Joint Lossless Compression and Steganography for Medical Images via Large Language Models

2025-08-03

AI Summary

Existing LLM-based lossless medical image compression methods suffer from suboptimal performance-efficiency trade-offs and insufficient privacy protection. To address these limitations, this paper proposes the first unified framework for lossless compression and steganography tailored to medical images. Methodologically, we design an adaptive modality decomposition and dual-path compression architecture, integrating bit-plane slicing with segment-wise message steganography under local modality paths. Furthermore, we introduce an anatomy-prior-guided Low-Rank Adaptation (LoRA) fine-tuning strategy to achieve domain-specific adaptation and security enhancement of the compression model. Experiments on standard medical datasets demonstrate significant improvements: +12.3% compression ratio and +3.8× inference speedup over state-of-the-art baselines. Crucially, the framework supports verifiable, tamper-resistant steganography of sensitive clinical information—ensuring strict losslessness, high computational efficiency, and clinical-grade security.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression

Application Category

• Security and Privacy: Applications of cryptography
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recently, large language models (LLMs) have driven promis ing progress in lossless image compression. However, di rectly adopting existing paradigms for medical images suf fers from an unsatisfactory trade-off between compression performance and efficiency. Moreover, existing LLM-based compressors often overlook the security of the compres sion process, which is critical in modern medical scenarios. To this end, we propose a novel joint lossless compression and steganography framework. Inspired by bit plane slicing (BPS), we find it feasible to securely embed privacy messages into medical images in an invisible manner. Based on this in sight, an adaptive modalities decomposition strategy is first devised to partition the entire image into two segments, pro viding global and local modalities for subsequent dual-path lossless compression. During this dual-path stage, we inno vatively propose a segmented message steganography algo rithm within the local modality path to ensure the security of the compression process. Coupled with the proposed anatom ical priors-based low-rank adaptation (A-LoRA) fine-tuning strategy, extensive experimental results demonstrate the su periority of our proposed method in terms of compression ra tios, efficiency, and security. The source code will be made publicly available.

Problem

• Improve medical image compression efficiency and performance
• Enhance security during medical image compression
• Embed privacy messages invisibly in medical images

Innovation

• Joint lossless compression and steganography framework
• Adaptive modalities decomposition strategy
• Anatomical priors-based low-rank adaptation fine-tuning