Novelty detection and in-line learning of novel concepts according to a case-based reasoning process schema for high-content image analysis in system biology and medicine

1Citations
Citations of this article
14Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Novelty detection, the ability to identify new or unknown situations that were never experienced before, is useful for intelligent systems aspiring to operate in environments where data are acquired incrementally. This characteristic is common to numerous problems in medical diagnosis and visual perception. We propose to see novelty detection as a case-based reasoning (CBR) process. Our novelty-detection method is able to detect the novel situation as well as to use the novel events for immediate reasoning. To ensure this capacity we combine statistical and similarity inference and learning. This view of CBR takes into account the properties of data such as the uncertainty and the underlying concepts such as storage, learning, retrieval and indexing can be formalized and performed efficiently. The novel events can be items being outliers or items making up a new class. Storage is done in a structured fashion, so that they can give a strategy for controlling the statistical learning process. Only when enough samples are available for a group of novel events, the statistical learning process proves if new models should be learned or if old models should be reorganized according to the new data. We use our novelty detection and handling method in a scenario where cell images may vary according to the particular cell line and the varying image quality given by the image acquisition unit. This scenario is valid for many medical applications and applications in system biology.© 2009 Wiley Periodicals, Inc.

Cite

CITATION STYLE

APA

Perner, P. (2009). Novelty detection and in-line learning of novel concepts according to a case-based reasoning process schema for high-content image analysis in system biology and medicine. Computational Intelligence, 25(3), 250–263. https://doi.org/10.1111/j.1467-8640.2009.00341.x

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free