Practical Lossless Volumetric Medical Image Compression via Tri-plane Context Tree Learning

2026-08-13

AI Summary

This study addresses the inefficiency of traditional methods and the high computational overhead of deep learning approaches in lossless volumetric medical image compression. We propose the Tri-plane Context Tree method, which decomposes 3D modeling into 2D orthogonal planes and integrates adaptive binary trees with the Minimum Description Length criterion to achieve neural-network-free, data-adaptive modeling and entropy coding. Experimental results demonstrate that this approach attains compression performance comparable to state-of-the-art deep learning methods across multiple datasets while significantly reducing computational costs and improving encoding speed. Consequently, this work establishes an efficient, lightweight paradigm for lossless compression, particularly suitable for resource-constrained scenarios where balancing performance with computational efficiency is critical.

Abstract

Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential. Traditional compression methods are often limited in efficiency due to rigid, handcrafted models. Conversely, deep neural network (DNN)-based compression methods, while effective, demand substantial computational resources, hindering deployment in resource-constrained settings. To address these challenges, we propose a novel tri-plane context tree (TCT)-based method for lossless volumetric medical image compression that delivers high performance without relying on DNNs or external training data. To exploit intra-slice and inter-slice redundancies, we introduce a compact tri-plane context representation that decomposes complex 3D context modeling into efficient 2D modeling on three orthogonal planes. By integrating this representation with a context tree framework, we develop an input-specific TCT model employing an adaptive binary tree structure. At each tree node, the model dynamically selects from a suite of tri-plane based predictors and contextual feature extractors, enabling data-adaptive context modeling tailored to local structural characteristics. Instead of offline training, we sample a subset of the input volume to learn the TCT model by optimizing the minimum description length (MDL) through iterative construction and pruning. With the learned TCT model, each pixel retrieves its corresponding context, computes the prediction residual using the predictor dictated by the context, and performs entropy encoding based on the associated histograms. Experimental results demonstrate that the proposed method achieves compression performance on par with recent DNN-based methods on multiple datasets, while maintaining low computational cost and fast coding speeds, making it highly applicable in practice.

Problem

• Lossless Volumetric Medical Image Compression
• Computational Efficiency
• Resource-constrained Deployment

Innovation

• Tri-plane Context Tree
• Lossless Compression
• Minimum Description Length
• Volumetric Medical Image
• Adaptive Context Modeling