# Label-free segmentation from cardiac ultrasound using self-supervised learning

arXiv: https://arxiv.org/abs/2210.04979 · HTML: https://mlsanity.com/paper/2210.04979/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 75 references that are in the map.
- First posted on arXiv 10 Oct 2022.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [U-Net and its variants for medical image segmentation: theory and applications](https://mlsanity.com/paper/2011.01118/) (2020)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [Understanding Deep Learning Techniques for Image Segmentation](https://mlsanity.com/paper/1907.06119/) (2019)
- [Contrastive Pretraining for Echocardiography Segmentation with Limited Data](https://mlsanity.com/paper/2201.07219/) (2022)
- [Robustness study of noisy annotation in deep learning based medical image segmentation](https://mlsanity.com/paper/2003.06240/) (2020)
- [Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual Annotation](https://mlsanity.com/paper/1801.08486/) (2018)
- [Deep-learning models improve on community-level diagnosis for common congenital heart disease lesions](https://mlsanity.com/paper/1809.06993/) (2018)

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

- [Are foundation models efficient for medical image segmentation?](https://mlsanity.com/paper/2311.04847/) (2023)
- [textitlucie: An Improved Python Package for Loading Datasets from the UCI Machine Learning Repository](https://mlsanity.com/paper/2410.09119/) (2024)
- [Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation](https://mlsanity.com/paper/2510.14244/) (2025)
- [Generative deep learning for foundational video translation in ultrasound](https://mlsanity.com/paper/2511.03255/) (2025)
- [Towards Better Ultrasound Video Segmentation Foundation Model: An Empirical study on SAM2 Finetuning from Data Perspective](https://mlsanity.com/paper/2511.05731/) (2025)
- [Imaging-anchored multiomics in cardiovascular disease: integrating cardiac imaging, bulk, single-cell, and spatial transcriptomics](https://mlsanity.com/paper/2601.07871/) (2026)
- [MARCUS: An agentic, multimodal vision-language model for cardiac diagnosis and management](https://mlsanity.com/paper/2603.22179/) (2026)
- [Evaluating self-supervised echocardiographic representations across downstream extraction strategies for left-ventricular segmentation and ejection fraction estimation](https://mlsanity.com/paper/2606.22943/) (2026)

## Abstract (arXiv)

Segmentation and measurement of cardiac chambers is critical in cardiac ultrasound but is laborious and poorly reproducible. Neural networks can assist, but supervised approaches require the same laborious manual annotations. We built a pipeline for self-supervised (no manual labels) segmentation combining computer vision, clinical domain knowledge, and deep learning. We trained on 450 echocardiograms (93,000 images) and tested on 8,393 echocardiograms (4,476,266 images; mean 61 years, 51% female), using the resulting segmentations to calculate biometrics. We also tested against external images from an additional 10,030 patients with available manual tracings of the left ventricle. r2 between clinically measured and pipeline-predicted measurements were similar to reported inter-clinician variation and comparable to supervised learning across several different measurements (r2 0.56-0.84). Average accuracy for detecting abnormal chamber size and function was 0.85 (range 0.71-0.97) compared to clinical measurements. A subset of test echocardiograms (n=553) had corresponding cardiac MRIs, where MRI is the gold standard. Correlation between pipeline and MRI measurements was similar to that between clinical echocardiogram and MRI. Finally, the pipeline accurately segments the left ventricle with an average Dice score of 0.89 (95% CI [0.89]) in the external, manually labeled dataset. Our results demonstrate a manual-label free, clinically valid, and highly scalable method for segmentation from ultrasound, a noisy but globally important imaging modality.