Super-Resolution Enhancement of Medical Images Based on Diffusion Model: An Optimization Scheme for Low-Resolution Gastric Images

TL;DR

This paper presents a diffusion model-based super-resolution framework to enhance low-resolution capsule endoscopy images, improving detail preservation and structural fidelity over traditional and GAN-based methods.

Contribution

It introduces a diffusion model approach for medical image super-resolution that outperforms existing GAN-based methods in stability and structural accuracy.

Findings

Achieves higher PSNR and SSIM compared to bicubic and GAN-based methods.

Improves preservation of anatomical and pathological details.

Demonstrates stable training and structural fidelity with diffusion models.

Abstract

Capsule endoscopy has enabled minimally invasive gastrointestinal imaging, but its clinical utility is limited by the inherently low resolution of captured images due to hardware, power, and transmission constraints. This limitation hampers the identification of fine-grained mucosal textures and subtle pathological features essential for early diagnosis. This work investigates a diffusion-based super-resolution framework to enhance capsule endoscopy images in a data-driven and anatomically consistent manner. We adopt the SR3 (Super-Resolution via Repeated Refinement) framework built upon Denoising Diffusion Probabilistic Models (DDPMs) to learn a probabilistic mapping from low-resolution to high-resolution images. Unlike GAN-based approaches that often suffer from training instability and hallucination artifacts, diffusion models provide stable likelihood-based training and improved structural fidelity. The HyperKvasir dataset, a large-scale publicly available gastrointestinal endoscopy dataset, is used for training and evaluation. Quantitative results demonstrate that the proposed method significantly outperforms bicubic interpolation and GAN-based super-resolution methods such as ESRGAN, achieving PSNR of 27.5 dB and SSIM of 0.65 for a baseline model, and improving to 29.3 dB and 0.71 with architectural enhancements including attention mechanisms. Qualitative results show improved preservation of anatomical boundaries, vascular patterns, and lesion structures. These findings indicate that diffusion-based super-resolution is a promising approach for enhancing non-invasive medical imaging, particularly in capsule endoscopy where image resolution is fundamentally constrained.