An X-ray CAD system with ribcage suppression for improved detection of lung lesions

• DOI: 10.3311/ppee.2079
• Publication Date: 2013-12-18T09:16:35Z
• Authors: Áron Horváth; Gergely Orbán; Ákos Horváth; Gábor Horváth
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

The purpose of our study is to prove that eliminating bone shadows from chest radiographs can greatly improve the accuracy automated lesion detection. To free images rib and clavicle shadows, they are first segmented using a dynamic programming approach. eliminated in difference space. cleaned processed by hybrid detector based on gradient convergence, contrast intensity statistics. False findings Support Vector Machine. Our method eliminate approximately 80% (84% for posterior part) with an average segmentation error 1 mm. With shadow removal number false dropped 2.94 1.23 at 63% sensitivity cancerous tumors. output improved system showed much less dependence shadows. show putting emphasis elimination lead great benefits computer aided