サポートベクターマシンを用いた肺腫瘍の鑑別

概要

論文の詳細を見る
Accurate segmentation of small pulmonary nodules (SPNs) is an important technique forvolumetric doubling time estimation and for feature characterization of the diagnosis of SPNs.Therefore, we have developed an automated volumetric segmentation algorithm of SPNs onthoracic CT images. This paper presents quantitative evaluation of the shape of the segmentedSPNs on thoracic CT images, and also presents quantitative estimation of the growth rate ofSPNs by use of repeated thoracic CT images. To quantitatively evaluate the performance of ouralgorithm, we employed the coincident rate. This coincident rate was calculated with both thecomputerized segmented region of an SPN and the region traced by a chest radiologist on axial,coronal MPR, sagittal MPR images. As the result of 90 selected cases, the mean value of thetotal coincident rate was 0.75 +/- 0.081. We also estimated the performance of our algorithm byuse of the doubling time of SPNs on repeated CT images. The doubling time of SPNs obtainedfrom computerized segmented regions closely correlated with the image findings reported byradiologists. From these results, we consider that our algorithm is useful for quantitativeestimation for the shape and the growth rate of SPNs on repeated CT in daily clinical practice.
大島商船高等専門学校の論文
2009-12-01