Image-guided decision support system for pathology

We present a content-based image retrieval system that supports decision ma king in clinical pathology. The image-guided decision support system locate s, retrieves, and displays cases which exhibit morphological profiles consi stent to the case in question. It uses an image database containing 261 dig itized specimens which belong to three classes of lymphoproliferative disor ders and a class of healthy leukocytes. The reliability of the central modu le, the fast color segmenter, makes possible unsupervised on-line analysis of the query image and extraction of the features of interest: shape, area, and texture of the nucleus. The nuclear shape is characterized through sim ilarity invariant Fourier descriptors, while the texture analysis is based on a multiresolution simultaneous autoregressive model. The system performa nce was assessed through ten-fold cross-validated classification and compar ed with that of a human expert. To facilitate a natural man-machine interfa ce, speech recognition and voice feedback are integrated. Client-server com munication is multithreaded, Internet-based, and provides access to support ing clinical records and video databases.