We propose several methods for minimizing the codelength achievable when encoding histological images in two phases, where a segmentation of the image is encoded in the first phase and the image conditional on its segmentation is encoded in the second phase. The main goal of the paper is to establish the class of models suitable to be used in minimum description based analysis of histological images, and to compare the compression performance achievable by several predictive coding schemes, which we derive specifically for the second phase. The most efficient of the publicly available general image compressors, JPEG-LS and CALIC, are also compared in the one phase coding scenario. We conclude with a preliminary study on setting automatically the optimal parameters of one segmentation algorithm so that the compressed description has minimum length.
This paper presents a lossless compression method performing separately the compression of the vessels and of the remaining part of eye fundus in retinal images. Retinal images contain valuable information sources for several distinct medical diagnosis tasks, where the features of interest can be e.g. the cotton wool spots in the eye fundus, or the volume of the vessels over concentric circular regions. It is assumed that one of the existent segmentation methods provided the segmentation of the vessels. The proposed compression method transmits losslessly the segmentation image, and then transmits the eye fundus part, or the vessels image, or both, conditional on the vessels segmentation. The independent compression of the two color image segments is performed using a sparse predictive method. Experiments are provided over a database of retinal images containing manual and estimated segmentations. The codelength of encoding the overall image, including the segmentation and the image segments, proves to be better than the codelength for the entire image obtained by JPEG2000 and other publicly available compressors.Index Termslossless compression, retinal images, region of interest, sparse prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.