Computer Methods and Programs in Biomedicine (2005) 79, 59—72 Image mining for investigative pathology using optimized feature extraction and data fusion Wenjin Chen a,* , Peter Meer c , Bogdan Georgescu d ,WeiHe a , Lauri A. Goodell b , David J. Foran a,b a Center for Biomedical Imaging & Informatics, Room R203, 675 Hoes Lane, Piscataway, NJ 08854, USA b Department of Pathology & Laboratory Medicine, University of Medicine & Dentistry of New Jersey, Piscataway, NJ 08854, USA c Department of Electrical and Computer Engineering, Center for Advanced Information Processing, Rutgers University, Piscataway, NJ 08854, USA d Siemens Corporate Research, Integrated Data Systems Department, Princeton, NJ, USA Received 22 August 2004; received in revised form 4 March 2005; accepted 8 March 2005 KEYWORDS Automated digital microscopy; Unsupervised cell imaging; Content-based image retrieval; Texture analysis; Data fusion Summary In many subspecialties of pathology, the intrinsic complexity of render- ing accurate diagnostic decisions is compounded by a lack of definitive criteria for detecting and characterizing diseases and their corresponding histological features. In some cases, there exists a striking disparity between the diagnoses rendered by recognized authorities and those provided by non-experts. We previously reported the development of an Image Guided Decision Support (IGDS) system, which was shown to reliably discriminate among malignant lymphomas and leukemia that are sometimes confused with one another during routine microscopic evaluation. As an extension of those efforts, we report here a web-based intelligent archiving subsystem that can automatically detect, image, and index new cells into distributed ground-truth databases. Systematic experiments showed that through the use of robust texture descriptors and density estimation based fusion the reliability and performance of the governing classifications of the system were improved significantly while simultaneously reducing the dimensionality of the feature space. © 2005 Elsevier Ireland Ltd. All rights reserved. * Corresponding author. Tel.: +1 732 235 5680; fax: +1 732 235 4825. E-mail address: wjc@pleiad.umdnj.edu (W. Chen). 1. Introduction 1.1. Clinical significance A differential diagnosis provides the basis for how patients are treated, which medications are appropriate, and what levels of risk are justified. As new treatments and therapies become available 0169-2607/$ — see front matter © 2005 Elsevier Ireland Ltd. All rights reserved. doi:10.1016/j.cmpb.2005.03.006