In this paper an image segmentation technique is presented by combining seed based region growing and boundary segmentation in sequential order. The first process in region growing is to identify an initial seed point. Most of region growing methods identify the seed point manually which involve human interaction. Thus, automated initial seed point identification for region growing algorithm is proposed. The boundary segmentation technique is implemented in order to improve the segmentation results. The method is tested on 50 mammogram images confirmed by a radiologist to consist microcalcifications. Experimental results show that the algorithm successfully segment the microcalcifications with accuracy of 0.94.

The active contour (Snake) is a computer generated curve that can trace boundaries of images. As a method which applies the computer technology in mathematics, Snake is computationally formulated based on controlled continuous splines and adopts the mathematical concept of energy minimization. This paper presents the application of Snake for the segmentation of masses on breast ultrasound images. The images used are taken from Malaysian population. The boundaries of the masses identified may be used in classification of cancers or non-cancerous masses. Specifically the Balloon Snake is applied in segmenting the masses in the breast ultrasound images. Comparison on the masses areas segmented by the Balloon Snake is done against the areas traced by an expert (radiologist). It is found that from forty-five masses tested, the average percentage area difference of Balloon Snake is 4.47%. This implies that the accuracy of segmentation results for the Balloon Snake is 95.53%.

Seed-based region growing (SBRG) has been widely used as a segmentation method for medical images. The selection of initial seed point in SBRG is the crucial part before the segmentation process is carried out. Most of the region growing methods identify the seed point manually which involve human interaction and require prior information about the image. In this paper, an automated initial seed point selection for SBRG algorithm is proposed. The proposed method is tested on 50 mammogram images confirmed by a radiologist to consist microcalcifications. The performance is evaluated using Receiving Operator Curve (ROC) based on level of detection. Experimental results show that the method has successfully segmented the microcalcifications with 0.98 accuracy.

The active contour or Snake is a computer generated curve, used to trace boundaries of images. This paper presents the application of Snake for the segmentation of masses on breast ultrasound images and the characterization of the segmented masses as malignant or benign. Initially, the Balloon Snake is chosen to segment the masses. Comparison on the masses areas segmented by the Balloon Snake is done against the areas traced by radiologist. Experimental result shows that from fifty masses tested, the Balloon Snake successfully segment the masses with accuracy of 95.71%. Then, a mass is characterized as benign or malignant using a proposed method namely the semi-automated characterization (SAC) method. The method is based on the segmented masses produced by the Balloon Snake. The criterion of angular margin is considered in characterizing the masses as malignant or benign by the SAC method. The characterization reading of a mass by the SAC method is compared with thirty sets of characterization readings of a mass by different radiologists. The comparison is made in terms of sensitivity and specificity values. Based on the values, the receiver operating characteristics (ROC) curve is plotted for each set of comparison. From the thirty sets of comparisons, it is found that the area under curve of all the thirty ROC curves are greater than 0.7. The value implies that the SAC method gives high accuracy in characterizing benign from malignant mass. Since the method is based on the segmented masses by the Balloon Snake, the value also implies that the accuracy of Balloon Snake in segmenting the images is high (95.71%).

The most common problem in image processing is image segmentation. One of the methods which can segment an image with a high accuracy is Balloon Snake. It uses the energy minimization conception where it has a dynamic behavior that deforms from an initial position and converges to the boundary of the object in an image. However, we found that the accurateness always influences by the edge map detector that being used in implementing the Balloon Snake. Edge map detector is used to strengthen the boundary of the object before the object is segmented. Two popular edge map detectors are chosen in this research namely Canny and Sobel edge detector. Both edge detectors are implemented in Balloon Snake in segmenting 40 masses in breast ultrasound images. The pixel area traced by the two combination methods namely Canny and Balloon Snake and Sobel and Balloon Snake are evaluated. The accuracy is measured based on the percentage pixel area difference between radiologist and the both combination methods. It is found that the combination of using Canny and Balloon Snake give 3.5% percentage of pixel area difference which is smaller compared to the other combination which have 12.7% percentage pixel area difference.

Edge detection has been widely used especially in medical image processing field. In this paper we are comparing Sobel, Prewitt and Laplacian of Gaussian (LoG) edge detection techniques in segmenting the boundary of microcalcifications. The edge detection must satisfy the breast phantom scoring criteria before the segmentation phase is carried out. Then, all of the edge detection techniques are implemented in the Enhanced Distance Active Contour (EDAC) model for the segmentation process. Results obtained from Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve shows that the Prewitt edge detection has the highest value of AUC, followed by the Sobel and LoG which are 0.79, 0.72 and 0.71 respectively.