Robustness and Diagnostic Performance of Super-Resolution Fetal Brain MRI

• URL: http://arxiv.org/abs/2509.10257v1
• Date: Fri, 12 Sep 2025 13:59:23 GMT
• Title: Robustness and Diagnostic Performance of Super-Resolution Fetal Brain MRI
• Abstract summary: Super-resolution reconstruction (SRR) methods combine slice-to-volume registration and super-resolution techniques to generate high-resolution (HR) 3D volumes.<n>In this study, we applied three state-of-the-art SRR methods - NiftyMIC, SVRTK, and NeSVoR - to 140 fetal brain MRI scans.<n>NeSVoR demonstrated the highest and most consistent reconstruction success rate (>90%) across both HC and PC groups.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fetal brain MRI relies on rapid multi-view 2D slice acquisitions to reduce motion artifacts caused by fetal movement. However, these stacks are typically low resolution, may suffer from motion corruption, and do not adequately capture 3D anatomy. Super-resolution reconstruction (SRR) methods aim to address these limitations by combining slice-to-volume registration and super-resolution techniques to generate high-resolution (HR) 3D volumes. While several SRR methods have been proposed, their comparative performance - particularly in pathological cases - and their influence on downstream volumetric analysis and diagnostic tasks remain underexplored. In this study, we applied three state-of-the-art SRR method - NiftyMIC, SVRTK, and NeSVoR - to 140 fetal brain MRI scans, including both healthy controls (HC) and pathological cases (PC) with ventriculomegaly (VM). Each HR reconstruction was segmented using the BoUNTi algorithm to extract volumes of nine principal brain structures. We evaluated visual quality, SRR success rates, volumetric measurement agreement, and diagnostic classification performance. NeSVoR demonstrated the highest and most consistent reconstruction success rate (>90%) across both HC and PC groups. Although significant differences in volumetric estimates were observed between SRR methods, classification performance for VM was not affected by the choice of SRR method. These findings highlight NeSVoR's robustness and the resilience of diagnostic performance despite SRR-induced volumetric variability.

Related papers

• Cardiac MRI Through-Plane Super-Resolution Guided by Reference and Memory [4.642439193156724]
  Clinical cardiac MRI is commonly acquired with high in-plane resolution but coarse through-plane resolution.<n>We propose STRMSR, a reference- and memory-guided through-plane super-resolution framework.<n>Our method uses coarse-to-fine contextual matching to establish robust correspondence between low-resolution target and reference/memory images.
  arXiv  Detail & Related papers  (2026-07-08T16:04:06Z)
• D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities [54.87947751720332]
  We propose a novel segmentation model D3Seg to maintain stable performance under missing-modality settings.<n>The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing modality configurations.
  arXiv  Detail & Related papers  (2026-05-21T09:55:42Z)
• Interpretable Motion Artificat Detection in structural Brain MRI [2.55957188107151]
  We propose a lightweight and interpretable framework for detecting motion related artifacts in T1weighted brain MRI.<n>The proposed method integrates complementary slice-level (2D) and volume-level (3D) DHoGM features through a parallel decision strategy.<n>Our method was evaluated on the MR-ART and ABIDE datasets under both seen-site and unseen-site conditions.
  arXiv  Detail & Related papers  (2026-03-05T22:34:27Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• SUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction [7.268308489093152]
  We propose an unsupervised iterative SVR-SRR framework for isotropic HR volume reconstruction.<n>A decoding network embedded within a deep image prior framework is incorporated with a comprehensive image degradation model to produce the high-resolution (HR) volume.<n>Experiments conducted on large-magnitude motion-corrupted simulation data and clinical data demonstrate the superior performance of the proposed framework.
  arXiv  Detail & Related papers  (2025-05-23T04:53:59Z)
• Super-resolution of biomedical volumes with 2D supervision [84.5255884646906]
  Masked slice diffusion for super-resolution exploits the inherent equivalence in the data-generating distribution across all spatial dimensions of biological specimens. We focus on the application of SliceR to stimulated histology (SRH), characterized by its rapid acquisition of high-resolution 2D images but slow and costly optical z-sectioning.
  arXiv  Detail & Related papers  (2024-04-15T02:41:55Z)
• Cross-modality Guidance-aided Multi-modal Learning with Dual Attention for MRI Brain Tumor Grading [47.50733518140625]
  Brain tumor represents one of the most fatal cancers around the world, and is very common in children and the elderly. We propose a novel cross-modality guidance-aided multi-modal learning with dual attention for addressing the task of MRI brain tumor grading.
  arXiv  Detail & Related papers  (2024-01-17T07:54:49Z)
• Resolution- and Stimulus-agnostic Super-Resolution of Ultra-High-Field Functional MRI: Application to Visual Studies [1.8327547104097965]
  High-resolution fMRI provides a window into the brain's mesoscale organization. Yet, higher spatial resolution increases scan times, to compensate for the low signal and contrast-to-noise ratio. This work introduces a deep learning-based 3D super-resolution (SR) method for fMRI.
  arXiv  Detail & Related papers  (2023-11-25T03:33:36Z)
• InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model [1.4126798060929953]
  High-resolution (HR) MRI scans obtained from research-grade medical centers provide precise information about imaged tissues. routine clinical MRI scans are typically in low-resolution (LR) End-to-end deep learning methods for MRI super-resolution (SR) have been proposed, but they require re-training each time there is a shift in the input distribution. We propose a novel approach that leverages a state-of-the-art 3D brain generative model, the latent diffusion model (LDM) trained on UK BioBank.
  arXiv  Detail & Related papers  (2023-08-23T23:04:42Z)
• AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI [8.087220876070477]
  We present a novel Affinity Fusion-based Framework for Iteratively Random Motion correction of the multi-slice fetal brain MRI. It learns the sequential motion from multiple stacks of slices and integrates the features between 2D slices and reconstructed 3D volume using affinity fusion. The method accurately estimates the motion regardless of brain orientations and outperforms other state-of-the-art learning-based methods on the simulated motion-corrupted data.
  arXiv  Detail & Related papers  (2022-05-12T02:54:55Z)
• 3-Dimensional Deep Learning with Spatial Erasing for Unsupervised Anomaly Segmentation in Brain MRI [55.97060983868787]
  We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance. We compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance. Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE.
  arXiv  Detail & Related papers  (2021-09-14T09:17:27Z)
• ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning [47.68307909984442]
  Single Image Super-Resolution (SISR) is a technique aimed to obtain high-resolution (HR) details from one single low-resolution input image. Deep learning extracts prior knowledge from big datasets and produces superior MRI images from the low-resolution counterparts.
  arXiv  Detail & Related papers  (2021-02-25T14:52:23Z)
• Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI [47.26574993639482]
  We show improved anomaly segmentation performance and the general capability to obtain much more crisp reconstructions of input data at native resolution. The modeling of the laplacian pyramid further enables the delineation and aggregation of lesions at multiple scales.
  arXiv  Detail & Related papers  (2020-06-23T09:20:42Z)
• 4D Deep Learning for Multiple Sclerosis Lesion Activity Segmentation [49.32653090178743]
  We investigate whether extending this problem to full 4D deep learning using a history of MRI volumes can improve performance. We find that our proposed architecture outperforms previous approaches with a lesion-wise true positive rate of 0.84 at a lesion-wise false positive rate of 0.19.
  arXiv  Detail & Related papers  (2020-04-20T11:41:01Z)

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.