The Study of Lung Nodules Detection for Chest Radiographs

• Main Authors: Yu-wen Liu, 劉育文
• Other Authors: Jiann-Shu Lee
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/68354t

碩士 === 國立臺南大學 === 數位學習科技學系碩士班 === 99 === The chest X-ray image is the most common modality for lung nodule detection. In this thesis, we propose a new lung nodule detection algorithm for chest X-ray image. The SIFT (Scale-Invariant Feature Transform) is used to extract feature points first. Then, the orthogonal subspace projection is utilized to enhance the difference between the nodule and non-nodule features. Finally, the proposed DPB-DCS (Data-Partition Based Dynamic Classifier Selection) scheme is exploited to decide whether there exists lung nodules. The experimental results reveal that the proposed system can effectively enhance the fine nodule detection rate.