An object-oriented library for systematic training and comparison of classifiers for computer-assisted tumor diagnosis from MRSI measurements

• Published in: Computer science (Berlin, Germany) Vol. 26; no. 1-2; pp. 65 - 85
• Main Authors: Kaster, Frederik O., Merkel, Bernd, Nix, Oliver, Hamprecht, Fred A.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Berlin/Heidelberg Springer-Verlag 01.02.2011; Springer
• Subjects: Applied sciences; Artificial intelligence; Biological and medical sciences; Computer Hardware; Computer Science; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Computer Systems Organization and Communication Networks; Data Structures and Information Theory; Exact sciences and technology; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Pattern recognition. Digital image processing. Computational geometry; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Software; Software Engineering/Programming and Operating Systems; Special Issue Paper; Theory of Computation; Tumors; Magnetic resonance spectroscopy imaging; Statistical classification; Computer-assisted diagnostics; Automated quality control; Performance evaluation; Human; Statistical analysis; Probabilistic approach; Expert system; Pattern recognition; Malignant tumor; Nuclear magnetic resonance imaging; Annotation; Cancerology; User interface; Classification; Quality control; Graphical interface; Object oriented; Diagnosis; Planning; Medical application; Cancer
• ISSN: 1865-2034; 1865-2042
• DOI: 10.1007/s00450-010-0143-z

We present an object-oriented library for the systematic training, testing and benchmarking of classification algorithms for computer-assisted diagnosis tasks, with a focus on tumor probability estimation from magnetic resonance spectroscopy imaging (MRSI) measurements. In connection with a graphical user interface for data annotation, it allows clinical end users to flexibly adapt these classifiers towards changed classification tasks, to benchmark various classifiers and preprocessing steps and to perform quality control of the results. This poses an advantage over previous classification software solutions, which required expert knowledge in pattern recognition techniques in order to adapt them to changes in the data acquisition protocols. This software will constitute a major part of the MRSI analysis functionality of RONDO, an integrated software platform for cancer diagnosis and therapy planning which is under current development.