Non-uniform Compression of Magnetic Resonance Brain Images Using Edge-based Active Contours Driven by Maximum Entropy Threshold

With the exponential growth of digital imaging data, the compression of medical images has become a critical issue for efficient storage and reliable transmission. Researchers are continuously exploring new methods for reducing the size of medical images.

To further improve compression methods, this study proposes a maximum entropy-based thresholding approach integrated into the edge-based active contour method. This integration automates the initialization of the curve for accurate extraction of diagnostically or pathologically significant regions from unevenly illuminated magnetic resonance (MR) brain images. This approach enables the segmentation of the images into informative and background regions, which are further subjected to high bit-rate compression and low bit-rate compression, respectively. This non-uniform compression results in an improvement in compression rate while preserving the quality of diagnostically significant regions.

The proposed method was evaluated on a dataset of MR brain images, and empirical analysis confirmed that the proposed method is able to outperform other existing methods in terms of both segmentation and compression metrics.

The mathematical results of the proposed method indicate that the extracted informative regions closely match the object of interest in the ground truth images. This accurate demarcation enhances the compression rate without compromising the quality of the informative content.