The existing three-dimensional (3D) x-ray reconstruction methods for lung cancer tissue reconstruct the investigated objects based on a series of two-dimensional (2D) image sections and a chosen 3D reconstruction algorithm. However, because these procedures apply the same segmentation method for all 2D image sections, they may not achieve the optimal segmentation for each section. As a result, the reconstructed 3D images have limited spatial resolution. Furthermore, the existing 3D reconstruction method is time-consuming and results in a limited time resolution. This research presents an innovation of 3D reconstruction by reformulating two main components of the method. First, a validity index for fuzzy clustering is used to obtain the optimal segmentations of any 2D x-ray image. The process is realized by automatically determining the optimal number of clusters for the image. Second, unlike the existing 3D reconstruction methods, a fast-FCM algorithm is used to speed up the 2D image segmenting process, thereby raising the time resolution of the 3D reconstruction process. With the aid of commonly used VTK software, the proposed method has been used to visualize four classes of typical lung cancer tissues: adenocarcinoma, large cell carcinoma, small cell carcinoma, and squamous cell carcinoma. Experimental results validate the effectiveness and efficiency of the proposed algorithm. Thus, the method contributes a useful tool for x-ray-based 3D image reconstruction.
Keywords: X-ray computed tomography; fuzzy image segmentation; lung cancer tissue; three-dimensional (3D) reconstruction.