Browsing by Subject "Image segmentation"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item An efficient approach to automated segmentation in medical image analysis(Texas Tech University, 2005-12) Gao, Fei; Mitra, Sunanda; Mitra, Sunanda; Karp, Tanja; Nutter, Brian; Nutter, Brian; Karp, TanjaAutomatic image segmentation is widely used in medical image analysis. However, an efficient way of automated segmentation is difficult to achieve. In this thesis, a survey of current image segmentation methods and their possible applications to identify Cervical Intraepithelial Neoplasia (CIN) are introduced. Approaches to Cervix image segmentation and analysis are discussed. A very efficient algorithm for segmentation of acetowhite regions is developed, verified and compared with other existing methodologies in this thesis. Several image processing methodologies and mathematical operations are exploited and applied to this research work. Although the success of the applied algorithms is highly dependent on the quality of the images used, statistical results regarding the feature extraction, running time and pattern classification are obtained and found to be quite satisfactory. Further identification and classification of some of the lesions within the acetowhite regions of the uterine cervix have also been achieved. This efficient automatic segmentation and classification methodology will greatly facilitate content-based image retrieval from digital archives of cervix images and has the potential of playing a significant role to the development of an image-based screening tool for Cervical Cancer.Item An efficient approach to automated segmentation in medical image analysis(2006-05) Gao, Fei; Mitra, Sunanda; Karp, Tanja; Nutter, BrianAutomatic image segmentation is widely used in medical image analysis. However, an efficient way of automated segmentation is difficult to achieve. In this thesis, a survey of current image segmentation methods and their possible applications to identify Cervical Intraepithelial Neoplasia (CIN) are introduced. Approaches to Cervix image segmentation and analysis are discussed. A very efficient algorithm for segmentation of acetowhite regions is developed, verified and compared with other existing methodologies in this thesis. Several image processing methodologies and mathematical operations are exploited and applied to this research work. Although the success of the applied algorithms is highly dependent on the quality of the images used, statistical results regarding the feature extraction, running time and pattern classification are obtained and found to be quite satisfactory. Further identification and classification of some of the lesions within the acetowhite regions of the uterine cervix have also been achieved. This efficient automatic segmentation and classification methodology will greatly facilitate content-based image retrieval from digital archives of cervix images and has the potential of playing a significant role to the development of an image-based screening tool for Cervical Cancer.Item Estimating volume of an object from two profile images(2010-12) Block, Scott T.; Pal, Ranadip; Nutter, BrianEstimating the volume of an object from two dimensional cross-sectional images of the object has applications in preventive and therapeutic medicine, automated industrial processing and defense. In this thesis, we present various approaches to achieve volume estimation from two profile images of the coronal (front) and sagittal (side) planes. The initial step in the process is segmenting the image to extract the object information. Secondly, the binary profile images are used to represent object slices based on an ellipse or rectangular cross section. The next step in estimating the volume is based on summing up the individual slice volumes along the height of the object. The known height of the object is used to give a relationship between the voxel volume and the actual volume. Finally objects of known volume are used to correct errors that may have occurred during segmentation and some of the optical effects of the camera. The thesis presents existing and modified approaches to achieve fast volume estimation from profile images.Item Reconstruction of 3D Neuronal Structures from Densely Packed Electron Microscopy Data Stacks(2012-10-19) Yang, Huei-FangThe goal of fully decoding how the brain works requires a detailed wiring diagram of the brain network that reveals the complete connectivity matrix. Recent advances in high-throughput 3D electron microscopy (EM) image acquisition techniques have made it possible to obtain high-resolution 3D imaging data that allows researchers to follow axons and dendrites and to identify pre-synaptic and post-synaptic sites, enabling the reconstruction of detailed neural circuits of the nervous system at the level of synapses. However, these massive data sets pose unique challenges to structural reconstruction because the inevitable staining noise, incomplete boundaries, and inhomogeneous staining intensities increase difficulty of 3D reconstruction and visualization. In this dissertation, a new set of algorithms are provided for reconstruction of neuronal morphology from stacks of serial EM images. These algorithms include (1) segmentation algorithms for obtaining the full geometry of neural circuits, (2) interactive segmentation tools for manual correction of erroneous segmentations, and (3) a validation method for obtaining a topologically correct segmentation when a set of segmentation alternatives are available. Experimental results obtained by using EM images containing densely packed cells demonstrate that (1) the proposed segmentation methods can successfully reconstruct full anatomical structures from EM images, (2) the editing tools provide a way for the user to easily and quickly refine incorrect segmentations, (3) and the validation method is effective in combining multiple segmentation results. The algorithms presented in this dissertation are expected to contribute to the reconstruction of the connectome and to open new directions in the development of reconstruction methods.Item Segmentation of radiographs of cervical spine using level sets(Texas Tech University, 2006-05) Raju, Rama Krishna; Sari-Sarraf, Hamed; Hequet, Eric F.; Karp, TanjaThis thesis proposes a novel level set segmentation technique to segment medical radiographs of cervical spine. In the past, the level set technique has been used alongside shape information of the target object. To the best of our knowledge, in most methods the curve is evolved towards the boundary using shape information complimented by region based or edge information. However, in many applications like ours, the region based information is non-existent and level set evolution starting from an arbitrary initial curve is difficult.Thus, we propose a method that uses the shape estimate as the initial curve and then evolve it towards the nearest edges in the image. We also present the performance analysis of our approach.