DSIN: dynamic system-empowered implicit neural representation for medical image compression

Multidimensional/Ultra-high-resolution medical imaging, e.g., Photon-counting computed tomography, multiparametric Magnetic resonance imaging (MRI), whole-slide digital pathology drives diagnostic precision but generates massive datasets that strain clinical infrastructure. Current compression methods either sacrifice subvisual diagnostic features to prioritize human perception or lack generalizability across modalities and pathologies. Here, we introduce Dynamic system-empowered implicit neural representation (DSIN), an image compression framework using image-specific implicit neural representations, where a stacked dynamic-system-based compression module further reduces model size while preserving reconstruction quality. When tested across five large-scale clinical datasets (including Computed tomography (CT), MRI, Positron emission tomography (PET), Computed tomography angiography (CTA), and histopathology images), DSIN achieves compression ratios up to 183-fold while maintaining high reconstruction quality, outperforming established and implicit neural representation methods in downstream tasks such as segmentation and classification. Quantitative evaluations reveal superior performance in preserving reconstruction quality, organ boundary fidelity, and metabolic activity delineation in low-dose PET imaging. DSIN provides an effective compression framework for the medical imaging modalities evaluated in this study.