cs.CVNov 16, 2026

Flexible Multi-Stack Super-Resolution of Clinical Brain MRI Using Hetero-Orientation Variational Encoding: Expert Reader Evaluation in a Nigerian Cohort

Authors: Kabir Hamzah Muhammad, Lorena Garcia-Foncillas Macias, Soumya Snigdha Kundu, Emily Guilhem, Jon Cleary, Amal Saleh Nour, Yodit Abraham Yaynishet, Chinasa Kalaiwo, 

Organizations: School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom · Medical Artificial Intelligence, Crestview Radiology Ltd., Lagos, Nigeria · King’s College Hospital NHS Foundation Trust, London, United Kingdom · Department of Radiology, Guy’s and St. Thomas’ NHS Foundation Trust, London, United Kingdom · 

Abstract

High-resolution brain MRI is important for neuroradiological assessment, yet routine clinical protocols often rely on fast, anisotropic 2D acquisitions, particularly in resource-constrained settings. These acquisitions may differ in orientation, alignment and anatomical coverage, resulting in partially overlapping image stacks. Existing learning-based super-resolution methods typically rely on single, under-constrained inputs or fixed multi-stack configurations with idealised acquisition geometry. We introduce MS-HVED, a sequence-agnostic framework for flexible multi-stack brain MRI super-resolution. Available axial, coronal and sagittal stacks are independently encoded into multi-scale Gaussian posteriors and fused using a field-of-view-aware Product-of-Gaussians formulation that limits contributions from unsupported regions. Physics-informed domain randomisation simulates heterogeneous clinical acquisition conditions, including obliqueness, partial coverage and imaging artefacts. MS-HVED achieved competitive or superior reconstruction fidelity across synthetic benchmarks and improved downstream tissue segmentation relative to low-resolution inputs. To assess generalisation beyond the training cohorts, we performed external clinical validation on 30 routine brain MRI examinations from a Nigerian cohort, representing an under-represented population in medical imaging research. These examinations formed the largest component of a blinded reader study involving 44 real cases and seven expert neuroradiologists. In the Nigerian cohort, MS-HVED was preferred over the supervised baseline for overall image quality in 187 of 210 paired assessments. Across all clinical cohorts, MS-HVED achieved higher overall-quality scores with all available inputs (5.93 vs. 4.49, p<.001), with the preference persisting when axial or coronal inputs were omitted (p<.001). Code at github.com/cai4cai/ms-hved

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Single-Subject Multi-View MRI Super-Resolution via Implicit Neural Representations

    Mar 23, 2026Heejong Kim, Abhishek Thanki, Roel van Herten +2Autoregressive Image Super-ResolutionMedical Image Super-Resolution

  2. PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution

    Jul 7, 2026Lihua Wei, Huatong Gao, Jia Gong +4Medical Image Super-ResolutionMagnetic Resonance Imaging

  3. Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-Resolution

    Mar 10, 2026Shuting Liu, Lei Zhang, Wei Huang +2Medical Image Super-ResolutionMagnetic Resonance Imaging