Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Review

2025-05-09

AI Summary

Diffusion models face high computational costs during training and inference, hindering their clinical deployment in medical imaging. This paper presents a systematic review and, for the first time, a unified analysis of three mainstream architectures—denoising diffusion probabilistic models (DDPMs), latent diffusion models (LDMs), and wavelet diffusion models (WDMs)—focusing on efficiency optimization strategies tailored to medical imaging. It clarifies the inherent trade-offs among image fidelity, inference latency, and hardware resource consumption across these models. The study identifies mechanistic approaches by which each architecture bridges the computational complexity gap, proposes scalable, lightweight modifications for clinical deployment, and establishes a comprehensive evaluation framework that jointly assesses generative quality and clinical utility. By integrating theoretical insights with practical design principles, this work provides both foundational guidance and an actionable roadmap for developing efficient, reliable, and accessible diffusion models in medical imaging.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

The diffusion model has recently emerged as a potent approach in computer vision, demonstrating remarkable performances in the field of generative artificial intelligence. Capable of producing high-quality synthetic images, diffusion models have been successfully applied across a range of applications. However, a significant challenge remains with the high computational cost associated with training and generating these models. This study focuses on the efficiency and inference time of diffusion-based generative models, highlighting their applications in both natural and medical imaging. We present the most recent advances in diffusion models by categorizing them into three key models: the Denoising Diffusion Probabilistic Model (DDPM), the Latent Diffusion Model (LDM), and the Wavelet Diffusion Model (WDM). These models play a crucial role in medical imaging, where producing fast, reliable, and high-quality medical images is essential for accurate analysis of abnormalities and disease diagnosis. We first investigate the general framework of DDPM, LDM, and WDM and discuss the computational complexity gap filled by these models in natural and medical imaging. We then discuss the current limitations of these models as well as the opportunities and future research directions in medical imaging.

Problem

• Reducing computational cost of diffusion models in medical imaging
• Improving efficiency and inference time of generative models
• Enhancing quality and speed of synthetic medical images

Innovation

• Denoising Diffusion Probabilistic Model (DDPM)
• Latent Diffusion Model (LDM)
• Wavelet Diffusion Model (WDM)