Abstract
Computer-aided diagnosis (CAD) (Giger and Suzuki 2007) has been an active area of study in medical image analysis, because evidence suggests that CAD can help improve the diagnostic performance of radiologists in their image interpretations (Li, Aoyama et al. 2004; Li, Arimura et al. 2005; Dean and Ilvento 2006). Many investigators have participated in and developed CAD schemes for detection/diagnosis of lesions in medical images, such as detection of lung nodules in chest radiographs (Giger, Doi et al. 1988; van Ginneken, ter Haar Romeny et al. 2001; Suzuki, Shiraishi et al. 2005) and in thoracic CT (Armato, Giger et al. 1999; Armato, Li et al. 2002; Suzuki, Armato et al. 2003; Arimura, Katsuragawa et al. 2004), detection of microcalcifications/masses in mammography (Chan, Doi et al. 1987), breast MRI (Gilhuijs, Giger et al. 1998), breast US (Horsch, Giger et al. 2004; Drukker, Giger et al. 2005), and detection of polyps in CT colonography (Yoshida and Nappi 2001; Suzuki, Yoshida et al. 2006; Suzuki, Yoshida et al. 2008). Some advanced CAD schemes employ a filter for enhancement of lesions as a preprocessing step for improving sensitivity and specificity. The filter enhances objects similar to a model employed in the filter; e.g., a blob enhancement filter based on the Hessian matrix enhances sphere-like objects (Frangi, Niessen et al. 1999). Actual lesions, however, often differ from a simple model, e.g., a lung nodule is generally modeled as a solid sphere, but there are nodules of various shapes and inhomogeneous nodules such as a spiculated nodule and a ground-glass opacity. A colorectal polyp is often modeled as a cap structure by using a shape index filter, but a sessile polyp or a flat polyp cannot be characterized well as a cap structure of the shape index. Thus, conventional filters often fail to enhance actual lesions such as lung nodules with ground-glass opacity and sessile/flat polyps. To address this issue, we developed a supervised filter for enhancement of actual lesions by use of a massive-training artificial neural network (MTANN) (Suzuki, Armato et al. 2003) filter in a CAD scheme. In this chapter, we introduce MTANN-based CAD schemes for detection of lung nodules in CT and for detection of polyps in CT colonography. To summerize, by extension of “neural filters” (Suzuki, Horiba et al. 2002) and “neural edge enhancers” (Suzuki, Horiba et al. 2003; Suzuki, Horiba et al. 2004), which are ANN-based 18
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have