Search

Pressure Ulcer (PU) or pressure sore is localized injury to the skin or underlying tissue or both that occur over a bony prominence when a patient is subjected to direct pressure for a lengthy period. Research have shown that skin blood flow response (SBFR) is a useful signal in PU evaluation due to its ability to determine ischemic stress response. In previous animal study, peak reactive hyperaemia (RH), a feature of SBFR has been measured for three loading-unloading cycles to indicate tissue recovery. However, in that study, peak SBFR feature cannot discriminate between tissue injury and tissue recovery effectively for short recovery time. In this study, the potential use of other SBFR signal features including time domain features i.e time to peak and frequency domain features i.e peak of power spectrum and total of power spectrum are investigated. The results show that for the samples taken, peak RH and area under the curve are both effective at discriminating between short of insufficient recovery time while other investigated features are ineffective.

Computer assisted diagnosis systems (CADs) is now commonly used as a second opinion to help radiologists in image interpretation by emphasizing on the suspicious areas. Segmentation of region of interests in 2-dimensional (2D) or volume of interests in 3-dimensional (3D) images is a critical step in CAD systems. 3D image segmentation using 2D slices has been a keen of interest for research purpose. In this paper we propose to reconstruct a 3D form of volume of interests (VOIs) from a series of 2D images in computed tomography laser mammography (CTLM). In this paper, a 3D Fuzzy C-Means clustering have been implemented to reconstruct VOIs for breast cancer detection in CTLM images. To assess the accuracy of the extracted VOIs against ground truth, percentage error factor is used and produced error value of 10.72% in our dataset of 62 CTLM breast images collected among Malaysian participants.

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.

In breast thermography diagnostic, proper detection and segmentation of the areola area as well as detection of breast boundaries present the biggest challenge. As the boundaries of breasts especially in the upper quadrants are usually not present, this produces a great deal of challenge to segment breasts automatically. Many approaches have been developed to segment the breast in the past such as Snakes, Active Contours and Circular Hough Transforms, but these methods fail to detect the boundaries of the breast with the required level of accuracy especially the upper boundaries of the breast. By utilizing most recent segmentation method which is Random Walkers, the breast can be segmented accurately which in turn will increase the accuracy and the reliability of computer aided detection/diagnosis systems.

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.

This paper presents the application of Active Contour or 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 segmented mass by the Balloon Snake is characterized as benign or malignant based on the measurement of angular margin. The mass is considered as a malignant if it has at least one acute angular margin. Otherwise it is a benign. The characterization of a mass by the Balloon Snake based on the criterion of angular margin is compared with the actual type of a mass characterized by an expert radiologist. The comparison is made in terms of sensitivity and specificity values. Based on the values, the receiver operating characteristics (ROC) curve is plotted. It is found that the area under curve is 0.8455. The value implies that the Balloon Snake gives high accuracy in characterizing benign from malignant mass based on the criterion used.

This study is focused on automatic detection of tumors in Ultrasound breast images in order to help medical doctors in interpretation of such images using Computer-Aided Detection. In this way a set of 6 most popular ultrasound machines were selected and images were captured with sweeping: modes of operation, transducer, frequency and contrast. A multi purpose multi tissue Ultrasound Phantom was used to make a complete set of ultrasound images in B-Mode. Pre-processing steps such as gamma corrections, contrast stretching and filtering accompanied by morphological Image Processing were among the steps that were applied to find the final image. All output images were reviewed and marked by two experienced radiologists. Statistical analysis showed a sensitivity of 100% and accuracy of 99% for proposed work. It also showed that the same procedure can be use for cystic and solid breast masses with small changes.

Snake, active contour or deformable active contour has been widely used in medical image segmentation area. In this paper, comparison between Gradient Vector Flow (GVF) snake and Enhanced Distance (ED) snake in segmenting microcalcifications is carried out. The performance is measured based on actual area of the average percentage difference traced by expert radiologists. Results obtained shows that the values of average percentage difference for the GVF and ED snake are 4.3% and 6.68% respectively. These results indicate that the GVF snake has better performance with 95.7%.

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%).

Segmentation of brain MRI is the core part in plenty of medical image processing methods. Due to some properties of MR images such as intensity inhomogeneity of tissues, partial volume effect, noise and some other imaging artifacts, segmentation of brain MRI based on voxel gray values is prone to error. Hence involving problem specific information and expert knowledge in designing segmentation algorithms seems to be useful. A two-fold fuzzy segmentation algorithm based on Bayesian method is proposed in this paper. The Bayesian part uses the gray value of voxels in segmenting images and the segmented image is used as the input to fuzzy classifier to improve the misclassified voxels especially in borders between tissues. Similarity index is used to compare our algorithm with the well known method of Ashburner which has been implemented by Statistical Parametric Mapping (SPM) software. Two different brain MRI datasets are used to evaluate the algorithm. Brainweb as a simulated brain MRI dataset and ADNI as real brain MRI dataset are practiced images. Results show that our algorithm performs well in comparison with the one implemented in SPM. It can be concluded that incorporating expert knowledge and problem specific information in segmentation process improve segmentation result. The major advantage of proposed method is that one can update the knowledge base and incorporate new information into segmentation process by adding new fuzzy rules.

Skull stripping is a major phase in MRI brain imaging applications and it refers to the removal of its non-cerebral tissues. The main problem in skull-stripping is the segmentation of the non-cerebral and the intracranial tissues due to their homogeneity intensities. As morphology requires prior binarization of the image, this paper proposed mathematical morphology segmentation using double and Otsu's thresholding. The purpose is to identify robust threshold values to remove the non-cerebral tissue from MRI brain images. Ninety collected samples of T1-weighted, T2-weighted and FLAIR MRI brain images are used in the experiments. The results showed promising use of double threholding as a robust threshold value in handling intensity inhomogeneities compared to Otsu's thresholding.

The 3S (Shrinking-Search-Space) multi-thresholding method which have been used for segmentation of medical images according to their intensities, now have been implemented and compared with FCM method in terms of segmentation quality and segmentation time as a benchmark in thresholding. The results show that 3S method produced almost the same segmentation quality or in some occasions better quality than FCM, and the computation time of 3S method is much lower than FCM. This is another superiority of this method with respect to others. Also, the performance of C-means has been compared with two other methods. This comparison shows that, C-means is not a reliable clustering algorithm and it needs several run to give us a reliable result.

Mammography is a known method for the early detection of breast cancer. However, the mammograms which are in black and white and in the shade of grey have some limitations in portraying the abnormalities. Image segmentation is a very crucial process in detecting abnormalities in computed radiography mammographic images. Active contours which are known as 'snake' are dynamic algorithms which can be used to perform the image segmentation. In order to test the applicability of the snake algorithm in performing segmentation, the breast phantom MRI-156 images are used. Only the breast phantom images at the exposures of 25 kV, 28 kV and 35 kV with milliampere (mAs) of 0.5 are considered. It is found that when the image is divided into four equal regions, the detection of abnormalities in the image is more effective as compared to the image processed as a whole.

Image segmentation is a key process in computer vision and image process applications. Accurate segmentation of medical images is very essential in medical applications but it is very difficult job due to noise and in homogeneity that are usual of medical images. In this paper a new method, based on FCM, is proposed to make FCM more robust against noise. Multi-scale images are obtained by smoothing input image in different scales. FCM is applied to multi-scale images from high scale to low scale. First FCM is applied to image with highest scale. Then in each scale, cluster centers of previous scale are used to initialization membership for current scale. Moreover, in FCM, neighborhood attraction is used to more decrease effect of noise in clustering. Experimental result shows effectiveness of new method.

Image segmentation is a critical stage in many computer vision and image process applications. Accurate segmentation of medical images is very essential in Medical applications but it is very difficult job due to noise and in homogeneity. Fuzzy C-Mean (FCM) is one of the most popular Medical image clustering methods. We noticed that for some images, FCM is sensitive to initialization of centre of clusters. This article introduced a new method based on the combination of genetic algorithm and FCM to solve this problem. The genetic algorithm is used to find initialized centre of the clusters. In this method, the centre is obtained by minimizing an object Function. This object Function specifies sum of distances between each data and their cluster centres. Then FCM is applied with to the case. The experimental result demonstrates the effectiveness of new method by able to initialize centre of the clusters.

Micro calcifications in mammograms can be very hard to detect because of the different shapes of these tumors and because of the confusion with the background texture. Different wavelet filters' abilities are investigated to detect micro calcifications in mammogram-digitized images obtained from a Malaysian women sample. The images are obtained from a major hospital with positive micro calcifications in them identified by two separate radiologists. The wavelets' abilities to decompose the images into different sub bands localized both in frequency and time domains is utilized decomposing a set of mammogram images into different frequency sub bands and then reconstructing the images with the high frequency components, which correspond to details in the images (micro calcifications) and removing the low frequency components that correspond to the smooth background of the mammogram. Finally evaluation is done on the separate filters by consultations with the radiologists to confirm the results of detections.