fine-tuning, USF-MAE supports both binary and multi-class classification of renal structural anomalies and integrates a Transformer-compatible Score-CAM variant for anatomically grounded, interpretable predictions. On an independent test set, USF-MAE achieves a 2.32% AUC improvement, a 4.33% gain in binary F1-score, and a substantial 46.15% increase in multi-class F1-score. Visualizations confirm that model attention consistently localizes clinically relevant anatomical regions—including the renal pelvis and cystic areas—demonstrating clinical interpretability and trustworthiness.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Unsupervised & Self-Supervised Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Prenatal ultrasound is the cornerstone for detecting congenital anomalies of the kidneys and urinary tract, but diagnosis is limited by operator dependence and suboptimal imaging conditions. We sought to assess the performance of a self-supervised ultrasound foundation model for automated fetal renal anomaly classification using a curated dataset of 969 two-dimensional ultrasound images. A pretrained Ultrasound Self-Supervised Foundation Model with Masked Autoencoding (USF-MAE) was fine-tuned for binary and multi-class classification of normal kidneys, urinary tract dilation, and multicystic dysplastic kidney. Models were compared with a DenseNet-169 convolutional baseline using cross-validation and an independent test set. USF-MAE consistently improved upon the baseline across all evaluation metrics in both binary and multi-class settings. USF-MAE achieved an improvement of about 1.87% (AUC) and 7.8% (F1-score) on the validation set, 2.32% (AUC) and 4.33% (F1-score) on the independent holdout test set. The largest gains were observed in the multi-class setting, where the improvement in AUC was 16.28% and 46.15% in F1-score. To facilitate model interpretability, Score-CAM visualizations were adapted for a transformer architecture and show that model predictions were informed by known, clinically relevant renal structures, including the renal pelvis in urinary tract dilation and cystic regions in multicystic dysplastic kidney. These results show that ultrasound-specific self-supervised learning can generate a useful representation as a foundation for downstream diagnostic tasks. The proposed framework offers a robust, interpretable approach to support the prenatal detection of renal anomalies and demonstrates the promise of foundation models in obstetric imaging.

Problem

• Develops a self-supervised model for automated fetal renal anomaly classification
• Addresses operator dependence and suboptimal imaging in prenatal ultrasound diagnosis
• Improves classification of normal kidneys, urinary tract dilation, and dysplastic kidney

Innovation

• Self-supervised masked autoencoding for ultrasound representation learning
• Fine-tuning foundation model for fetal renal anomaly classification
• Score-CAM visualizations adapted for transformer interpretability