DRIFTS: Optimizing Domain Randomization with Synthetic Data and Weight Interpolation for Fetal Brain Tissue Segmentation

• URL: http://arxiv.org/abs/2411.06842v2
• Date: Wed, 04 Jun 2025 18:56:48 GMT
• Title: DRIFTS: Optimizing Domain Randomization with Synthetic Data and Weight Interpolation for Fetal Brain Tissue Segmentation
• Authors: Vladyslav Zalevskyi, Thomas Sanchez, Margaux Roulet, Hélène Lajous, Jordina Aviles Verdera, Roxane Licandro, Georg Langs, Gregor Kasprian, Jana Hutter, Hamza Kebiri, Meritxell Bach Cuadra,
• Abstract summary: We show how to maximize the out-of-domain generalization potential of SynthSegbased methods in fetal brain MRI.<n>We propose DRIFTS as an effective and practical solution for single-source domain generalization.
• Score: 1.7134826630987745
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fetal brain tissue segmentation in magnetic resonance imaging (MRI) is a crucial tool that supports understanding of neurodevelopment, yet it faces challenges due to the heterogeneity of data coming from different scanners and settings, as well as data scarcity. Recent approaches based on domain randomization, like SynthSeg, have shown great potential for single-source domain generalization by simulating images with randomized contrast and image resolution from the label maps. In this work, we investigate how to maximize the out-of-domain (OOD) generalization potential of SynthSegbased methods in fetal brain MRI. Specifically, we demonstrate that the simple Gaussian mixture models employed in FetalSynthSeg outperform physics-informed generation methods in terms of OOD generalization. We further show that incorporating intensity clustering significantly enhances generalization in settings with limited label classes by producing more realistic synthetic data. By combining synthetic pretraining with fine-tuning on real images and applying weight-space interpolation between the two models, we propose DRIFTS as an effective and practical solution for single-source domain generalization. DRIFTS consistently outperforms current state-of-the-art models across multiple benchmarks and is, to our knowledge, the first method to achieve accurate brain tissue segmentation on fetal T1-weighted images. We validate our approach on 308 subjects from four datasets acquired at three different sites, covering a range of scanner field strengths (0.55T to 3T) and both T1w and T2w modalities. We conclude with five practical recommendations to guide the development of SynthSeg-based methods for other organs and imaging modalities.

Related papers

• Diffusion Bridge Models for 3D Medical Image Translation [15.751276389741877]
  We propose a diffusion bridge model for 3D brain image translation between T1w MRI and DTI modalities.<n>Our model learns to generate high-quality DTI fractional anisotropy images from T1w images and vice versa, enabling cross-modality data augmentation.
  arXiv  Detail & Related papers  (2025-04-21T17:49:06Z)
• MRGen: Segmentation Data Engine For Underrepresented MRI Modalities [59.61465292965639]
  Training medical image segmentation models for rare yet clinically significant imaging modalities is challenging due to the scarcity of annotated data. This paper investigates leveraging generative models to synthesize training data, to train segmentation models for underrepresented modalities.
  arXiv  Detail & Related papers  (2024-12-04T16:34:22Z)
• Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data [0.15749416770494706]
  We introduce two physics-constrained approaches to generate synthetic quantitative MRI (qMRI) images.<n>Our first method, $textttqATLAS$, trains a neural network to estimate qMRI maps from standard MPRAGE images.<n>The second method, $textttq Synth$, synthesises qMRI maps directly from tissue labels.
  arXiv  Detail & Related papers  (2024-12-04T13:52:05Z)
• An Ensemble Approach for Brain Tumor Segmentation and Synthesis [0.12777007405746044]
  The integration of machine learning in magnetic resonance imaging (MRI) is proving to be incredibly effective. Deep learning models utilize multiple layers of processing to capture intricate details of complex data. We propose a deep learning framework that ensembles state-of-the-art architectures to achieve accurate segmentation.
  arXiv  Detail & Related papers  (2024-11-26T17:28:51Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging [59.78761085714715]
  This study proposes a novel Siamese Dual-Resolution Transformer (SDR-Former) framework for liver lesion classification. The proposed framework has been validated through comprehensive experiments on two clinical datasets. To support the scientific community, we are releasing our extensive multi-phase MR dataset for liver lesion analysis to the public.
  arXiv  Detail & Related papers  (2024-02-27T06:32:56Z)
• GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images [79.39247661907397]
  We introduce an effective framework Generalizable Model-based Neural Radiance Fields to synthesize free-viewpoint images. Specifically, we propose a geometry-guided attention mechanism to register the appearance code from multi-view 2D images to a geometry proxy.
  arXiv  Detail & Related papers  (2023-03-24T03:32:02Z)
• MRIS: A Multi-modal Retrieval Approach for Image Synthesis on Diverse Modalities [19.31577453889188]
  We develop an approach based on multi-modal metric learning to synthesize images of diverse modalities. We test our approach by synthesizing cartilage thickness maps obtained from 3D magnetic resonance (MR) images using 2D radiographs.
  arXiv  Detail & Related papers  (2023-03-17T20:58:55Z)
• Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
  We propose a domain transfer approach based on conditional invertible neural networks (cINNs) Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood. Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
  arXiv  Detail & Related papers  (2023-03-17T18:00:27Z)
• High-fidelity Direct Contrast Synthesis from Magnetic Resonance Fingerprinting [28.702553164811473]
  We propose a supervised learning-based method that directly synthesizes contrast-weighted images from the MRF data without going through the quantitative mapping and spin-dynamics simulation. In-vivo experiments demonstrate excellent image quality compared to simulation-based contrast synthesis and previous DCS methods, both visually as well as by quantitative metrics.
  arXiv  Detail & Related papers  (2022-12-21T07:11:39Z)
• Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANs [0.5039813366558306]
  We propose a method for generating labeled data for the application of supervised deep-learning (DL) training. The image synthesis consists of label deformation and label-to-image translation tasks. We demonstrate that such an approach could provide a solution to diversify and enrich an available database of cardiac MR images.
  arXiv  Detail & Related papers  (2022-09-09T10:17:49Z)
• Subject-Specific Lesion Generation and Pseudo-Healthy Synthesis for Multiple Sclerosis Brain Images [1.7328025136996081]
  We present a novel generative method for modelling the local lesion characteristics. It can generate synthetic lesions on healthy images and synthesize subject-specific pseudo-healthy images from pathological images. The proposed method can be used as a data augmentation module to generate synthetic images for training brain image segmentation networks.
  arXiv  Detail & Related papers  (2022-08-03T15:12:55Z)
• Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis [68.5287824124996]
  We present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images. We apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem. Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-03-29T08:41:17Z)
• Robust Segmentation of Brain MRI in the Wild with Hierarchical CNNs and no Retraining [1.0499611180329802]
  Retrospective analysis of brain MRI scans acquired in the clinic has the potential to enable neuroimaging studies with sample sizes much larger than those found in research datasets. Recent advances in convolutional neural networks (CNNs) and domain randomisation for image segmentation may enable morphometry of clinical MRI at scale. We show that SynthSeg is generally robust, but frequently falters on scans with low signal-to-noise ratio or poor tissue contrast. We propose SynthSeg+, a novel method that greatly mitigates these problems using a hierarchy of conditional segmentation and denoising CNNs.
  arXiv  Detail & Related papers  (2022-03-03T19:18:28Z)
• Functional Magnetic Resonance Imaging data augmentation through conditional ICA [44.483210864902304]
  We introduce Conditional Independent Components Analysis (Conditional ICA): a fast functional Magnetic Resonance Imaging (fMRI) data augmentation technique. We show that Conditional ICA is successful at synthesizing data indistinguishable from observations, and that it yields gains in classification accuracy in brain decoding problems.
  arXiv  Detail & Related papers  (2021-07-11T22:36:14Z)
• You Only Need Adversarial Supervision for Semantic Image Synthesis [84.83711654797342]
  We propose a novel, simplified GAN model, which needs only adversarial supervision to achieve high quality results. We show that images synthesized by our model are more diverse and follow the color and texture of real images more closely.
  arXiv  Detail & Related papers  (2020-12-08T23:00:48Z)
• Fader Networks for domain adaptation on fMRI: ABIDE-II study [68.5481471934606]
  We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.
  arXiv  Detail & Related papers  (2020-10-14T16:50:50Z)
• Lesion Mask-based Simultaneous Synthesis of Anatomic and MolecularMR Images using a GAN [59.60954255038335]
  The proposed framework consists of a stretch-out up-sampling module, a brain atlas encoder, a segmentation consistency module, and multi-scale label-wise discriminators. Experiments on real clinical data demonstrate that the proposed model can perform significantly better than the state-of-the-art synthesis methods.
  arXiv  Detail & Related papers  (2020-06-26T02:50:09Z)
• Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study [55.78588835407174]
  We show that high quality, diverse and realistic-looking diffusion-weighted magnetic resonance images can be synthesized using deep generative models. We present two networks, the Introspective Variational Autoencoder and the Style-Based GAN, that qualify for data augmentation in the medical field.
  arXiv  Detail & Related papers  (2020-06-24T18:00:01Z)
• Modeling Shared Responses in Neuroimaging Studies through MultiView ICA [94.31804763196116]
  Group studies involving large cohorts of subjects are important to draw general conclusions about brain functional organization. We propose a novel MultiView Independent Component Analysis model for group studies, where data from each subject are modeled as a linear combination of shared independent sources plus noise. We demonstrate the usefulness of our approach first on fMRI data, where our model demonstrates improved sensitivity in identifying common sources among subjects.
  arXiv  Detail & Related papers  (2020-06-11T17:29:53Z)
• Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image Synthesis [30.64847799586407]
  We propose a multi-modality generative adversarial network (MGAN) to synthesize three high-quality MR modalities (FLAIR, T1 and T1ce) from one MR modality T2 simultaneously. The experimental results show that the quality of the synthesized images is better than the one synthesized by the baseline model, pix2pix.
  arXiv  Detail & Related papers  (2020-05-02T21:33:15Z)
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation [84.7571086566595]
  We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
  arXiv  Detail & Related papers  (2020-03-31T11:50:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.