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

TL;DR

This study demonstrates that deep learning models aware of MRI k-space data significantly enhance the robustness of breast lesion segmentation under undersampling and noise, outperforming traditional image-space methods in challenging conditions.

Contribution

The paper introduces a hybrid k-space-to-image deep learning model that improves segmentation robustness in MRI under acceleration and noise, a novel approach compared to existing image-space models.

Findings

Hybrid k-space-to-image model outperforms image-space baseline under undersampling.

Model degrades more slowly with added k-space noise.

Frequency-domain filtering complements image localization.

Abstract

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.