Towards contrast- and pathology-agnostic clinical fetal brain MRI segmentation using SynthSeg
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915748406886400 |
|---|---|
| author | Shang, Ziyao Kaandorp, Misha Payette, Kelly Garcia, Marina Fernandez Licandro, Roxane Langs, Georg Verdera, Jordina Aviles Hutter, Jana Menze, Bjoern Kasprian, Gregor Cuadra, Meritxell Bach Jakab, Andras |
| author_facet | Shang, Ziyao Kaandorp, Misha Payette, Kelly Garcia, Marina Fernandez Licandro, Roxane Langs, Georg Verdera, Jordina Aviles Hutter, Jana Menze, Bjoern Kasprian, Gregor Cuadra, Meritxell Bach Jakab, Andras |
| contents | Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep Learning providing an automated alternative for this otherwise tedious manual process. However, segmentation performances of Convolutional Neural Networks often suffer from domain shift, where the network fails when applied to subjects that deviate from the distribution with which it is trained on. In this work, we aim to train networks capable of automatically segmenting fetal brain MRIs with a wide range of domain shifts pertaining to differences in subject physiology and acquisition environments, in particular shape-based differences commonly observed in pathological cases. We introduce a novel data-driven train-time sampling strategy that seeks to fully exploit the diversity of a given training dataset to enhance the domain generalizability of the trained networks. We adapted our sampler, together with other existing data augmentation techniques, to the SynthSeg framework, a generator that utilizes domain randomization to generate diverse training data. We ran thorough experimentations and ablation studies on a wide range of training/testing data to test the validity of the approaches. Our networks achieved notable improvements in the segmentation quality on testing subjects with intense anatomical abnormalities (p < 1e-4), though at the cost of a slighter decrease in performance in cases with fewer abnormalities. Our work also lays the foundation for future works on creating and adapting data-driven sampling strategies for other training pipelines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10244 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards contrast- and pathology-agnostic clinical fetal brain MRI segmentation using SynthSeg Shang, Ziyao Kaandorp, Misha Payette, Kelly Garcia, Marina Fernandez Licandro, Roxane Langs, Georg Verdera, Jordina Aviles Hutter, Jana Menze, Bjoern Kasprian, Gregor Cuadra, Meritxell Bach Jakab, Andras Image and Video Processing Computer Vision and Pattern Recognition Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep Learning providing an automated alternative for this otherwise tedious manual process. However, segmentation performances of Convolutional Neural Networks often suffer from domain shift, where the network fails when applied to subjects that deviate from the distribution with which it is trained on. In this work, we aim to train networks capable of automatically segmenting fetal brain MRIs with a wide range of domain shifts pertaining to differences in subject physiology and acquisition environments, in particular shape-based differences commonly observed in pathological cases. We introduce a novel data-driven train-time sampling strategy that seeks to fully exploit the diversity of a given training dataset to enhance the domain generalizability of the trained networks. We adapted our sampler, together with other existing data augmentation techniques, to the SynthSeg framework, a generator that utilizes domain randomization to generate diverse training data. We ran thorough experimentations and ablation studies on a wide range of training/testing data to test the validity of the approaches. Our networks achieved notable improvements in the segmentation quality on testing subjects with intense anatomical abnormalities (p < 1e-4), though at the cost of a slighter decrease in performance in cases with fewer abnormalities. Our work also lays the foundation for future works on creating and adapting data-driven sampling strategies for other training pipelines. |
| title | Towards contrast- and pathology-agnostic clinical fetal brain MRI segmentation using SynthSeg |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10244 |