Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
By: Divyanshu Mishra , Mohammadreza Salehi , Pramit Saha and more
Potential Business Impact:
Helps doctors see heart problems in ultrasound.
Self-supervised learning (SSL) has achieved major advances in natural images and video understanding, but challenges remain in domains like echocardiography (heart ultrasound) due to subtle anatomical structures, complex temporal dynamics, and the current lack of domain-specific pre-trained models. Existing SSL approaches such as contrastive, masked modeling, and clustering-based methods struggle with high intersample similarity, sensitivity to low PSNR inputs common in ultrasound, or aggressive augmentations that distort clinically relevant features. We present DISCOVR (Distilled Image Supervision for Cross Modal Video Representation), a self-supervised dual branch framework for cardiac ultrasound video representation learning. DISCOVR combines a clustering-based video encoder that models temporal dynamics with an online image encoder that extracts fine-grained spatial semantics. These branches are connected through a semantic cluster distillation loss that transfers anatomical knowledge from the evolving image encoder to the video encoder, enabling temporally coherent representations enriched with fine-grained semantic understanding. Evaluated on six echocardiography datasets spanning fetal, pediatric, and adult populations, DISCOVR outperforms both specialized video anomaly detection methods and state-of-the-art video-SSL baselines in zero-shot and linear probing setups, and achieves superior segmentation transfer.
Similar Papers
DiSSECT: Structuring Transfer-Ready Medical Image Representations through Discrete Self-Supervision
CV and Pattern Recognition
Helps doctors find sickness in X-rays better.
HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation
CV and Pattern Recognition
Helps doctors see inside the body better.
Self-supervised structured object representation learning
CV and Pattern Recognition
Helps computers see objects in pictures better.