Fast and accurate edge-based segmentation with no contour smoothing in 2-D real images

Instant Segmentation and Fitting of Excavations in Subsurface Utility Engineering

Using augmented reality for subsurface utility engineering (SUE) has benefited from recent advances in sensing hardware, enabling the first practical and commercial applications. However, this progress has uncovered a latent problem - the insufficient quality of existing SUE data in terms of completeness and accuracy. In this work, we present a novel approach to automate the process of aligning existing SUE databases with measurements taken during excavation works, with the potential to correct the deviation from the as-planned to as-built documentation, which is still a big challenge for traditional workers at sight. Our segmentation algorithm performs infrastructure segmentation based on the live capture of an excavation on site. Our fitting approach correlates the inferred position and orientation with the existing digital plan and registers the as-planned model into the as-built state. Our approach is the first to circumvent tedious postprocessing, as it corrects data online and on-site. In our experiments, we show the results of our proposed method on both synthetic data and a set of real excavations.

Femoral image segmentation based on two-stage convolutional network using 3D-DMFNet and 3D-ResUnet

OBJECTIVE

The femur is a typical human long bone with an irregular spatial structure. Femoral fractures are the most common occurrence in middle-aged and older adults. The structure of human bone tissue is very complex, and there are significant differences between individuals. Segmenting bone tissue is a challenging task and of great practical significance.

METHODS

Our research is based on segmenting and the three-dimensional reconstruction of femoral images using X-ray imaging. The currently commonly used two-dimensional fully convolutional network Unet has the problem of ignoring spatial position information and losing too much feature information. The commonly used three-dimensional fully convolutional network 3D Unet has the problem of ignoring spatial position information and losing too much feature information. For the problem of many model parameters, we proposes a two-stage network segmentation model composed of 3D-DMFNet and 3D-ResUnet networks and trains the network in stages to segment the femur. One stage is used to detect the coarse segmentation of the femur range, and one stage is used for the fine segmentation of the femur so that the training speed is fast and the segmentation accuracy is moderate, which is suitable for detecting the femur range.

RESULTS

The experimental dataset used in this paper is from The Second Affiliated Hospital of Fujian Medical University, which consists of 30 sets of femur X-ray images. The experiment compares the accuracy and loss value of Unet and the two-stage convolutional network. The image shows that the two-stage convolutional network has higher accuracy. At the same time, this paper shows the effect of the two-stage coarse segmentation and fine segmentation of medical images. Subsequently, this paper applies the model to practice and obtains the model's Dice, Sensitivity, Specificity and Pixel Accuracy values. After comparative analysis, the experimental results show that the two-stage network segmentation model composed of 3D-DMFNet and 3D-ResUnet network designed in this paper has higher accuracy, intuitiveness, and more application value than traditional image segmentation algorithms.

CONCLUSION

With the continuous application of X-ray images in clinical diagnosis using femoral images, the method in this paper is expected to become a diagnostic tool that can effectively improve the accuracy and loss of femoral image segmentation and the three-dimensional reconstruction.

Graphical Image Region Extraction with K-Means Clustering and Watershed

With a wide range of applications, image segmentation is a complex and difficult preprocessing step that plays an important role in automatic visual systems, which accuracy impacts, not only on segmentation results, but directly affects the effectiveness of the follow-up tasks. Despite the many advances achieved in the last decades, image segmentation remains a challenging problem, particularly, the segmenting of color images due to the diverse inhomogeneities of color, textures and shapes present in the descriptive features of the images. In trademark graphic images segmentation, beyond these difficulties, we must also take into account the high noise and low resolution, which are often present. Trademark graphic images can also be very heterogeneous with regard to the elements that make them up, which can be overlapping and with varying lighting conditions. Due to the immense variation encountered in corporate logos and trademark graphic images, it is often difficult to select a single method for extracting relevant image regions in a way that produces satisfactory results. Many of the hybrid approaches that integrate the Watershed and K-Means algorithms involve processing very high quality and visually similar images, such as medical images, meaning that either approach can be tweaked to work on images that follow a certain pattern. Trademark images are totally different from each other and are usually fully colored. Our system solves this difficulty given it is a generalized implementation designed to work in most scenarios, through the use of customizable parameters and completely unbiased for an image type. In this paper, we propose a hybrid approach to Image Region Extraction that focuses on automated region proposal and segmentation techniques. In particular, we analyze popular techniques such as K-Means Clustering and Watershedding and their effectiveness when deployed in a hybrid environment to be applied to a highly variable dataset. The proposed system consists of a multi-stage algorithm that takes as input an RGB image and produces multiple outputs, corresponding to the extracted regions. After preprocessing steps, a K-Means function with random initial centroids and a user-defined value for k is executed over the RGB image, generating a gray-scale segmented image, to which a threshold method is applied to generate a binary mask, containing the necessary information to generate a distance map. Then, the Watershed function is performed over the distance map, using the markers defined by the Connected Component Analysis function that labels regions on 8-way pixel connectivity, ensuring that all regions are correctly found. Finally, individual objects are labelled for extraction through a contour method, based on border following. The achieved results show adequate region extraction capabilities when processing graphical images from different datasets, where the system correctly distinguishes the most relevant visual elements of images with minimal tweaking.

A Novel Framework with Weighted Decision Map Based on Convolutional Neural Network for Cardiac MR Segmentation

For diagnosing cardiovascular disease, an accurate segmentation method is needed. There are several unre-solved issues in the complex field of cardiac magnetic resonance imaging, some of which have been partially addressed by using deep neural networks. To solve two problems of over-segmentation and under-segmentation of anatomical shapes in the short-axis view from different cardiac magnetic resonance sequences, we propose a novel two-stage framework with a weighted decision map based on convolutional neural networks to segment the myocardium (Myo), left ventricle (LV), and right ventricle (RV) simultaneously. The framework comprises a deci-sion map extractor and a cardiac segmenter. A cascaded U-Net++ is used as a decision map extractor to acquire the decision map that decides the category of each pixel. Cardiac segmenter is a multiscale dual-path feature ag-gregation network (MDFA-Net) which consists of a densely connected network and an asymmetric encoding and decoding network. The input to the cardiac seg-menter is derived from processed original images weighted by the output of the decision map extractor. We conducted experiments on two datasets of mul-ti-sequence cardiac magnetic resonance segmentation challenge 2019 (MS-CMRSeg 2019) and myocardial pa-thology segmentation challenge 2020 (MyoPS 2020). Test results obtained on MyoPS 2020 show that proposed method with average Dice coefficient of 84.70%, 86.00% and 86.31% in the segmentation task of Myo, LV, and RV, respectively.

A curvature-based approach for left ventricular shape analysis from cardiac magnetic resonance imaging

It is believed that left ventricular (LV) regional shape is indicative of LV regional function, and cardiac pathologies are often associated with regional alterations in ventricular shape. In this article, we present a set of procedures for evaluating regional LV surface shape from anatomically accurate models reconstructed from cardiac magnetic resonance (MR) images. LV surface curvatures are computed using local surface fitting method, which enables us to assess regional LV shape and its variation. Comparisons are made between normal and diseased hearts. It is illustrated that LV surface curvatures at different regions of the normal heart are higher than those of the diseased heart. Also, the normal heart experiences a larger change in regional curvedness during contraction than the diseased heart. It is believed that with a wide range of dataset being evaluated, this approach will provide a new and efficient way of quantifying LV regional function.

An efficient parameterless quadrilateral-based image segmentation method

This paper proposes a general quadrilateral-based framework for image segmentation, in which quadrilaterals are first constructed from an edge map, where neighboring quadrilaterals with similar features of interest are then merged together to form regions. Under the proposed framework, the quadrilaterals enable the elimination of local variations and unnecessary details for merging from which each segmented region is accurately and completely described by a set of quadrilaterals. To illustrate the effectiveness of the proposed framework, we derived an efficient and high-performance parameterless quadrilateral-based segmentation algorithm from the framework. The proposed algorithm shows that the regions obtained under the framework are segmented into multiple levels of quadrilaterals that accurately represent the regions without severely over or undersegmenting them. When evaluated objectively and subjectively, the proposed algorithm performs better than three other segmentation techniques, namely, seeded region growing, K-means clustering and constrained gravitational clustering, and offers an efficient description of the segmented objects conducive to content-based applications.

Vascular tree object segmentation by deskeletonization of valley courses

In this paper, we propose a valley-course-based image segmentation technique for tree-like object delineation, as an alternative to the traditional centerline-based methods. This technique consists of valley-course extraction, skeleton pruning and deskeletonization. Valley courses, constructed from valley points that are obtained by star-pattern scanning over an image, offer a natural manner of identifying tree skeletons. Unattached segments are removed using morphological operations. A structured tree is then constructed from the skeletons by using a tree pruning/spanning algorithm. A fleshy tree-like object is obtained by a deskeletonization procedure, which consists of extracting tree boundary in vicinity of the skeletons in the original image. The tree boundary is determined by identifying paired edge points at a valley point. A derivative-free edge identification approach is proposed, which defines an edge point at a side-slope by a relative intensity drop with respect to the local background. An empirical formula using a logarithmic function of local intensity contrast offers desirable characteristics of adaptability and stability. The adaptability of edge points to the local background is attributed to the compression behavior of logarithmic function. Furthermore, stability to noise is resulted because derivative operations are not used. The segmentation technique was validated using coronary angiographic images.