PRUNED TREE-STRUCTURED VECTOR QUANTIZATION OF MEDICAL IMAGES WITH SEGMENTATION AND IMPROVED PREDICTION

In this work, we use predictive pruned tree-structured vector quantiza tion for the compression of medical images. Our goal is to obtain a hi gh compression ratio without impairing the image quality, at least so far as diagnostic purposes are concerned. We use a priori knowledge of the class of images to be encoded to help us segment the images and t hereby to reserve bits for diagnostically relevant areas. Moreover, we improve the quality of prediction and encoding in two additional ways : by increasing the memory of the predictor itself and by using ridge regression for prediction. The improved encoding scheme was tested via computer simulations on a set of mediastinal CT scans; results are co mpared with those obtained using a more conventional scheme proposed r ecently in the literature, There were remarkable improvements in both the prediction accuracy and the encoding quality, above and beyond wha t comes from the segmentation. Test images were encoded at 0.5 bit per pixel and less without any visible degradation for the diagnostically relevant region.