Shift-Invariant DWT for Medical Image Classification

Abstract

The discrete wavelet transform (DWT) is gaining momentum as a feature extraction and/or classification tool, because of its ability to localize structures with good resolution in a computationally effective manner. The result is a unique and discriminatory representation, where important and interesting structures (edges, details) are quantified efficiently by few coefficients. These coefficients may be used as features themselves, or features may be computed from the wavelet domain that describe the anomalies in the data. As a result of the potential that the DWT possesses for feature extraction and classification applications, the current work focuses on its utility in a computer-aided diagnosis (CAD) framework. CAD systems are computer-based methods that offer diagnosis support to physicians. The images are automatically analyzed and the presence of pathology is identified using quantitative measures (features) of disease. With traditional radiology screening techniques, visually analyzing medical images is labourious, time consuming, expensive (in terms of the radiologist’s time) and each individual scan is prone to interpretation error (the error rate among radiologists is reported to hover around 30% Lee (2007)). Additionally, visual analysis of radiographic images is subjective; one rater may choose a particular lesion as a candidate, while another radiologist may find this lesion insignificant. Consequently, some lesions are beingmissed ormisinterpreted. To reduce the error rates, a secondary opinion may be obtained with a CAD system (automatically reanalyze the images after the physician). Such methods are advantageous not only because they are cost effective, but also because they are designed to objectively quantify pathology in a robust, reliable and reproduciblemanner. There has been a lot of research in CAD-system design for specific modalities or applications with excellent results, i.e. see Sato et al. (2006) for CT, or Guliato et al. (2007) for mammography. Although these techniques may render good results for the particular modality it was built for, the technique is not transferable and has little-to-no utility in other CAD problems (cannot be applied to other images or databases). Since CAD systems are being employed widely, a framework that encompasses a variety of imaging modalities not just a single one would be of value. To this end, this work concerns the development of a generalized computer-aided diagnosis system that is based on the DWT. It is considered generalized, since the same framework can 0