# CAHAL: Clinically Applicable resolution enHAncement for Low-resolution MRI scans

arXiv: https://arxiv.org/abs/2604.18781 · HTML: https://mlsanity.com/paper/2604.18781/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 49 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [SynthMorph: learning contrast-invariant registration without acquired images](https://mlsanity.com/paper/2004.10282/) (2020)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation](https://mlsanity.com/paper/2110.14476/) (2021)
- [Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast](https://mlsanity.com/paper/2012.13340/) (2020)
- [AssemblyNet: A large ensemble of CNNs for 3D Whole Brain MRI Segmentation](https://mlsanity.com/paper/1911.09098/) (2019)
- [DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation](https://mlsanity.com/paper/2012.07950/) (2020)
- [A Modality-agnostic Multi-task Foundation Model for Human Brain Imaging](https://mlsanity.com/paper/2509.00549/) (2025)
- [DA-VSR: Domain Adaptable Volumetric Super-Resolution For Medical Images](https://mlsanity.com/paper/2210.05117/) (2022)
- [Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence](https://mlsanity.com/paper/2206.03247/) (2022)
- [Deep grading for MRI-based differential diagnosis of Alzheimer's disease and Frontotemporal dementia](https://mlsanity.com/paper/2211.14096/) (2022)
- [DISGAN: Wavelet-informed Discriminator Guides GAN to MRI Super-resolution with Noise Cleaning](https://mlsanity.com/paper/2308.12084/) (2023)
- [Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization](https://mlsanity.com/paper/2407.15717/) (2024)
- [Learn2Synth: Learning Optimal Data Synthesis Using Hypergradients for Brain Image Segmentation](https://mlsanity.com/paper/2411.16719/) (2024)
- [DeepCERES: A Deep learning method for cerebellar lobule segmentation using ultra-high resolution multimodal MRI](https://mlsanity.com/paper/2401.12074/) (2024)
- [vol2Brain: A new online Pipeline for whole Brain MRI analysis](https://mlsanity.com/paper/2202.03920/) (2022)
- [MoEDiff-SR: Mixture of Experts-Guided Diffusion Model for Region-Adaptive MRI Super-Resolution](https://mlsanity.com/paper/2504.07308/) (2025)

## Abstract (arXiv)

Large-scale automated morphometric analysis of brain MRI is limited by the thick-slice, anisotropic acquisitions prevalent in routine clinical practice. Existing generative super-resolution (SR) methods produce visually compelling isotropic volumes but often introduce anatomical hallucinations, systematic volumetric overestimation, and structural distortions that compromise downstream quantitative analysis and diagnostic safety. To address this, we propose CAHAL (Clinically Applicable resolution enHAncement for Low-resolution MRI scans), a hallucination-robust, physics-informed resolution enhancement framework that operates directly in the patient's native acquisition space. CAHAL employs a deterministic bivariate Mixture of Experts (MoE) architecture routing each input through specialised residual 3D U-Net experts conditioned on both volumetric resolution and acquisition anisotropy, two independent descriptors of clinical MRI acquisition. Experts are optimised with a composite loss combining edge-penalised spatial reconstruction, Fourier-domain spectral coherence matching, and a segmentation-guided semantic consistency constraint. Training pairs are generated on-the-fly via physics-based degradation sampled from a large-scale real-world database, ensuring robust generalisation. Validated on T1-weighted and FLAIR sequences against generative baselines, CAHAL achieves state-of-the-art results, improving the best related methods in terms of accuracy and efficiency.