Level Set Segmentation Algorithm Research Articles

Radiation therapy effects on white matter fiber tracts of the limbic circuit

To segment fiber tracts in the limbic circuit and to assess their sensitivity to radiation therapy (RT). Twelve patients with brain metastases who had received fractionated whole brain radiation therapy to 30 Gy or 37.5 Gy were included in the study. Diffusion weighted images were acquired pre-RT, at the end of RT, and 1-month post-RT. The fornix, corpus callosum, and cingulum were extracted from diffusion weighted images by combining fiber tracking and segmentation methods based upon characteristics of the fiber bundles. Cingulum was segmented by a seed-based tractography, fornix by a region of interests (ROI)-based tractography, and corpus callosum by a level-set segmentation algorithm. The radiation-induced longitudinal changes of diffusion indices of the structures were evaluated. Significant decreases were observed in the fractional anisotropy of the posterior part of the cingulum, fornix, and corpus callosum from pre-RT to end of RT by -14.0%, -12.5%, and -5.2%, respectively (p < 0.001), and from pre-RT to 1-month post-RT by -11.9%, -12.8%, and -6.4%, respectively (p < 0.001). Moreover, significant increases were observed in the mean diffusivity of the corpus callosum and the posterior part of the cingulum from pre-RT to end of RT by 6.8% and 6.5%, respectively, and from pre-RT to 1-month post-RT by 8.5% and 6.3%, respectively. The increase in the radial diffusivity primarily contributed to the significant decrease in the fractional anisotropy, indicating that demyelination is the predominant radiation effect on the white matter structures. Our findings indicate that the fornix and the posterior part of the cingulum are significantly susceptible to radiation damage. We have developed robust computer-aided semiautomatic segmentation and fiber tracking tools to facilitate the ROI delineation of critical structures, which is important for assessment of radiation damage in a longitudinal fashion.

WE-G-217A-04: Segmenting Limbic Circuit Fiber Tracts for Quantifying Changes in Diffusion Indices Due to Partial Radiation Therapy.

To segment the cingulum, fornix and the corpus callosum using diffusion weighted images, in order to evaluate the radiation-induced damage on these important white matter structures Methods: We propose a seed-based tractography algorithm for segmenting the entire cingulum into the left and right anterior, superior, and posterior subdivisions. In that algorithm, multiple ROIs (regions of interest) for tractography are automatically created from seeded points by a level-set segmentation algorithm. Moreover, we propose new ROI placements for fornix tractography. Furthermore, a new subdividing method is proposed for supporting the possible rotation in the corpus callosum longitudinal axis in presence of glioma tumors. To test the reproducibility of the proposed algorithm for segmenting the cingulum, test-retest diffusion tensor data-sets of twelve patients were chosen from the National Biomedical Imaging Archive database. We calculated the Dice coefficients of the volumetric overlap between the test and retest cingulum segments. Twenty-two patients with low grade brain gliomas underwent 6-week fractionated radiation therapy (RT). The patients prospectively enrolled MRI with diffusion tensor imaging up to 18 months after starting RT. The fornix and subdivisions of cingulum and corpus callosum were segmented. The Dice coefficients between test and retest data were 0.878, 0.899, 0.951, 0.954, 0.926, and 0.929 for the anterior right and left, the superior right and left, and the posterior right and left cingulum segments respectively, suggesting our method's high reproducibility. Amongst the fornix and subdivisions of cingulum and corpus callosum, the most significant changes in fractional anisotropy, mean, axial, and radial diffusivity were observed in fornix throughout all dose volumes, indicating that both axonal degradation and dysmyelination are prominent radiation effects in the fornix. The proposed seed-based tractography method segments the cingulum accurately and completely with dramatically reducing the operator's interaction time and effort in manual depicting large number of ROIs. Supported in part by National Institutes of Health grants RO1 NS064973.

Level Set Segmentation Method in Medical Image Segmentation Research and Application

Medical image segmentation can be divided into two categories: one is the region of interest (ROI) identification; the other is the description of the integrity and the extraction of interest region. The emergence of the level set method greatly promoted the development of medical image segmentation. This paper studies three different level set segmentation algorithm to achieve the effective segmentation for brain gray matter and white matter of MRI image.

Endocardial border detection in cardiac magnetic resonance images using level set method.

Segmentation of the left ventricle in MRI images is a task with important diagnostic power. Currently, the evaluation of cardiac function involves the global measurement of volumes and ejection fraction. This evaluation requires the segmentation of the left ventricle contour. In this paper, we propose a new method for automatic detection of the endocardial border in cardiac magnetic resonance images, by using a level set segmentation-based approach. To initialize this level set segmentation algorithm, we propose to threshold the original image and to use the binary image obtained as initial mask for the level set segmentation method. For the localization of the left ventricular cavity, used to pose the initial binary mask, we propose an automatic approach to detect this spatial position by the evaluation of a metric indicating object's roundness. The segmentation process starts by the initialization of the level set algorithm and ended up through a level set segmentation. The validation process is achieved by comparing the segmentation results, obtained by the automated proposed segmentation process, to manual contours traced by tow experts. The database used was containing one automated and two manual segmentations for each sequence of images. This comparison showed good results with an overall average similarity area of 97.89%.

Volume measurement of bone erosions in magnetic resonance images of patients with rheumatoid arthritis

The volume of bone erosions in the metacarpophalangeal joints is a radiological feature that can be used to track the progression of rheumatoid arthritis. We introduce a hybrid segmentation algorithm that combines region growing and level-set segmentation algorithms to semiautomatically measure the volume of bone erosions in magnetic resonance images. A total of 40 rheumatoid arthritis patients were included in the study. The scans of eight patients were used for training, whereas the remaining 32 scans were used to determine the accuracy, precision, and speed of the technique. The reproducibility of the semiautomated technique and that of manual segmentation was defined in terms of intraclass correlation coefficients. Both techniques were equally precise with intraclass correlation coefficient values greater than 0.9. The hybrid algorithm was highly accurate: the least squares fit between the semiautomated segmentations to those manually traced by a musculoskeletal radiologist resulted in a slope of 1.030 with an x-intercept of 1.385 mm(3) and an R(2) value of 0.923. The semiautomated technique was significantly faster than manual segmentation, which took two to four times longer to complete. Our hybrid algorithm shows promise in the quantitative assessment of radiological features of rheumatoid arthritis in a clinical setting.

A framework for comparing different image segmentation methods and its use in studying equivalences between level set and fuzzy connectedness frameworks

In the current vast image segmentation literature, there seems to be considerable redundancy among algorithms, while there is a serious lack of methods that would allow their theoretical comparison to establish their similarity, equivalence, or distinctness. In this paper, we make an attempt to fill this gap. To accomplish this goal, we argue that: (1) every digital segmentation algorithm A should have a well defined continuous counterpart M A , referred to as its model, which constitutes an asymptotic of A when image resolution goes to infinity; (2) the equality of two such models M A and M A ′ establishes a theoretical (asymptotic) equivalence of their digital counterparts A and A ′ . Such a comparison is of full theoretical value only when, for each involved algorithm A , its model M A is proved to be an asymptotic of A . So far, such proofs do not appear anywhere in the literature, even in the case of algorithms introduced as digitizations of continuous models, like level set segmentation algorithms. The main goal of this article is to explore a line of investigation for formally pairing the digital segmentation algorithms with their asymptotic models, justifying such relations with mathematical proofs, and using the results to compare the segmentation algorithms in this general theoretical framework. As a first step towards this general goal, we prove here that the gradient based thresholding model M ▿ is the asymptotic for the fuzzy connectedness Udupa and Samarasekera segmentation algorithm used with gradient based affinity A ▿ . We also argue that, in a sense, M ▿ is the asymptotic for the original front propagation level set algorithm of Malladi, Sethian, and Vemuri, thus establishing a theoretical equivalence between these two specific algorithms. Experimental evidence of this last equivalence is also provided.

Level-Set Segmentation Algorithm Combined with Local Gray Threshold on Image Sequences of Neuron Stem Cells

Level-Set Segmentation Algorithm Combined with Local Gray Threshold on Image Sequences of Neuron Stem Cells

WE‐C‐BRB‐05: Tracking of Thoracic Tumor Using EPID for Respiratory Gating Purposes: A Retrospective Feasibility Study

Purpose: Conventional respiratory gating relies on an external surrogate which might provide suboptimal tracking of the tumor in many cases. In the present study, an attempt has been made to exploit the density differences between the tumor and its surrounding lung tissue to gate treatments directly using electronic portal imaging device [EPID]. Material &amp; Methods: Varian Trilogy unit equipped with EPID [AS1000, resolution 1024×1024] was used. During treatment, a custom designed image acquisition template captured the portal images. The treatment plan along with the raw scan data and structures was also exported. DRRs for each field with the tumor [hereafter referred as nodule] projection overlaid on it, were also exported and were used as a shaped prior. Nodule was segmented in each portal image using a level set segmentation algorithm which includes an energy term that is minimized when the shape of the segmented region matches the shape prior. Results: The nodule segmentation algorithm was evaluated on a series of 20 portal images of a nodule located just above the diaphragm. The nodule has an average distance from the center of the portal of 5.68 mm with the standard deviation, minimum, and maximum distance of 1.79, 2.44, and 9.13 mm, respectively. The distance between the nodule and segmented region center was 1.98 mm and the standard deviation, minimum, and maximum distance being 0.96, 0.13, and 4.12 mm, respectively. The average &amp; maximum position error between the portal and nodule center could be reduced by 35% &amp; 45%, respectively, using the nodule segmentation algorithm. Present runtime of 4 seconds will be reduced to real‐time as the algorithm is being ported to graphic cards [GPUs]. Conclusion: The proposed method utilizes the tumor motion directly, thereby, eliminating an external surrogate system and its associated inaccuracies and offers promise for respiratory gating treatment delivery.

An automatic system for in vitro cell migration studies

This paper describes a system for in vitro cell migration analysis. Adult neural stem/progenitor cells are studied using time-lapse bright-field microscopy and thereafter stained immunohistochemically to find and distinguish undifferentiated glial progenitor cells and cells having differentiated into type-1 or type-2 astrocytes. The cells are automatically segmented and tracked through the time-lapse sequence. An extension to the Chan-Vese Level Set segmentation algorithm, including two new terms for specialized growing and pruning, made it possible to resolve clustered cells, and reduced the tracking error by 65%. We used a custom-built manual correction module to form a ground truth used as a reference for tracked cells that could be identified from the fluorescence staining. On average, the tracks were correct 95% of the time, using our new segmentation. The tracking, or association of segmented cells, was performed using a 2-state Hidden Markov Model describing the random behaviour of the cells. By re-estimating the motion model to conform with the segmented data we managed to reduce the number of tracking parameters to essentially only one. Upon characterization of the cell migration by the HMM state occupation function, it was found that glial progenitor cells were moving randomly 2/3 of the time, while the type-2 astrocytes showed a directed movement 2/3 of the time. This finding indicates possibilities for cell-type specific identification and cell sorting of live cells based on specific movement patterns in individual cell populations, which would have valuable applications in neurobiological research.

Level set segmentation of bovine corpora lutea in ex situ ovarian ultrasound images

BackgroundThe objective of this study was to investigate the viability of level set image segmentation methods for the detection of corpora lutea (corpus luteum, CL) boundaries in ultrasonographic ovarian images. It was hypothesized that bovine CL boundaries could be located within 1–2 mm by a level set image segmentation methodology.MethodsLevel set methods embed a 2D contour in a 3D surface and evolve that surface over time according to an image-dependent speed function. A speed function suitable for segmentation of CL's in ovarian ultrasound images was developed. An initial contour was manually placed and contour evolution was allowed to proceed until the rate of change of the area was sufficiently small. The method was tested on ovarian ultrasonographic images (n = 8) obtained ex situ. A expert in ovarian ultrasound interpretation delineated CL boundaries manually to serve as a "ground truth". Accuracy of the level set segmentation algorithm was determined by comparing semi-automatically determined contours with ground truth contours using the mean absolute difference (MAD), root mean squared difference (RMSD), Hausdorff distance (HD), sensitivity, and specificity metrics.Results and discussionThe mean MAD was 0.87 mm (sigma = 0.36 mm), RMSD was 1.1 mm (sigma = 0.47 mm), and HD was 3.4 mm (sigma = 2.0 mm) indicating that, on average, boundaries were accurate within 1–2 mm, however, deviations in excess of 3 mm from the ground truth were observed indicating under- or over-expansion of the contour. Mean sensitivity and specificity were 0.814 (sigma = 0.171) and 0.990 (sigma = 0.00786), respectively, indicating that CLs were consistently undersegmented but rarely did the contour interior include pixels that were judged by the human expert not to be part of the CL. It was observed that in localities where gradient magnitudes within the CL were strong due to high contrast speckle, contour expansion stopped too early.ConclusionThe hypothesis that level set segmentation can be accurate to within 1–2 mm on average was supported, although there can be some greater deviation. The method was robust to boundary leakage as evidenced by the high specificity. It was concluded that the technique is promising and that a suitable data set of human ovarian images should be obtained to conduct further studies.

Image Segmentation Project - Open source software practices class

This document describes implementation of two Level-set segmentation algorithms using Insight Toolkit ITK . The algorithms chosen for implementation are are 1) Geodesic Active contour Levelset segmentation and 2) Shape Detection Levelset segmentation. The project is oriented to expose the concepts of Open Data, Open Source and Open Access which form the pillars of open-source software ideology.

SU‐EE‐A2‐03: Evaluation of Auto‐Segmentation Tools for the Target Definition for the Treatment of Lung Cancer

Purpose: With the advent of more sophisticated image devices in the treatment room, image guided radiotherapy (IGRT) and adaptive radiotherapy (ART) have become distinct possibilities. IGRT and ART techniques in their various stages have been implemented in clinics. One of the ART techniques using the daily acquired CT images involves re‐planning due to the target shape variation during the treatment. Lung cancer volumes of some cases are observed to undergo significant changes where re‐planning is a necessity. To be able to define target efficiently can help the treatment flow significantly. This study evaluates various auto or semi‐auto contouring tools either commercially available or under development for their accuracy and ease of use. Method and Materials: Three methods are included in the study. Two are commercially available (Focal,CMS): auto threshold (of gray level); and auto Segmentation where gray level, the edges and prior shape information are used. The third method is the ITK‐SNAP program that uses a powerful level set(snake) segmentation algorithm to segment anatomical structures in three dimensions. Results: Ten image sets from helical and cone beam CTs are included in the study. The acceptable contours are defined as those with distance to agreement to those drawn by radiation oncologists less than 3 mm. For target volume surrounded by normal lung, the percentage slices of contours that do not need manual adjustment are 41–62%, 23–39%, 62–78% for threshold, auto‐segmentation and SNAP respectively. For cone beam CT, these numbers are approximately 10% lower. SNAP can also be used for target volume with no clear boundary, although the percentage success is much lower. Conclusion: More sophisticated auto‐segmentation tools need to be available routinely with more flexibility for users to adjust algorithm parameters in order for them to be useful for routine clinical ART purposes.