Distributed Tomographic Reconstruction with Quantization

TL;DR

This paper presents a scalable decentralized tomographic reconstruction method using ADMM with quantization, reducing communication overhead and memory use while maintaining reconstruction quality.

Contribution

It introduces a novel decentralized ADMM algorithm with configurable quantization techniques to improve efficiency and scalability in distributed tomographic reconstruction.

Findings

Quantization techniques reduce communication costs.

The method maintains high reconstruction accuracy.

Tradeoffs between communication, memory, and accuracy are demonstrated.

Abstract

Conventional tomographic reconstruction typically depends on centralized servers for both data storage and computation, leading to concerns about memory limitations and data privacy. Distributed reconstruction algorithms mitigate these issues by partitioning data across multiple nodes, reducing server load and enhancing privacy. However, these algorithms often encounter challenges related to memory constraints and communication overhead between nodes. In this paper, we introduce a decentralized Alternating Directions Method of Multipliers (ADMM) with configurable quantization. By distributing local objectives across nodes, our approach is highly scalable and can efficiently reconstruct images while adapting to available resources. To overcome communication bottlenecks, we propose two quantization techniques based on K-means clustering and JPEG compression. Numerical experiments with benchmark images illustrate the tradeoffs between communication efficiency, memory use, and reconstruction accuracy.