# Efficient multi-class fetal brain segmentation in high resolution MRI reconstructions with noisy labels

arXiv: https://arxiv.org/abs/2009.06275 · HTML: https://mlsanity.com/paper/2009.06275/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation](https://mlsanity.com/paper/2107.03846/) (2021)
- [Learning to segment fetal brain tissue from noisy annotations](https://mlsanity.com/paper/2203.14962/) (2022)
- [Synthetic magnetic resonance images for domain adaptation: Application to fetal brain tissue segmentation](https://mlsanity.com/paper/2111.04737/) (2021)
- [Detailed delineation of the fetal brain in diffusion MRI via multi-task learning](https://mlsanity.com/paper/2409.06716/) (2024)
- [An automatic pipeline for atlas-based fetal and neonatal brain segmentation and analysis](https://mlsanity.com/paper/2205.07575/) (2022)
- [Domain generalization in fetal brain MRI segmentation with multi-reconstruction augmentation](https://mlsanity.com/paper/2211.14282/) (2022)
- [Multi-task learning for joint weakly-supervised segmentation and aortic arch anomaly classification in fetal cardiac MRI](https://mlsanity.com/paper/2311.07234/) (2023)

## Abstract (arXiv)

Segmentation of the developing fetal brain is an important step in quantitative analyses. However, manual segmentation is a very time-consuming task which is prone to error and must be completed by highly specialized indi-viduals. Super-resolution reconstruction of fetal MRI has become standard for processing such data as it improves image quality and resolution. However, dif-ferent pipelines result in slightly different outputs, further complicating the gen-eralization of segmentation methods aiming to segment super-resolution data. Therefore, we propose using transfer learning with noisy multi-class labels to automatically segment high resolution fetal brain MRIs using a single set of seg-mentations created with one reconstruction method and tested for generalizability across other reconstruction methods. Our results show that the network can auto-matically segment fetal brain reconstructions into 7 different tissue types, regard-less of reconstruction method used. Transfer learning offers some advantages when compared to training without pre-initialized weights, but the network trained on clean labels had more accurate segmentations overall. No additional manual segmentations were required. Therefore, the proposed network has the potential to eliminate the need for manual segmentations needed in quantitative analyses of the fetal brain independent of reconstruction method used, offering an unbiased way to quantify normal and pathological neurodevelopment.