# Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound

arXiv: https://arxiv.org/abs/2208.10642 · HTML: https://mlsanity.com/paper/2208.10642/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [A Broad Study on the Transferability of Visual Representations with Contrastive Learning](https://mlsanity.com/paper/2103.13517/) (2021)
- [Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube](https://mlsanity.com/paper/1910.02241/) (2019)
- [SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound](https://mlsanity.com/paper/1612.05601/) (2016)
- [Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction](https://mlsanity.com/paper/1907.02757/) (2019)
- [Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations](https://mlsanity.com/paper/2007.07423/) (2020)
- [MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models](https://mlsanity.com/paper/2010.05352/) (2020)
- [MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation](https://mlsanity.com/paper/2102.10663/) (2021)
- [Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restoration](https://mlsanity.com/paper/2007.06959/) (2020)
- [USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning](https://mlsanity.com/paper/2011.13066/) (2020)
- [A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis](https://mlsanity.com/paper/2108.05930/) (2021)
- [Self-supervised Representation Learning for Ultrasound Video](https://mlsanity.com/paper/2003.00105/) (2020)
- [Attention-Gated Networks for Improving Ultrasound Scan Plane Detection](https://mlsanity.com/paper/1804.05338/) (2018)
- [Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound](https://mlsanity.com/paper/2008.06607/) (2020)
- [Ultrasound Image Representation Learning by Modeling Sonographer Visual Attention](https://mlsanity.com/paper/1903.02974/) (2019)

## Built on by (most cited first, 8 of 8)

- [Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train](https://mlsanity.com/paper/2306.16741/) (2023)
- [Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision](https://mlsanity.com/paper/2404.15672/) (2024)
- [Self-Supervised Ultrasound-Video Segmentation with Feature Prediction and 3D Localised Loss](https://mlsanity.com/paper/2507.18424/) (2025)
- [Temporal Representation Learning for Real-Time Ultrasound Analysis](https://mlsanity.com/paper/2509.01433/) (2025)
- [Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation](https://mlsanity.com/paper/2605.25402/) (2026)
- [ACE: Anatomically Consistent Embeddings in Composition and Decomposition](https://mlsanity.com/paper/2501.10131/) (2025)
- [Show from Tell: Audio-Visual Modelling in Clinical Settings](https://mlsanity.com/paper/2310.16477/) (2023)
- [Leveraging Self-Supervised Learning for Fetal Cardiac Planes Classification using Ultrasound Scan Videos](https://mlsanity.com/paper/2407.21738/) (2024)

## Abstract (arXiv)

Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations that are inconsistent in appearance and semantics. In this paper, we propose to improve visual representations of medical images via anatomy-aware contrastive learning (AWCL), which incorporates anatomy information to augment the positive/negative pair sampling in a contrastive learning manner. The proposed approach is demonstrated for automated fetal ultrasound imaging tasks, enabling the positive pairs from the same or different ultrasound scans that are anatomically similar to be pulled together and thus improving the representation learning. We empirically investigate the effect of inclusion of anatomy information with coarse- and fine-grained granularity, for contrastive learning and find that learning with fine-grained anatomy information which preserves intra-class difference is more effective than its counterpart. We also analyze the impact of anatomy ratio on our AWCL framework and find that using more distinct but anatomically similar samples to compose positive pairs results in better quality representations. Experiments on a large-scale fetal ultrasound dataset demonstrate that our approach is effective for learning representations that transfer well to three clinical downstream tasks, and achieves superior performance compared to ImageNet supervised and the current state-of-the-art contrastive learning methods. In particular, AWCL outperforms ImageNet supervised method by 13.8% and state-of-the-art contrastive-based method by 7.1% on a cross-domain segmentation task.