Application of an edge detection algorithm for surface determination in industrial X-ray computed tomography

Surface determination is an essential step of the measurement process in industrial X-ray computed tomography (XCT). The starting point of the surface determination process step is a single grey value threshold within a voxel volume in conventional surface determination methods. However, this value is not always found in the reconstructed volume in the local environment of the surface of the measurement object due to various artefacts, so that none or incorrect surfaces are determined. In order to find surfaces independently of a single grey value, a three-dimensional approach of the initial contour determination based on a Prewitt edge detection algorithm is presented in this work. This method is applied to different test specimens and specimen compositions which, due to their material or material constellation, their geometric properties with regard to surfaces and interfaces as well as their calibrated size and length dimensions, embody relevant properties in the examination of joining connections. It is shown that by using the surface determination method in the measurement process, both a higher metrological structure resolution and interface structure resolution can be achieved. Surface artefacts can be reduced by the application and it is also an approach to improved surface finding for the multi-material components that are challenging for XCT.

Road Detection Based on Edge Feature with GAC Model in Aerial Image

Road detection from aerial images still is a challenging task since it is heavily influenced by spectral reflectance, shadows and occlusions. In order to increase the road detection accuracy, a proposed method for road detection by GAC model with edge feature extraction and segmentation is studied in this paper. First, edge feature can be extracted using the proposed gradient magnitude with Canny operator. Then, a reconstructed gradient map is applied in watershed transformation method, which is segmented for the next initial contour. Last, with the combination of edge feature and initial contour, the boundary stopping function is applied in the GAC model. The road boundary result can be accomplished finally. Experimental results show, by comparing with other methods in [Formula: see text]-measure system, that the proposed method can achieve satisfying results.

Edge Enhancement Based Active Contour Model for Segmentation of Brain Tumor in MRI Images

Tumor segmentation is one of the most significant tasks in brain image analysis due to the significant information obtained by the tumor region. Therefore, many methods have been proposed during the last two decades for segmenting the tumor in MRI images. In this paper, an automated method is proposed using an active contour model with an initial contour creation using edge sharpening, thresholding, and morphological operations. Four methods of edge detection are utilized in the edge sharpening process (Sobel, Roberts, Prewitt, and Canny) and their performance was investigated in terms of Dice, Jaccard, and F1 score. The experiments were implemented on BRATS datasets with both HGG and LGG images. The study indicates that sharpening the edges using edge detection is essential to improve the segmentation of the tumor region especially when it is used with an active contour model. The achieved results show the effectiveness of the proposed method and it outperformed some recent existing methods.

P14.85 Impact of the neuro-radiologist and neuro-surgeon in contouring with the neuro-oncologist on local relapse rates for brain metastases treated with stereotactic radiosurgery

BACKGROUND The audit evaluates the value of MDT, including neuro-radiologist and neuro-surgeon, review of contouring carried out by a clinical oncologist in stereotactic radiosurgery (SRS). MATERIAL AND METHODS A sequential audit was conducted of all patients receiving intracranial SRS at our local institution for the first 22 months of a new SRS service. Lesions were contoured first by clinical oncologist then reviewed/edited by the MDT. The initial contour was compared with final contour using Jaccard conformity and geographical miss indices. The dosimetric impact of a contouring change was assessed using plan metrics to both original and final contour. The impact of the contouring review on local relapse, overall survival and radio necrosis rate was evaluated with at least 24 months follow up (24–46 months). RESULTS 113 patients and 142 lesions treated over 22 months were identified. Mean JCI was 0.92 (0.32–1.00) and 38% needed significant editing (JCI<0.95). Mean GMI was 0.03 (0.0–0.65) and 17% showed significant miss (GMI>0.05). Resection cavities showed more changes, with lower JCI and higher GMI (p<0.05). There was no significant improvement on JCI or GMI shown over time. Dosimetric analysis indicated a strong association of conformity metrics with PTV dose metrics; a 0.1 change in GTV conformity metric association with 6–17% change in dose to 95% of resulting PTV. Greater association was seen in resection cavity suggesting the geographical nature of a typical contouring error gives rise to greater potential change in dose. Clinical outcomes compared well with published series. Median survival was 20 months and local relapse free rate in the treated areas of 0.89 (0.8–0.94) at 40 months, and 0.9 (0.83–0.95) radio-necrosis free rate at 40 months with a median 17 months to developing radio-necrosis for those that did. CONCLUSION This work highlights that a MDT contour review adds significant value to SRS and the approach translates into reduced local recurrence rates at our local institution compared with previously published data. Radio-necrosis rates are below 10%. No improvement in clinical oncologist contouring over time was shown indicating a collaborative approach is needed regardless of experience of clinical oncologist. MDT input is recommended in particular in contouring of resection cavities.

Automatic Recognition Method of Letter Images in English Self-Learning Based on Partial Differential Equation Method

According to the current situation of knowledge popularization, students simply rely on the knowledge learned in the classroom that is far from adapting to the development of modern society; so, every student needs to have the consciousness and ability of independent learning. The research of the English self-help learning system based on partial differential equation method comes into being with information network technology as the foundation for survival and development. The existing partial differential equation recognition models based on average curvature motion are all edge-based and need to use the external force defined by the image gradient to attract the zero level set (evolution curve) to move to the target edge and finally stay on the target edge. Therefore, it is difficult to obtain ideal results when extracting fuzzy or discrete boundaries (perceptual boundaries), and it is very sensitive to the selection of initial contour and noise. To solve this problem, this paper proposes a new recognition model of partial differential equations based on mean curvature motion. This overcomes some defects of existing edge models because it is region-based and does not require image gradient as a condition to stop evolution. The proposed model can avoid manual initial curve selection and allow stopping conditions to be set in the algorithm. In addition, in the numerical solution of partial differential equations, the existing model uses upwind difference scheme, and the semi-implicit additive operator separation method is adopted in this paper. Some other layers are added, and some hyperparameters are adjusted when the convolutional neural networks of inception PDEs are constructed by stacking the structure of inception PDEs. In the contrast experiment with the prototype, the software and hardware environment are the same, and the input is exactly the same. For the handwritten English alphabet data set, the variant structure can obtain more than 90% of the training accuracy and verification accuracy, which is better than the experimental accuracy of the prototype. In addition, because the inception PDE structure contains fewer parameters than the prototype, it is more computationally efficient and takes less training time per batch than the prototype.

On Combining DeepSnake and Global Saliency for Detection of Orchard Apples

For the fast detection and recognition of apple fruit targets, based on the real-time DeepSnake deep learning instance segmentation model, this paper provided an algorithm basis for the practical application and promotion of apple picking robots. Since the initial detection results have an important impact on the subsequent edge prediction, this paper proposed an automatic detection method for apple fruit targets in natural environments based on saliency detection and traditional color difference methods. Combined with the original image, the histogram backprojection algorithm was used to further optimize the salient image results. A dynamic adaptive overlapping target separation algorithm was proposed to locate the single target fruit and further to determine the initial contour for DeepSnake, in view of the possible overlapping fruit regions in the saliency map. Finally, the target fruit was labeled based on the segmentation results of the examples. In the experiment, 300 training datasets were used to train the DeepSnake model, and the self-built dataset containing 1036 pictures of apples in various situations under natural environment was tested. The detection accuracy of target fruits under non-overlapping shaded fruits, overlapping fruits, shaded branches and leaves, and poor illumination conditions were 99.12%, 94.78%, 90.71%, and 94.46% respectively. The comprehensive detection accuracy was 95.66%, and the average processing time was 0.42 s in 1036 test images, which showed that the proposed algorithm can effectively separate the overlapping fruits through a not-very-large training samples and realize the rapid and accurate detection of apple targets.

Active Contour driven by geometric mean and standard deviation-based energy fitting model for the left ventricle segmentation from cardiac magnetic resonance images

This paper proposes a geometric mean and standard deviation-based energy fitting model to improve the accuracy of segmentation of the left ventricle from cardiac Magnetic Resonance Imaging (MRI). Energy-fitting-based active contour models emerged so far suffer either from intensity inhomogeneity or gives wrong segmentation result due to an inappropriate initial contour. Thus, accurate and robust segmentation of the left ventricle from cardiac MRI still a challenging problem. Therefore, to tackle both the problems, a geometric mean-based energy-fitting model is proposed. Unlike the recent energy-fitting-based models which use the arithmetic mean to calculate the local energy, the proposed method uses geometric mean and scaled standard deviation to compute the energy functional which drives the active contour to the region of interest. In addition to that completely removes the initial contour problem by automating it according to the input. The initial contour in the proposed model is a circle its radius and the center are calculated from the input sample itself. This initial contour is an appropriate and automated one that helps to reduce the computation time for segmentation. Experiments are conducted on cardiac MRI images the result obtained is compared with ground truth and evaluated by Average perpendicular distance (APD) and DICE similarity coefficient. Further the visual, as well as evaluated parameters, evidences that the proposed model performs better than the existing methods.

Object-Oriented Building Contour Optimization Methodology for Image Classification Results via Generalized Gradient Vector Flow Snake Model

Building boundary optimization is an essential post-process step for building extraction (by image classification). However, current boundary optimization methods through smoothing or line fitting principles are unable to optimize complex buildings. In response to this limitation, this paper proposes an object-oriented building contour optimization method via an improved generalized gradient vector flow (GGVF) snake model and based on the initial building contour results obtained by a classification method. First, to reduce interference from the adjacent non-building object, each building object is clipped via their extended minimum bounding rectangles (MBR). Second, an adaptive threshold Canny edge detection is applied to each building image to detect the edges, and the progressive probabilistic Hough transform (PPHT) is applied to the edge result to extract the line segments. For those cases with missing or wrong line segments in some edges, a hierarchical line segments reconstruction method is designed to obtain complete contour constraint segments. Third, accurate contour constraint segments for the GGVF snake model are designed to quickly find the target contour. With the help of the initial contour and constraint edge map for GGVF, a GGVF force field computation is executed, and the related optimization principle can be applied to complex buildings. Experimental results validate the robustness and effectiveness of the proposed method, whose contour optimization has higher accuracy and comprehensive value compared with that of the reference methods. This method can be used for effective post-processing to strengthen the accuracy of building extraction results.

A hybrid level set model for image segmentation

Active contour models driven by local binary fitting energy can segment images with inhomogeneous intensity, while being prone to falling into a local minima. However, the segmentation result largely depends on the location of the initial contour. We propose an active contour model with global and local image information. The local information of the model is obtained by bilateral filters, which can also enhance the edge information while smoothing the image. The local fitting centers are calculated before the contour evolution, which can alleviate the iterative process and achieve fast image segmentation. The global information of the model is obtained by simplifying the C-V model, which can assist contour evolution, thereby increasing accuracy. Experimental results show that our algorithm is insensitive to the initial contour position, and has higher precision and speed.

An Improved Image Segmentation Algorithm CT Superpixel Grid Using Active Contour

The traditional CT image segmentation algorithm is easy to ignore image contour initialization, which leads to the problem of long time consuming and low accuracy. A superpixel mesh CT image improved segmentation algorithm using active contour was proposed. CT image superpixel gridding was carried out first; secondly, on the basis of gridding, the region growth criterion was improved by superpixel processing, the region growth graph was established, the image edge salient graph was calculated based on the growth graph, and the target edge was obtained as the initial contour; finally, the Mumford-Shah model in the active contour model was improved; the energy functional was constructed based on the improved model and transformed into the symbol distance function. The results show that the proposed algorithm takes less time to mesh superpixels, the accuracy of image edge calculation is high, the correct classification coefficient is as high as 0.9, and the accuracy of CT image segmentation is always higher than 90%, which has superiority.