# Robustness of breast lesion segmentation under MRI undersampling improves with k-space-aware deep learning

arXiv: https://arxiv.org/abs/2605.22327 · HTML: https://mlsanity.com/paper/2605.22327/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 10 of 10)

- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [Learning a Variational Network for Reconstruction of Accelerated MRI Data](https://mlsanity.com/paper/1704.00447/) (2017)
- [SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation](https://mlsanity.com/paper/2203.06823/) (2022)
- [A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations](https://mlsanity.com/paper/2406.13844/) (2024)
- [Radiologist-level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans](https://mlsanity.com/paper/2009.09827/) (2020)
- [Classification, Regression and Segmentation directly from k-Space in Cardiac MRI](https://mlsanity.com/paper/2407.20108/) (2024)
- [k-strip: A novel segmentation algorithm in k-space for the application of skull stripping](https://mlsanity.com/paper/2205.09706/) (2022)
- [fastMRI Breast: A publicly available radial k-space dataset of breast dynamic contrast-enhanced MRI](https://mlsanity.com/paper/2406.05270/) (2024)
- [Direct Cardiac Segmentation from Undersampled K-space Using Transformers](https://mlsanity.com/paper/2406.00192/) (2024)
- [Domain Influence in MRI Medical Image Segmentation: spatial versus k-space inputs](https://mlsanity.com/paper/2407.01367/) (2024)

## Abstract (arXiv)

Purpose: To assess whether breast lesion segmentation can be learned directly from acquired MRI k-space, and whether doing so improves robustness when data are accelerated or noisy. Materials and Methods: This retrospective study used public breast dynamic contrast-enhanced MRI (DCE-MRI) datasets with acquired and synthetic k-space, together with a within-dataset synthetic control. We compared four 3D U-Net variants: a hybrid k-space-to-image model, a native k-space model, and magnitude and complex image-space baselines. Models were evaluated under increasing undersampling and added complex Gaussian k-space noise. The primary outcome was patient-level Dice similarity coefficient under cross-validation, with the hybrid model prespecified as the main comparison against the magnitude image-space baseline. Results: At full sampling, the hybrid and image-space models performed similarly. As acceleration increased, the hybrid model retained substantially more segmentation accuracy and significantly outperformed the magnitude image-space baseline across moderate to high undersampling levels. The same pattern was observed when noise was added directly to k-space: the hybrid model degraded more slowly, whereas the image-space baseline failed under heavier noise. This advantage was reproduced in the within-dataset synthetic control. Feature analysis suggested that the k-space stage and image-space stage played complementary roles, with frequency-domain filtering concentrated before image-domain lesion localization. Conclusion: K-space-aware deep learning improves the robustness of breast lesion segmentation under MRI undersampling and k-space noise, while matching image-space methods at full sampling.