# Semi-Supervised Training of Optical Flow Convolutional Neural Networks in Ultrasound Elastography

arXiv: https://arxiv.org/abs/2007.01421 · HTML: https://mlsanity.com/paper/2007.01421/

## Key facts

- Cited by 9 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 2 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow](https://mlsanity.com/paper/2203.13214/) (2022)
- [Optical Flow Training under Limited Label Budget via Active Learning](https://mlsanity.com/paper/2203.05053/) (2022)
- [Adaptive 3D Localization of 2D Freehand Ultrasound Brain Images](https://mlsanity.com/paper/2209.05477/) (2022)
- [Physically Inspired Constraint for Unsupervised Regularized Ultrasound Elastography](https://mlsanity.com/paper/2206.02225/) (2022)
- [Lateral Strain Imaging using Self-supervised and Physically Inspired Constraints in Unsupervised Regularized Elastography](https://mlsanity.com/paper/2212.08740/) (2022)
- [Robust Scatterer Number Density Segmentation of Ultrasound Images](https://mlsanity.com/paper/2201.06143/) (2022)
- [Ultrasound Shear Wave Elasticity Imaging with Spatio-Temporal Deep Learning](https://mlsanity.com/paper/2204.05745/) (2022)
- [Infusing known operators in convolutional neural networks for lateral strain imaging in ultrasound elastography](https://mlsanity.com/paper/2211.00172/) (2022)
- [Multi-Stage Residual-Aware Unsupervised Deep Learning Framework for Consistent Ultrasound Strain Elastography](https://mlsanity.com/paper/2511.15640/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks (CNN) have been found to have great potential in optical flow problems thanks to an abundance of data available for training a deep network. The displacement estimation step in UltraSound Elastography (USE) can be viewed as an optical flow problem. Despite the high performance of CNNs in optical flow, they have been rarely used for USE due to unique challenges that both input and output of USE networks impose. Ultrasound data has much higher high-frequency content compared to natural images. The outputs are also drastically different, where displacement values in USE are often smooth without sharp motions or discontinuities. The general trend is currently to use pre-trained networks and fine-tune them on a small simulation ultrasound database. However, realistic ultrasound simulation is computationally expensive. Also, the simulation techniques do not model complex motions, nonlinear and frequency-dependent acoustics, and many sources of artifact in ultrasound imaging. Herein, we propose an unsupervised fine-tuning technique which enables us to employ a large unlabeled dataset for fine-tuning of a CNN optical flow network. We show that the proposed unsupervised fine-tuning method substantially improves the performance of the network and reduces the artifacts generated by networks trained on computer vision databases.