MALIGNANT TYPE LIVER CANCER DETECTION IN CT IMAGES USING MORPHOLOGICAL WATERSHED SEGMENTATION METHOD TO IMPROVE ACCURACY IN COMPARISON WITH THRESHOLD BASED SEGMENTATION METHOD

Aim : Image segmentation is a process in which a digital image is processed by using a set of algorithms to segment a portion of image which will have enough information like the input images. This research work aimed at developing liver cancer detection in CT images using image segmentation algorithms. Materials and Methods: In this research a morphological watershed transform is proposed for segmenting malignant types of liver cancer detection in CT images. The proposed work is compared with another image segmentation technique called threshold based segmentation and the sample size for each group is 30. Result: The performance of the image segmentation algorithm is measured using normalized correlation (NC) and universal index quality measure (UIQI)parameters. High values of NC and UIQI indicate better segmentation. Watershed transform provides mean NC values of 12.1814, mean of UIQI 61.3080 and threshold transform provides mean NC values of 8.8774, mean of UIQI 59.426. Conclusion: Based on the experimental results and statistical analysis using independent sample T-test, the watershed transform significantly performs better than threshold based transform with NC (0.09) and UIQI(0.5).