Visceral fat in the abdomen is one of the leading causes of many health problems. A CT-scan modality is the most precise examination in determining the visceral fat tissue. Still, there are obstacles. The number of images produced by the CT scan to be analyzed is quite a lot. In this study, Computer Aided Diagnosis (CAD) system was developed using the Thresholding segmentation method, feature extraction based on Gray Level Co-Occurrence Matrix (GLCM) for identifying abdominal fat. Next, the Multilayer Perceptron (MLP) classification process separates the visceral fat area from the subcutaneous fat area. This study uses 665 abdominal CT-scan images divided into 481 images as training data and 184 images as test data that has validated the area and volume of visceral fat by an expert radiographer. The CAD system performance results are the accuracy level with a value of 95.58% for training data and 88.73% for test data. In addition, information was also obtained by the area of the visceral fat area in women, which is 83.71 cm2 with a total volume of visceral fat of 1739.8 cm3. Whereas in men, the area of visceral fat is 70.82 cm3 with a total volume of visceral fat of 1036.23 cm2. Based on the cut-off value in the visceral fat area, the results obtained in this study are said to have a normal visceral fat area (VFA) because it has a normal value < 100 cm2 and there is a minimal risk of metabolic syndrome.