Automated mediastinal lymph node detection from CT volumes based on intensity targeted radial structure tensor analysis

This paper presents a local intensity structure analysis based on an intensity targeted radial structure tensor(ITRST) and the blob-like structure enhancement filter based on it (ITRST filter) for the mediastinal lymph nodedetection algorithm from chest computed tomography (CT) volumes. Although the filter based on radial structure tensoranalysis (RST filter) based on conventional RST analysis can be utilized to detect lymph nodes, some lymph nodesadjacent to regions with extremely high or low intensities cannot be detected. Therefore, we propose the ITRST filter, which integrates the prior knowledge on detection target intensity range into the RST filter. Our lymph nodedetection algorithm consists of two steps: (1) obtaining candidate regions using the ITRST filter and (2) removing false positives (FPs) using the support vector machine classifier. We evaluated lymph nodedetection performance of the ITRST filter on 47 contrast-enhanced chest CT volumes and compared it with the RST and Hessian filters. The detection rate of the ITRST filter was 84.2% with 9.1 FPs/volume for lymph nodeswhose short axis was at least 10 mm, which outperformed the RST and Hessian filters.