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

TL;DR

This paper demonstrates that reformulating the problem of MRI slice interpolation significantly outperforms architectural complexity, with a 58% SSIM improvement, emphasizing the importance of problem formulation in deep learning for medical imaging.

Contribution

It shows that problem formulation has a greater impact than model architecture in MRI slice interpolation, with a new formulation improving SSIM by 58%.

Findings

Reformulating the interpolation task improves SSIM by 58%.

U-Net achieved PSNR of 30.08 dB and SSIM of 0.898.

DDPM performed poorly due to mismatch with deterministic tasks.

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.