# Mitigating Aberration-Induced Noise: A Deep Learning-Based Aberration-to-Aberration Approach

arXiv: https://arxiv.org/abs/2308.11149 · HTML: https://mlsanity.com/paper/2308.11149/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2023.

## Built on by (most cited first, 5 of 5)

- [Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Data](https://mlsanity.com/paper/2507.06828/) (2025)
- [Denoising Plane Wave Ultrasound Images Using Diffusion Probabilistic Models](https://mlsanity.com/paper/2408.10987/) (2024)
- [CABLD: Contrast-Agnostic Brain Landmark Detection with Consistency-Based Regularization](https://mlsanity.com/paper/2411.17845/) (2024)
- [Lightweight Physics-Aware Zero-Shot Ultrasound Plane-Wave Denoising](https://mlsanity.com/paper/2506.21499/) (2025)
- [From Narrow to Wide: Autoencoding Transformers for Ultrasound Bandwidth Recovery](https://mlsanity.com/paper/2511.02938/) (2025)

## Abstract (arXiv)

One of the primary sources of suboptimal image quality in ultrasound imaging is phase aberration. It is caused by spatial changes in sound speed over a heterogeneous medium, which disturbs the transmitted waves and prevents coherent summation of echo signals. Obtaining non-aberrated ground truths in real-world scenarios can be extremely challenging, if not impossible. This challenge hinders the performance of deep learning-based techniques due to the domain shift between simulated and experimental data. Here, for the first time, we propose a deep learning-based method that does not require ground truth to correct the phase aberration problem and, as such, can be directly trained on real data. We train a network wherein both the input and target output are randomly aberrated radio frequency (RF) data. Moreover, we demonstrate that a conventional loss function such as mean square error is inadequate for training such a network to achieve optimal performance. Instead, we propose an adaptive mixed loss function that employs both B-mode and RF data, resulting in more efficient convergence and enhanced performance. Finally, we publicly release our dataset, comprising over 180,000 aberrated single plane-wave images (RF data), wherein phase aberrations are modeled as near-field phase screens. Although not utilized in the proposed method, each aberrated image is paired with its corresponding aberration profile and the non-aberrated version, aiming to mitigate the data scarcity problem in developing deep learning-based techniques for phase aberration correction.