An effective computer aided diagnosis model for pancreas cancer on PET/CT images

Abstract

Background and objective: Pancreas cancer is a digestive tract tumor with high malignancy, which is difficult for diagnosis and treatment at early time. To this end, this paper proposes a computer aided diagnosis (CAD) model for pancreas cancer on Positron Emission Tomography/Computed Tomography (PET/CT) images.

Methods: There are three essential steps in the proposed CAD model, including (1) pancreas segmentation, (2) feature extraction and selection, (3) classifier design, respectively. First, pancreas segmentation is performed using simple linear iterative clustering (SLIC) on CT pseudo-color images generated by the gray interval mapping (GIP) method. Second, dual threshold principal component analysis (DT-PCA) is developed to select the most beneficial feature combination, which not only considers principal features but also integrates some non-principal features into a new polar angle representation. Finally, a hybrid feedback-support vector machine-random forest (HFB-SVM-RF) model is designed to identify normal pancreas or pancreas cancer and the key is to use 8 types of SVMs to establish the decision trees of RF.

Results: The proposed CAD model is tested on 80 cases of PET/CT data (from General Hospital of Shenyang Military Area Command) and achieves the average pancreas cancer identification accuracy of 96.47%, sensibility of 95.23% and specificity of 97.51%, respectively. In addition, the proposed pancreas segmentation method is also evaluated using a public dataset with 82 3D CT scans from the National Institutes of Health (NIH) Clinical Center and its performance is found to surpass other methods, with a mean Dice coefficient of 78.9% and Jaccard index of 65.4%.

Conclusions: Collectively, contrast experiments in 10-fold cross validation demonstrate the efficiency and accuracy of the proposed CAD model as well as its performance advantages as compared with related methods.

Keywords: Feature selection; Machine learning; PET/CT Image; Pancreas cancer identification; Pancreas segmentation.