English

Deep Learning for MRI Slice Interpolation: The Critical Role of Problem Formulation

Image and Video Processing 2026-05-19 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Through-plane resolution in clinical MRI is typically much coarser than in-plane resolution, limiting diagnostic utility. This work investigates deep learning approaches to interpolate intermediate MRI slices in prostate imaging, effectively doubling through-plane resolution. I evaluated five architectures (CNN, U-Net, two GAN variants, and DDPM) and discovered that problem formulation has dramatically more impact than architectural complexity. By reformulating the interpolation task to use adjacent slices (i-1, i+1) rather than distant slices (i-2, i+2), I achieved a 58% improvement in SSIM performance across all deterministic architectures. The U-Net model achieved the best results with PSNR of 30.08 dB and SSIM of 0.898, representing a 10.1% improvement over linear interpolation baseline. A DDPM was also evaluated but showed poor reconstruction quality due to fundamental mismatch between stochastic generation and deterministic reconstruction requirements. These findings demonstrate that problem formulation can have 290x more impact than architectural sophistication in medical imaging tasks.

Keywords

Cite

@article{arxiv.2605.16476,
  title  = {Deep Learning for MRI Slice Interpolation: The Critical Role of Problem Formulation},
  author = {Shamit Savant},
  journal= {arXiv preprint arXiv:2605.16476},
  year   = {2026}
}

Comments

10 pages main text, 21 pages total with supplementary, 8 figures, supplementary material included

R2 v1 2026-07-22T07:15:31.350Z