Learning Lossless Compression for High Bit-Depth Volumetric Medical Image

Recent advances in learning-based methods have markedly enhanced the capabilities of image compression. However, these methods struggle with high bit-depth volumetric medical images, facing issues such as degraded performance, increased memory demand, and reduced processing speed. To address these challenges, this paper presents the Bit-Division based Lossless Volumetric Image Compression (BD-LVIC) framework, which is tailored for high bit-depth medical volume compression. The BD-LVIC framework skillfully divides the high bit-depth volume into two lower bit-depth segments: the Most Significant Bit-Volume (MSBV) and the Least Significant Bit-Volume (LSBV). The MSBV concentrates on the most significant bits of the volumetric medical image, capturing vital structural details in a compact manner. This reduction in complexity greatly improves compression efficiency using traditional codecs. Conversely, the LSBV deals with the least significant bits, which encapsulate intricate texture details. To compress this detailed information effectively, we introduce an effective learning-based compression model equipped with a Transformer-Based Feature Alignment Module, which exploits both intra-slice and inter-slice redundancies to accurately align features. Subsequently, a Parallel Autoregressive Coding Module merges these features to precisely estimate the probability distribution of the least significant bit-planes. Our extensive testing demonstrates that the BD-LVIC framework not only sets new performance benchmarks across various datasets but also maintains a competitive coding speed, highlighting its significant potential and practical utility in the realm of volumetric medical image compression.

I. Introduction

The ever-increasing utilization of advanced medical imaging techniques, such as computer tomography (CT) scans and magnetic resonance imaging (MRI), has led to a surge in the generation of volumetric medical image data. For instance, a single CT scan can produce a three-dimensional (3D) image of a patient’s body comprising dozens or even hundreds of two-dimensional (2D) slices at a 16-bit depth, resulting in a total data volume reaching hundreds of megabytes or even one gigabyte. These detailed volumetric images are indispensable for accurate diagnosis and effective treatment planning. However, their considerable size presents notable challenges for storage and transmission. Given these challenges, there is a clear need for efficient compression methods. While lossy compression techniques can achieve higher compression ratios, they risk introducing distortions that could compromise the diagnostic integrity of the images and potentially lead to medical errors. Consequently, lossless compression emerges as the preferred method for medical imaging, adhering to the strict requirements for maintaining data fidelity.