Medical image compression using region-based prediction

This paper describes a novel technique that uses prior knowledge of anatomical information to improve the performance of medical image compression. This technique uses a series of predictors that have been optimised to deal with specific regions within medical image datasets. Instead of relying on a global prediction model, the proposed technique adaptively switches to an optimal predictor according to the characteristics of the region being compressed. Experimental results show that the proposed adaptive prediction method indeed achieves high prediction accuracy and when combined with an efficient entropy encoder, it provides a higher compression ratio than current general purpose state-of-the-art alternatives.