This paper presents a novel method that can automatically segment solitary pulmonary nodule (SPN) and match
such segmented SPNs on follow-up thoracic CT scans. Due to the clinical importance, a physician needs to find
SPNs on chest CT and observe its progress over time in order to diagnose whether it is benign or malignant, or
to observe the effect of chemotherapy for malignant ones using follow-up data. However, the enormous amount
of CT images makes large burden tasks to a physician. In order to lighten this burden, we developed a method
for automatic segmentation and assisting observation of SPNs in follow-up CT scans. The SPNs on input 3D
thoracic CT scan are segmented based on local intensity structure analysis and the information of pulmonary
blood vessels. To compensate lung deformation, we co-register follow-up CT scans based on an affine and a
non-rigid registration. Finally, the matches of detected nodules are found from registered CT scans based on a
similarity measurement calculation. We applied these methods to three patients including 14 thoracic CT scans.
Our segmentation method detected 96.7% of SPNs from the whole images, and the nodule matching method
found 83.3% correspondences from segmented SPNs. The results also show our matching method is robust to the
growth of SPN, including integration/separation and appearance/disappearance. These confirmed our method
is feasible for segmenting and identifying SPNs on follow-up CT scans.
We previously proposed a recognition method of lung nodules based on experimentally selected feature values (such as contrast, circularities, etc.) of the suspicious shadows detected by our Quoit filter. In this paper, we propose a new recognition method of lung nodule using each CT value itself in ROI (region of interest) area as a feature value. In the clustering stage, first, the suspicious shadows are classified into some clusters using Principal Component (PC) theories. A set of CT values in each ROI is regarded as a feature vector, and then the eigen vectors and the eigen values are calculated for each cluster by applying Principal Component Analysis (PCA). The eigen vectors (we call them Eigen Images) corresponding to the first 10 largest eigen values, are utilized as base vectors for subspaces of the clusters in the feature space. In the discrimination stage, correlations are measured between the unknown shadow and the subspace which is spanned by the Eigen Images. If the correlation with the abnormal subspace is large, the suspicious shadow is determined to be abnormal. Otherwise, it is determined to be normal. By applying our new method, good results have been acquired.