Abstract. In this study, a computer-aided detection (CAD) system was developed for the detection of lung nodules in computed tomography images. The CAD system consists of four phases, including two-dimensional and three-dimensional preprocessing phases. In the feature extraction phase, four different groups of features are extracted from volume of interests: morphological features, statistical and histogram features, statistical and histogram features of outer surface, and texture features of outer surface. The support vector machine algorithm is optimized using particle swarm optimization for classification. The CAD system provides 97.37% sensitivity, 86.38% selectivity, 88.97% accuracy and 2.7 false positive per scan using three groups of classification features. After the inclusion of outer surface texture features, classification results of the CAD system reaches 98.03% sensitivity, 87.71% selectivity, 90.12% accuracy and 2.45 false positive per scan. Experimental results demonstrate that outer surface texture features of nodule candidates are useful to increase sensitivity and decrease the number of false positives in the detection of lung nodules in computed tomography images.

No abstract

ObjectiveThe purpose of this study was to develop a new method for automated mass detection in digital mammographic images using templates.Materials and MethodsMasses were detected using a two steps process. First, the pixels in the mammogram images were scanned in 8 directions, and regions of interest (ROI) were identified using various thresholds. Then, a mass template was used to categorize the ROI as true masses or non-masses based on their morphologies. Each pixel of a ROI was scanned with a mass template to determine whether there was a shape (part of a ROI) similar to the mass in the template. The similarity was controlled using two thresholds. If a shape was detected, then the coordinates of the shape were recorded as part of a true mass. To test the system's efficiency, we applied this process to 52 mammogram images from the Mammographic Image Analysis Society (MIAS) database.ResultsThree hundred and thirty-two ROI were identified using the ROI specification methods. These ROI were classified using three templates whose diameters were 10, 20 and 30 pixels. The results of this experiment showed that using the templates with these diameters achieved sensitivities of 93%, 90% and 81% with 1.3, 0.7 and 0.33 false positives per image respectively.ConclusionThese results indicate that the detection performance of this template based algorithm is satisfactory, and may improve the performance of computer-aided analysis of mammographic images and early diagnosis of mammographic masses.

No abstract

No abstract

Educational data mining is a very novel research area, offering fertile ground for many interesting data mining applications. Educational data mining can extract useful information from educational activities for better understanding and assessment of the student learning process. In this way, it is possible to explore how students learn topics in interactive learning environments such as an intelligent tutoring system (ITS). In this article, we demonstrate the use of association rule mining to extract mistakes often occurring together in the student data captured in an ITS we developed, called "intelligent tutor for computer systems course" (ITCS). Student assessment results from the ITCS were analyzed using association rule mining. This analytical process could help teachers to carry out modification to the ITCS to improve it together with the concept and sub-concept relationships obtained. We further developed two software programs to extract hidden patterns from the student assessment results on the ITCS using association rule mining. The first program analyzes and finds association rules derived from the students' incorrect answers to the concepts by single dimensional association rule mining, while the second program does so by multidimensional association rule mining. Design of these programs and the data mining results in this study are described.

No abstract

Data mining can be used in the educational field to make teaching more effective, to provide help for the student and teacher, and to analyze data. Data mining can be useful with educational software like intelligent tutoring systems which contain large quantities of data about students and their degree of success, scores, and errors. By analyzing these data, it is possible to obtain pedagogically reliable information as feedback for the teacher. The objectives of this study are to cluster the data available from an Intelligent Tutoring System (ITS) and to visualize the multidimensional data analysis results. In this study, the ITS data, which contain exam results on six different concepts, are clustered using k-means and fuzzy c-means algorithms, and the clustering performance of the two algorithms is compared. Cluster analysis results are visualized using a parallel coordinate system. Clustering and visualizing of the concept-level scores is used to provide meaningful and nontrivial insights into the workings of a course. Such information is useful for the teacher to discover which concepts give students difficulty and which do not. The paper also describes the data mining software developed in this study and the analytical results obtained.