901 resultados para Classification image technique
Resumo:
We propose a novel methodology to generate realistic network flow traces to enable systematic evaluation of network monitoring systems in various traffic conditions. Our technique uses a graph-based approach to model the communication structure observed in real-world traces and to extract traffic templates. By combining extracted and user-defined traffic templates, realistic network flow traces that comprise normal traffic and customized conditions are generated in a scalable manner. A proof-of-concept implementation demonstrates the utility and simplicity of our method to produce a variety of evaluation scenarios. We show that the extraction of templates from real-world traffic leads to a manageable number of templates that still enable accurate re-creation of the original communication properties on the network flow level.
Resumo:
External beam proton radiation therapy has been used since 1975 to treat choroidal melanoma. For tumor location determination during proton radiation treatment, surgical tantalum clips are registered with image data. This report introduces the intraoperative application of an opto-electronic navigation system to determine with high precision the position of the tantalum markers and their spatial relationship to the tumor and anatomical landmarks. The application of the technique in the first 4 patients is described.
Resumo:
Current methods to characterize mesenchymal stem cells (MSCs) are limited to CD marker expression, plastic adherence and their ability to differentiate into adipogenic, osteogenic and chondrogenic precursors. It seems evident that stem cells undergoing differentiation should differ in many aspects, such as morphology and possibly also behaviour; however, such a correlation has not yet been exploited for fate prediction of MSCs. Primary human MSCs from bone marrow were expanded and pelleted to form high-density cultures and were then randomly divided into four groups to differentiate into adipogenic, osteogenic chondrogenic and myogenic progenitor cells. The cells were expanded as heterogeneous and tracked with time-lapse microscopy to record cell shape, using phase-contrast microscopy. The cells were segmented using a custom-made image-processing pipeline. Seven morphological features were extracted for each of the segmented cells. Statistical analysis was performed on the seven-dimensional feature vectors, using a tree-like classification method. Differentiation of cells was monitored with key marker genes and histology. Cells in differentiation media were expressing the key genes for each of the three pathways after 21 days, i.e. adipogenic, osteogenic and chondrogenic, which was also confirmed by histological staining. Time-lapse microscopy data were obtained and contained new evidence that two cell shape features, eccentricity and filopodia (= 'fingers') are highly informative to classify myogenic differentiation from all others. However, no robust classifiers could be identified for the other cell differentiation paths. The results suggest that non-invasive automated time-lapse microscopy could potentially be used to predict the stem cell fate of hMSCs for clinical application, based on morphology for earlier time-points. The classification is challenged by cell density, proliferation and possible unknown donor-specific factors, which affect the performance of morphology-based approaches. Copyright © 2012 John Wiley & Sons, Ltd.
Resumo:
Presenting visual feedback for image-guided surgery on a monitor requires the surgeon to perform time-consuming comparisons and diversion of sight and attention away from the patient. Deficiencies in previously developed augmented reality systems for image-guided surgery have, however, prevented the general acceptance of any one technique as a viable alternative to monitor displays. This work presents an evaluation of the feasibility and versatility of a novel augmented reality approach for the visualisation of surgical planning and navigation data. The approach, which utilises a portable image overlay device, was evaluated during integration into existing surgical navigation systems and during application within simulated navigated surgery scenarios.
Resumo:
Image-guided microsurgery requires accuracies an order of magnitude higher than today's navigation systems provide. A critical step toward the achievement of such low-error requirements is a highly accurate and verified patient-to-image registration. With the aim of reducing target registration error to a level that would facilitate the use of image-guided robotic microsurgery on the rigid anatomy of the head, we have developed a semiautomatic fiducial detection technique. Automatic force-controlled localization of fiducials on the patient is achieved through the implementation of a robotic-controlled tactile search within the head of a standard surgical screw. Precise detection of the corresponding fiducials in the image data is realized using an automated model-based matching algorithm on high-resolution, isometric cone beam CT images. Verification of the registration technique on phantoms demonstrated that through the elimination of user variability, clinically relevant target registration errors of approximately 0.1 mm could be achieved.
Resumo:
Hydrogels are composed of cross-linked networks of hydrophilic polymers that are biocompatible due to their high water content. Mass transfer through hydrogels has been suggested as an effective method of drug delivery, specifically in degradable polymers to minimize lasting effects within the body. Diffusion of small molecules in poly (ethylene glycol) diacrylate (PEG-DA) and dextran methacrylate (dex-MA) hydrogels was characterized in a microfluidic device and by complementary techniques. Microfluidic devices were prepared by crosslinking a formulation of hydrogel and photo-initiator, with and without visible dye, using photolithography to define a central microchannel. Channel sizes within the devices were approximately 600 ¿m to simulate vessels within the body. The microfluidic technique allows for both image and effluent analyses. To visualize the diffusive behavior within the dextran hydrogel, methylene blue and sulforhodamine 101 dyes were used in both elution and uptake experiments. Three analysis techniques for measuring diffusion coefficients were used to quantify the diffusion of solute in the hydrogel, including optical microscopy, characterization of device effluent, and NMR analyses. The optical microscopy technique analyzes images of the dye diffusion captured by a stereomicroscope to generate dye concentration v. position profiles. The data was fit to a diffusion model to determine diffusion coefficients and the dye release profile. In a typical elution experiment, aqueous solution is pumped through the microchannel and dye diffuses out of the hydrogel and into the aqueous phase. During elution, images are taken at regular time intervals and the effluent was collected. Analysis of the device effluent was performed using ultraviolet-visible (UV/Vis) spectroscopy to determine the effluent dye concentration and thus a short-time diffusion coefficient. Nuclear magnetic resonance (NMR) was used to determine a free diffusion coefficient of molecules in hydrogel without the effect of a concentration gradient. Diffusion coefficients for methylene blue and sulforhodamine 101 dyes in dex-MA hydrogel calculated using the three analysis methods all agree well. It was determined that utilizing a combination of the three techniques offers greater insight into molecular diffusion in hydrogels than employing each technique individually. The use of the same microfluidic devices used to measure diffusion is explored in the use of studying the degradation of dex-MA hydrogels. By combining what is known about the degradation rate in regards to the effect of pH and crosslinking and the ability to use a dye solution in contrast to establish the hydrogel boundaries could be a novel approach to studying hydrogel degradation.
Resumo:
PURPOSE: A microangiographical technique is described, which allows visualization of small and capillary blood vessels and quantification of fasciocutaneous blood vessels by means of digital computer analysis in very small laboratory animals. MATERIALS AND METHODS: The left carotid artery of 20 nu/nu mice was cannulated (26 gauge) and a mixture of gelatin, bariumsulfate, and green ink was injected according to standardized protocol. Fasciocutaneous blood vessels were visualized by digital mammography and analyzed for vessel length and vessel surface area as standardized units [SU] by computer program. RESULTS: With the described microangiography method, fasciocutaneous blood vessels down to capillary size level can be clearly visualized. Regions of interest (ROIs) can be defined and the containing vascular network quantified. Comparable results may be obtained by calculating the microvascular area index (MAI) and the microvascular length index (MLI), related to the ROIs size. Identical ROIs showed a high reproducibility for measured [SU] < 0.01 +/- 0.0012%. CONCLUSION: Combining microsurgical techniques, pharmacological knowledge, and modern digital image technology, we were able to visualize small and capillary blood vessels even in small laboratory animals. By using our own computer analytical program, quantification of vessels was reliable, highly reproducible, and fast.
Resumo:
The verification possibilities of dynamically collimated treatment beams with a scanning liquid ionization chamber electronic portal image device (SLIC-EPID) are investigated. The ion concentration in the liquid of a SLIC-EPID and therefore the read-out signal is determined by two parameters of a differential equation describing the creation and recombination of the ions. Due to the form of this equation, the portal image detector describes a nonlinear dynamic system with memory. In this work, the parameters of the differential equation were experimentally determined for the particular chamber in use and for an incident open 6 MV photon beam. The mathematical description of the ion concentration was then used to predict portal images of intensity-modulated photon beams produced by a dynamic delivery technique, the sliding window approach. Due to the nature of the differential equation, a mathematical condition for 'reliable leaf motion verification' in the sliding window technique can be formulated. It is shown that the time constants for both formation and decay of the equilibrium concentration in the chamber is in the order of seconds. In order to guarantee reliable leaf motion verification, these time constants impose a constraint on the rapidity of the image-read out for a given maximum leaf speed. For a leaf speed of 2 cm s(-1), a minimum image acquisition frequency of about 2 Hz is required. Current SLIC-EPID systems are usually too slow since they need about a second to acquire a portal image. However, if the condition is fulfilled, the memory property of the system can be used to reconstruct the leaf motion. It is shown that a simple edge detecting algorithm can be employed to determine the leaf positions. The method is also very robust against image noise.
Resumo:
BACKGROUND: Recent advances in the understanding of the anatomy and function of the acetabular labrum suggest that it is important for normal joint function. We found no available data regarding whether labral refixation after treatment of femoro-acetabular impingement affects the clinical and radiographic results. METHODS: We retrospectively reviewed the clinical and radiographic results of fifty-two patients (sixty hips) with femoro-acetabular impingement who underwent arthrotomy and surgical dislocation of the hip to allow trimming of the acetabular rim and femoral osteochondroplasty. In the first twenty-five hips, the torn labrum was resected (Group 1); in the next thirty-five hips, the intact portion of the labrum was reattached to the acetabular rim (Group 2). At one and two years postoperatively, the Merle d'Aubigné clinical score and the Tönnis arthrosis classification system were used to compare the two groups. RESULTS: At one year postoperatively, both groups showed a significant improvement in their clinical scores (mainly pain reduction) compared with their preoperative values (p = 0.0003 for Group 1 and p < 0.0001 for Group 2). At two years postoperatively, 28% of the hips in Group 1 (labral resection) had an excellent result, 48% had a good result, 20% had a moderate result, and 4% had a poor result. In contrast, in Group 2 (labral reattachment), 80% of the hips had an excellent result, 14% had a good result, and 6% had a moderate result. Comparison of the clinical scores between the two groups revealed significantly better outcomes for Group 2 at one year (p = 0.0001) and at two years (p = 0.01). Radiographic signs of osteoarthritis were significantly more prevalent in Group 1 than in Group 2 at one year (p = 0.02) and at two years (p = 0.009). CONCLUSIONS: Patients treated with labral refixation recovered earlier and had superior clinical and radiographic results when compared with patients who had undergone resection of a torn labrum. Although the results must be considered preliminary, we now recommend refixation of the intact portion of the labrum after trimming of the acetabular rim during surgical treatment of femoro-acetabular impingement.
Resumo:
A post classification change detection technique based on a hybrid classification approach (unsupervised and supervised) was applied to Landsat Thematic Mapper (TM), Landsat Enhanced Thematic Plus (ETM+), and ASTER images acquired in 1987, 2000 and 2004 respectively to map land use/cover changes in the Pic Macaya National Park in the southern region of Haiti. Each image was classified individually into six land use/cover classes: built-up, agriculture, herbaceous, open pine forest, mixed forest, and barren land using unsupervised ISODATA and maximum likelihood supervised classifiers with the aid of field collected ground truth data collected in the field. Ground truth information, collected in the field in December 2007, and including equalized stratified random points which were visual interpreted were used to assess the accuracy of the classification results. The overall accuracy of the land classification for each image was respectively: 1987 (82%), 2000 (82%), 2004 (87%). A post classification change detection technique was used to produce change images for 1987 to 2000, 1987 to 2004, and 2000 to 2004. It was found that significant changes in the land use/cover occurred over the 17- year period. The results showed increases in built up (from 10% to 17%) and herbaceous (from 5% to 14%) areas between 1987 and 2004. The increase of herbaceous was mostly caused by the abandonment of exhausted agriculture lands. At the same time, open pine forest and mixed forest areas lost (75%) and (83%) of their area to other land use/cover types. Open pine forest (from 20% to 14%) and mixed forest (from18 to 12%) were transformed into agriculture area or barren land. This study illustrated the continuing deforestation, land degradation and soil erosion in the region, which in turn is leading to decrease in vegetative cover. The study also showed the importance of Remote Sensing (RS) and Geographic Information System (GIS) technologies to estimate timely changes in the land use/cover, and to evaluate their causes in order to design an ecological based management plan for the park.
Resumo:
For a fluid dynamics experimental flow measurement technique, particle image velocimetry (PIV) provides significant advantages over other measurement techniques in its field. In contrast to temperature and pressure based probe measurements or other laser diagnostic techniques including laser Doppler velocimetry (LDV) and phase Doppler particle analysis (PDPA), PIV is unique due to its whole field measurement capability, non-intrusive nature, and ability to collect a vast amount of experimental data in a short time frame providing both quantitative and qualitative insight. These properties make PIV a desirable measurement technique for studies encompassing a broad range of fluid dynamics applications. However, as an optical measurement technique, PIV also requires a substantial technical understanding and application experience to acquire consistent, reliable results. Both a technical understanding of particle image velocimetry and practical application experience are gained by applying a planar PIV system at Michigan Technological University’s Combustion Science Exploration Laboratory (CSEL) and Alternative Fuels Combustion Laboratory (AFCL). Here a PIV system was applied to non-reacting and reacting gaseous environments to make two component planar PIV as well as three component stereographic PIV flow field velocity measurements in conjunction with chemiluminescence imaging in the case of reacting flows. This thesis outlines near surface flow field characteristics in a tumble strip lined channel, three component velocity profiles of non-reacting and reacting swirled flow in a swirl stabilized lean condition premixed/prevaporized-fuel model gas turbine combustor operating on methane at 5-7 kW, and two component planar PIV measurements characterizing the AFCL’s 1.1 liter closed combustion chamber under dual fan driven turbulent mixing flow.
Resumo:
Quantifying belowground dynamics is critical to our understanding of plant and ecosystem function and belowground carbon cycling, yet currently available tools for complex belowground image analyses are insufficient. We introduce novel techniques combining digital image processing tools and geographic information systems (GIS) analysis to permit semi-automated analysis of complex root and soil dynamics. We illustrate methodologies with imagery from microcosms, minirhizotrons, and a rhizotron, in upland and peatland soils. We provide guidelines for correct image capture, a method that automatically stitches together numerous minirhizotron images into one seamless image, and image analysis using image segmentation and classification in SPRING or change analysis in ArcMap. These methods facilitate spatial and temporal root and soil interaction studies, providing a framework to expand a more comprehensive understanding of belowground dynamics.
Resumo:
Obesity is becoming an epidemic phenomenon in most developed countries. The fundamental cause of obesity and overweight is an energy imbalance between calories consumed and calories expended. It is essential to monitor everyday food intake for obesity prevention and management. Existing dietary assessment methods usually require manually recording and recall of food types and portions. Accuracy of the results largely relies on many uncertain factors such as user's memory, food knowledge, and portion estimations. As a result, the accuracy is often compromised. Accurate and convenient dietary assessment methods are still blank and needed in both population and research societies. In this thesis, an automatic food intake assessment method using cameras, inertial measurement units (IMUs) on smart phones was developed to help people foster a healthy life style. With this method, users use their smart phones before and after a meal to capture images or videos around the meal. The smart phone will recognize food items and calculate the volume of the food consumed and provide the results to users. The technical objective is to explore the feasibility of image based food recognition and image based volume estimation. This thesis comprises five publications that address four specific goals of this work: (1) to develop a prototype system with existing methods to review the literature methods, find their drawbacks and explore the feasibility to develop novel methods; (2) based on the prototype system, to investigate new food classification methods to improve the recognition accuracy to a field application level; (3) to design indexing methods for large-scale image database to facilitate the development of new food image recognition and retrieval algorithms; (4) to develop novel convenient and accurate food volume estimation methods using only smart phones with cameras and IMUs. A prototype system was implemented to review existing methods. Image feature detector and descriptor were developed and a nearest neighbor classifier were implemented to classify food items. A reedit card marker method was introduced for metric scale 3D reconstruction and volume calculation. To increase recognition accuracy, novel multi-view food recognition algorithms were developed to recognize regular shape food items. To further increase the accuracy and make the algorithm applicable to arbitrary food items, new food features, new classifiers were designed. The efficiency of the algorithm was increased by means of developing novel image indexing method in large-scale image database. Finally, the volume calculation was enhanced through reducing the marker and introducing IMUs. Sensor fusion technique to combine measurements from cameras and IMUs were explored to infer the metric scale of the 3D model as well as reduce noises from these sensors.
Resumo:
All optical systems that operate in or through the atmosphere suffer from turbulence induced image blur. Both military and civilian surveillance, gun-sighting, and target identification systems are interested in terrestrial imaging over very long horizontal paths, but atmospheric turbulence can blur the resulting images beyond usefulness. My dissertation explores the performance of a multi-frame-blind-deconvolution technique applied under anisoplanatic conditions for both Gaussian and Poisson noise model assumptions. The technique is evaluated for use in reconstructing images of scenes corrupted by turbulence in long horizontal-path imaging scenarios and compared to other speckle imaging techniques. Performance is evaluated via the reconstruction of a common object from three sets of simulated turbulence degraded imagery representing low, moderate and severe turbulence conditions. Each set consisted of 1000 simulated, turbulence degraded images. The MSE performance of the estimator is evaluated as a function of the number of images, and the number of Zernike polynomial terms used to characterize the point spread function. I will compare the mean-square-error (MSE) performance of speckle imaging methods and a maximum-likelihood, multi-frame blind deconvolution (MFBD) method applied to long-path horizontal imaging scenarios. Both methods are used to reconstruct a scene from simulated imagery featuring anisoplanatic turbulence induced aberrations. This comparison is performed over three sets of 1000 simulated images each for low, moderate and severe turbulence-induced image degradation. The comparison shows that speckle-imaging techniques reduce the MSE 46 percent, 42 percent and 47 percent on average for low, moderate, and severe cases, respectively using 15 input frames under daytime conditions and moderate frame rates. Similarly, the MFBD method provides, 40 percent, 29 percent, and 36 percent improvements in MSE on average under the same conditions. The comparison is repeated under low light conditions (less than 100 photons per pixel) where improvements of 39 percent, 29 percent and 27 percent are available using speckle imaging methods and 25 input frames and 38 percent, 34 percent and 33 percent respectively for the MFBD method and 150 input frames. The MFBD estimator is applied to three sets of field data and the results presented. Finally, a combined Bispectrum-MFBD Hybrid estimator is proposed and investigated. This technique consistently provides a lower MSE and smaller variance in the estimate under all three simulated turbulence conditions.
Resumo:
In this paper we compare the performance of two image classification paradigms (object- and pixel-based) for creating a land cover map of Asmara, the capital of Eritrea and its surrounding areas using a Landsat ETM+ imagery acquired in January 2000. The image classification methods used were maximum likelihood for the pixel-based approach and Bhattacharyya distance for the object-oriented approach available in, respectively, ArcGIS and SPRING software packages. Advantages and limitations of both approaches are presented and discussed. Classifications outputs were assessed using overall accuracy and Kappa indices. Pixel- and object-based classification methods result in an overall accuracy of 78% and 85%, respectively. The Kappa coefficient for pixel- and object-based approaches was 0.74 and 0.82, respectively. Although pixel-based approach is the most commonly used method, assessment and visual interpretation of the results clearly reveal that the object-oriented approach has advantages for this specific case-study.