Comparative Analysis of 3D Convolutional and 2.5D Slice-Conditioned U-Net Architectures for MRI Super-Resolution via Elucidated Diffusion Models

• URL: http://arxiv.org/abs/2603.14667v1
• Date: Sun, 15 Mar 2026 23:48:29 GMT
• Title: Comparative Analysis of 3D Convolutional and 2.5D Slice-Conditioned U-Net Architectures for MRI Super-Resolution via Elucidated Diffusion Models
• Abstract summary: We investigate an elucidated diffusion model (EDM) framework for brain MRI SR.<n>We compare two U-Net backbone architectures: a full 3D convolutional U-Net that processes volumetric patches with 3D convolutions and multi-head self-attention, and a 2.5D slice-conditioned U-Net that super-resolves each slice independently while conditioning on an adjacent slice for inter-slice context.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Magnetic resonance imaging (MRI) super-resolution (SR) methods that computationally enhance low-resolution acquisitions to approximate high-resolution quality offer a compelling alternative to expensive high-field scanners. In this work we investigate an elucidated diffusion model (EDM) framework for brain MRI SR and compare two U-Net backbone architectures: (i) a full 3D convolutional U-Net that processes volumetric patches with 3D convolutions and multi-head self-attention, and (ii) a 2.5D slice-conditioned U-Net that super-resolves each slice independently while conditioning on an adjacent slice for inter-slice context. Both models employ continuous-sigma noise conditioning following Karras et al. and are trained on the NKI cohort of the FOMO60K dataset. On a held-out test set of 5 subjects (6 volumes, 993 slices), the 3D model achieves 37.75 dB PSNR, 0.997 SSIM, and 0.020 LPIPS, improving on the off-the-shelf pretrained EDSR baseline (35.57 dB / 0.024 LPIPS) and the 2.5D variant (35.82 dB) across all three metrics under the same test data and degradation pipeline.

Related papers

• Cross-Modality Structural Guidance in 3D Latent Diffusion for Robust FLAIR Super-Resolution [0.2959600957981674]
  High-resolution (HR) MRI acquisition is often hampered by scan time constraints.<n>Deep learning-based super-resolution methods often hallucinate anatomical details, which can compromise brain structural integrity.<n>We introduce MR-DiffuSR, a Multi-Resolution Diffusion-based Super-Resolution framework that incorporates HR T1w structural image priors to guide the restoration of thick-slice FLAIR scans.
  arXiv  Detail & Related papers  (2026-06-24T00:26:01Z)
• 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)
• DALight-3D: A Lightweight 3D U-Net for Brain Tumor Segmentation from Multi-Modal MRI [0.0]
  DALight-3D is a compact 3D U-Net variant that combines depthwise separable 3D convolutions, identifier-conditioned normalization, cross-slice attention, and adaptive skip fusion.<n>Results show DALight-3D offers a favorable accuracy-efficiency trade-off within the present benchmark setting.
  arXiv  Detail & Related papers  (2026-05-06T05:54:44Z)
• VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation [5.653007117827187]
  Diffusion models produce high-quality synthetic data but suffer from slow inference.<n>We propose 3D Variable-Step Denoising Diffusion Probabilistic Model (VS-DDPM)<n>We tested our approach on four tasks (missing MRI, tumor removal, MRI-to-sCT, and CBCT-to-sCT) within the BraTS2025 and SynthRAD2025 challenges.
  arXiv  Detail & Related papers  (2026-04-24T18:32:22Z)
• Halfway to 3D: Ensembling 2.5D and 3D Models for Robust COVID-19 CT Diagnosis [5.645096759437525]
  We propose a deep learning framework for COVID-19 detection and disease classification from chest CT scans.<n>The framework integrates both 2.5D and 3D representations to capture complementary slice-level and volumetric information.<n>Experiments on the PHAROS-AIF-MIH benchmark demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2026-03-16T05:24:10Z)
• Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification [69.87877580725768]
  Multimodal Visual Surrogate Compression (MVSC) learns to compress and adapt large 3D sMRI volumes into compact 2D features.<n>MVSC has two key components: a Volume Context that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner.
  arXiv  Detail & Related papers  (2026-01-29T13:05:46Z)
• Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks [23.30947697113457]
  We address the challenge of parameter-efficient fine-tuning (PEFT) for 3D U-Net-based denoising diffusion probabilistic models (DDPMs)<n>We propose TenVOO, a novel PEFT method specifically designed for fine-tuning DDPMs with 3D convolutional backbones.<n>Our results demonstrate that TenVOO achieves state-of-the-art performance in multi-scale similarity index measure (MS-SSIM)
  arXiv  Detail & Related papers  (2025-07-24T05:51:51Z)
• Schrödinger Diffusion Driven Signal Recovery in 3T BOLD fMRI Using Unmatched 7T Observations [1.8091533096543726]
  We introduce a new computational approach designed to enhance the quality of 3T BOLD fMRI acquisitions.<n>We employ a lightweight, unsupervised Schr"odinger Bridge framework to infer a high-SNR, high-resolution counterpart of the 3T data.<n>Our findings suggest that it is feasible to computationally approximate 7T-level quality from standard 3T acquisitions.
  arXiv  Detail & Related papers  (2025-04-01T17:41:24Z)
• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets.<n>Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection [64.93675471780209]
  We present V2X-R, the first simulated V2X dataset incorporating LiDAR, camera, and 4D radar.<n>V2X-R contains 12,079 scenarios with 37,727 frames of LiDAR and 4D radar point clouds, 150,908 images, and 170,859 annotated 3D vehicle bounding boxes.<n>We propose a novel cooperative LiDAR-4D radar fusion pipeline for 3D object detection and implement it with various fusion strategies.
  arXiv  Detail & Related papers  (2024-11-13T07:41:47Z)
• Learning to Discretize Denoising Diffusion ODEs [41.50816120270017]
  Diffusion Probabilistic Models (DPMs) are generative models showing competitive performance in various domains.<n>We propose LD3, a lightweight framework designed to learn the optimal time discretization for sampling.<n>We demonstrate analytically and empirically that LD3 improves sampling efficiency with much less computational overhead.
  arXiv  Detail & Related papers  (2024-05-24T12:51:23Z)
• Segmenting white matter hyperintensities on isotropic three-dimensional Fluid Attenuated Inversion Recovery magnetic resonance images: Assessing deep learning tools on norwegian imaging database [0.0]
  White matter hyperintensities (WMHs) are a hallmark of cerebral small vessel disease and Alzheimer's disease (AD) Current study details the deployment of deep learning tools to enable automated WMH segmentation and characterization from 3D FLAIR-weighted images.
  arXiv  Detail & Related papers  (2022-07-18T09:36:44Z)
• 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)
• Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices [48.85784310158493]
  We propose a Modified Pseudo-3D Feature Pyramid Network (MP3D FPN) to efficiently extract 3D context enhanced 2D features for universal lesion detection in CT slices. With the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset. The proposed 3D pre-trained weights can potentially be used to boost the performance of other 3D medical image analysis tasks.
  arXiv  Detail & Related papers  (2020-12-16T07:11:16Z)
• Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE [66.63629641650572]
  We propose a method to model 3D MR brain volumes distribution by combining a 2D slice VAE with a Gaussian model that captures the relationships between slices. We also introduce a novel evaluation method for generated volumes that quantifies how well their segmentations match those of true brain anatomy.
  arXiv  Detail & Related papers  (2020-07-09T13:23:15Z)

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.