Novel Algorithm for Pancreatic Tumor Detection and Classification

Fuzzy-based segmentation and classification techniques have been used in various medical imaging applications although not pancreatic cancer [46-48]. An application closest to CT pancreatic imaging with analogous problems is the magnetic resonance imaging (MRI) of the brain and brain tumors. Unsupervised, supervised, and semisupervised fuzzy c-means (FCM) algorithms and knowledge-guided FCM segmentation have been successfully applied to brain tumor MRI applications [49-55]. Similar approaches have also shown promising results for breast tumor segmentation in mammography [56], and lung nodule segmentation on CT images [57]. Here, we present the implementation and initial performance of an FCM based algorithm for pancreatic tumor segmentation and tumor measurements on 2D CT slices. Figure 4.8 presents a flowchart of

Figure 4.8: Block diagram of CAD algorithm developed for the clustering and classification of pancreatic tumors on helical CT scans.

the design and implementation of the algorithm. The designed CAD scheme follows the general principles presented in Fig. 4.5 but includes additional steps for postprocessing and validation that will be discussed in more detail below.

Was this article helpful?

0 0

Post a comment