A method for linking computed image features to histological semantics in neuropathology

In medical image analysis, the image content is often represented by computed features that need to be interpreted at a clinical level of understanding to support lopment of clinical diagnosis systems. Many features are of abstract nature, as for instance features derived from a wavelet transform. The interpretation and analysis of such features is difficult. This lack of coincidence between computed features and their meaning for a user in a given situation is commonly referred to as the semantic gap. In this work, we propose a method for feature analysis and interpretation based on the simultaneous visualization of feature and image domain. Histopathological images of meningioma WHO (World Health Organization) grade I are firstly color transformed and then characterized by features derived from the Discrete Wavelet Transform. The wavelet-based feature space is then visualized and explored using unsupervised machine learning methods. Our approach allows to analyze and select feature...

• Type: Journal
• Year: 2007
• Where: JBI
• Authors: Birgit Lessmann, Tim W. Nattkemper, V. H. Hans, Andreas Degenhard
• Keywords: Discrete Wavelet Transform, Images, JBI 2004, JBI 2007, Wavelet Transform