THE TWO PHASE GENERALIZED MEAN MODEL BASED ON FUZZY LEVEL SET FOR ROBUST IMAGE SEGMENTATION

Image segmentation is the problem of partitioning an image into different subsets, where each subset may have a different characterization in terms of color, intensity, texture, and/or other features. Segmentation is a fundamental component of image processing, and plays a significant role in computer vision, object recognition, and object tracking. Active Contour Models (ACMs) constitute a powerful energy-based minimization framework for image segmentation, which relies on the concept of contour evolution. Starting from an initial guess, the contour is evolved with the aim of approximating better and better the actual object boundary. Handling complex images in an efficient, effective, and robust way is a real challenge, especially in the presence of intensity inhomogeneity, overlap between the foreground/background intensity distributions, objects characterized by many different intensities, and/or additive noise. In this thesis, to deal with these challenges, we propose a number of image segmentation models relying on variational level set methods and specific kinds of neural networks, to handle complex images in both supervised and unsupervised ways. Experimental results demonstrate the high accuracy of the segmentation results, obtained by the proposed models on various benchmark synthetic and real images compared with state-of-the-art active contour models.

In this paper, we introduce multi-symplectic Lagrangian variational integrators for solving Chan-Vese active contour models in image segmentation. Energy functionals are discretized firstly, and numerical schemes are derived from discrete Euler-Lagrange equations based on discrete variational principle. Lagrangian variational integrators preserve native differential structure-multi-symplecticity, that makes the numerical methods have a satisfied behavior. Experiments are performed on the benchmark images from literature. We further evaluated the methods in a segmentation database containing 1023 images. It shows that the proposed numerical schemes attain relatively faster convergence rates and better segmentation accuracy. Comparisons with the standard explicit Euler method of the original Chan-Vese model and other fast numerical optimization methods show that the proposed methods have better stability, higher accuracy, and are more robust when dealing with a large number of pictures. This study provides an example for further research to improve the performance of other existing image segmentation methods based on active contour models.

Image segmentation and image denoising are two important and fundamental topics in the field of image processing. Geometric active contour model based on level set method can deal with the problem of image segmentation, but it does not consider the problem of image denoising. In this paper, a new diffusion equation model for noisy image segmentation is proposed by incorporating some classical diffusion equation denoising models into the segmental process. An assumption about the connection between the image intensity and level set function is given firstly. Some classical denoising models are employed to describe the evolution of level set function secondly. The final nonlinear diffusion equation model for noisy image segmentation is built thirdly. Then image segmentation and image denoising are combined in a united framework. The segmental results can be presented by level set function. Experimental results show that the new model has the advantage of noise resistance and is superior to traditional segmentation model.

C-V model has the advantage of being able to detect boundaries of objects that are not defined by gradient. However, when detecting these types of edges, the C-V model only considers the average value of each region without local information. As a result, its segmentation result may exist errors, when detecting non-gradient defined boundaries. In order to overcome this problem, we modify the fitting term of classical C-V model with an extra weight. This weight can control the relative height of zero-level contour, so the new method can decrease the segmentation errors. Experiments show that the new model can obtain more accurate results and segment multi-phase images by setting proper weights. Active contour models (1), based on level set method, are one important type of methods in image segmentation. Those methods can handle topological changes automatically, and can get the boundaries of objects with complex edges. At present, there are two categories of active contour methods. One is based on the edge information and the other is based on the region information. Snakes (2), geometric active contours (3), geodesic active contours (GAC) model (4) are edge-based models. These methods get the boundaries of objects from the gradients of images. As these methods depend on the gradient information, when processing images with non-gradient defined edges, they will get wrong boundaries. While M-S model (5) and C-V model (6) are based on global region information. They take piecewise constant patches as the solution of segmentation problems. As a result, it can process the images whose edges are not well defined. Additionally, C-V model can process images fast and segment the objects with inner-boundaries, and its solution is robust to the initialization of the curves. However, C-V model may have problems when detecting blurred and fuzzy edges. The reason is that the C-V model only considers the averages inside and outside the zero-level contours, and the results determined by its energy functional may be not suitable for these edge types. In this paper, we propose an improved C-V model with a generalized fitting term to deal with the above problem. A weight factor w added into the generalized fitting term, controls the height of zero-level sets of the original C-V model. Thus we may obtain accurate segmentation results by

Liver segmentation plays a crucial role mainly in tumor segmentation, 3D volume reconstruction and treatment planning of liver disease. In the present work, a comparative evaluation of two segmentation methods named as active contour and level set is presented. Comparative evaluation of both methods has been done individually by applying on Computed Tomography (CT) abdomen images. Comparative study is done by following steps (i) Preprocessing using morphological functions (ii) Segmentation of liver using active contour/level set algorithms (iii) 3-Dimensional volume reconstruction. Results of applied liver segmentation algorithms are compared with manually performed delineations by radiologist. Volume overlapping of above methods is assessed using Dice similarity coefficient (DSC) which gives mean DSC of 93.52%±.62 and 89.48%±.76 in case of active contour and level set method respectively. Finally it can be demonstrated that active contour is superior to level set in terms of accuracy, processing time and 3D volume reconstruction.

The problem of segmentation of a given image using the active contour technique is considered. An abstract calculus to find appropriate speed functions for active contour models in image segmentation or related problems based on variational principles is presented. The speed method from shape sensitivity analysis is used to derive speed functions which correspond to gradient or Newton-type directions for the underlying optimization problem. The Newton-type speed function is found by solving an elliptic problem on the current active contour in every time step. Numerical experiments comparing the classical gradient method with Newton's method are presented.

Active contours driven by divergence of gradient vector flow

Convolutional neural networks (CNNs), as a typical deep learning technique, have been widely used in image segmentation, but they often require a large amount of annotated data. However, the number of available pixel-wise labeled medical images is extremely small, and this prevents the application of CNNs in many medical image segmentation tasks. We proposed a self-paced learning with diversity SPLD) framework to boost the performances of medical image segmentation models with a limited amount of annotated data. Self-paced learning (SPL) is a learning regime that selects training samples in order from the easiest to the most difficult for model training. In addition, we took the diversity of the data into consideration. The proposed self-paced learning with diversity by query-by-committee (SPLD-QBC) algorithm dynamically and diversely selects the appropriate training data to boost the performance of an image segmentation model. SPLD-QBC incorporates the query-by-committee (QBC) technique for data selection and affinity propagation for optimizing the data diversity. By dynamically selecting the optimal sequence of training samples from different probability distributions, the segmentation models achieved improved performances. To verify the effectiveness of the proposed SPLD-QBC framework, we conducted experiments on three medical image segmentation tasks with five different datasets. The experimental results indicated that the proposed SPLD-QBC algorithm significantly improved upon the segmentation performances of the baseline models and resulted in a higher Dice score, surface distance and mean intersection over union (mIoU). The proposed SPLD significantly boosts the segmentation performances of models and is easily embedded into CNN-based image segmentation models.

In this paper, we propose a full-automatic algorithm for extracting elongated object from CT image. Given an input image, we use the SWT(Stroke Width Transform) and MM(Mathematical Morphology) to locate the coarse location of target. Thus leading to over-segmentation. In order to refine the segmentation result, Levelset method is applied to make the contour fit the object. Experimental results show that the proposed algorithm gives precise contour in elongated object segmentation.

Many current and state-of-the-art deep learning models for accurate image segmentation are based on the U-Net architecture, a convolutional neural network designed for biomedical applications. Despite its widespread adoption in the medical imaging community, U-Net has two major limitations. First, due to its deep structure and the large number of filters used, the number of parameters and Floating-Point Operations Per Second (FLOPS) are high. This results in high computational complexity and demands a large memory size, making real-time implementation and deployment of U-Net models challenging. Second, the base U-Net model only uses a single type of kernel (i.e., 3×3) throughout the network for all convolution operations. Feature extraction using a single spatial extent throughout the network is suitable if the size, location, and shape of the salient regions remain static in all the images of a dataset, which is not necessarily the case in medical imaging. To address these two limitations, we propose an Efficient Multi-Encoder-Decoder based UNet (EMED-UNet), a novel architecture for efficient medical image segmentation. We evaluated our network on four medical imaging datasets: Montgomery County, Shenzhen CXR, COVID-19 CT LS, and BraTS (Brain Tumor Segmentation) dataset. EMED-UNet outperforms the U-Net and its variants in terms of accuracy, with around 77% reduction in parameters, a 60% reduction in FLOPS, and a 79.2% reduction in memory usage (all as compared to U-Net). The results demonstrate that EMED-UNet is a lightweight and accurate model for image segmentation that substantially improves upon the U-Net base model and is more feasible to deploy, given its decreased computational cost.

Image segmentation and selective smoothing based on p-harmonic Mumford–Shah functional

HomeRadiology: Imaging CancerVol. 2, No. 2 Previous Research HighlightsFree AccessA New Approach for Automated Image Segmentation of Organs at Risk in Cervical CancerMeredith Jones, Lacey R. McNallyMeredith Jones, Lacey R. McNallyMeredith JonesLacey R. McNallyPublished Online:Mar 27 2020https://doi.org/10.1148/rycan.2020204010MoreSectionsPDF ToolsImage ViewerAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookTwitterLinked InEmail Take-Away Points■ Major Focus: Development of an automated multiclass image segmentation model to identify organs at risk (OARs) on CT scans in patients with locally advanced cervical cancer, prior to radiation therapy.■ Key Results: The convolutional neural network model outperformed model-based, intensity-based, and atlas-based segmentation algorithms, with comparable results to other deep learning segmentation models while also decreasing the time needed for image segmentation by several thousand-fold.■ Impact: Reduction of intra- and interuser variability imposed by manual OAR delineation can lead to more accurate and efficient radiation therapy planning.The recent article by Liu et al developed an automated multiclass image segmentation model to identify organs at risk (OARs) on CT scans. To plan effective and safe radiation therapy in the context of cervical cancer, a CT scan is often acquired prior to the first treatment. Currently, a radiation oncologist will segment the CT images by hand, which is a time-consuming process, subject to intra- and interobserver variability, to identify OARs. To overcome these potential limitations and biases, automated image segmentation techniques can be utilized to improve accuracy and speed of annotating each image. A major problem in creation of deep learning image segmentation models for medical images is the lack of available datasets for model training and validation. Liu et al developed a two-dimensional image segmentation model based off the established convolutional neural network architecture, U-Net. U-Net was utilized because it is feasible to train from scratch with a small training set.This study looked at the CT scans of 105 patients with locally advanced cervical cancer. OAR segmentation for cervical cancer is a particularly challenging problem due to variability in organ size and frequent unclear boundaries. Even an experienced radiologist will have trouble. Seven organs were identified as OARs for cervical cancer radiation therapy: bladder, bone marrow, femoral head left, femoral head right, rectum, small intestine, and spinal cord.The model uses context aggregation blocks where U-Net has convolution layers. These context aggregation blocks use dilation convolution layers with different dilated rates and normal convolution layers with different kernel sizes to yield a low false-positive rate and accurate feature extraction in a large receptive field. A squeeze-extract block was used to ensure proper consideration of organs that are small. A class-weighted cross-entropy loss function was also used to overcome the imbalance in the datasets created by the differences in size and shape of each OAR.A ground truth was available based on the radiation oncologist’s annotations, allowing a Dice similarity coefficient (DSC) and 95th Hausdorff distance (HD) to be calculated and used as an evaluation metric. The DSC and the HD metrics indicated a comparable performance to other deep learning image segmentation models in most of the organs analyzed; inferior results were seen in the rectum and superior results in the intestines. All results were analyzed by an oncologist who determined that greater than 90% of results produced by this model were highly acceptable to be used during radiation therapy planning. To make the model more robust and generalizable, it is necessary to acquire a larger dataset with scans from different sources. Translation of this model to three dimensional may ultimately improve clinical translation.Highlighted ArticleLiu Z, Liu X, Xiao B, et al. Segmentation of organs-at-risk in cervical cancer CT images with a convolutional neural network. Physica Medica 2020;69:184-191. doi: https://doi.org/10.1016/j.ejmp.2019.12.008Highlighted ArticleLiu Z, Liu X, Xiao B, et al. Segmentation of organs-at-risk in cervical cancer CT images with a convolutional neural network. Physica Medica 2020;69:184-191. doi: https://doi.org/10.1016/j.ejmp.2019.12.008 Crossref, Medline, Google ScholarArticle HistoryPublished online: Mar 27 2020 FiguresReferencesRelatedDetailsCited ByJournal of Biomimetics, Biomaterials and Biomedical Engineering, Vol. 49Mathematical Problems in Engineering, Vol. 2020Recommended Articles nnU-Net: Further Automating Biomedical Image AutosegmentationRadiology: Imaging Cancer2021Volume: 3Issue: 1Deep Learning: A Primer for RadiologistsRadioGraphics2017Volume: 37Issue: 7pp. 2113-2131Generative Adversarial Networks: A Primer for RadiologistsRadioGraphics2021Volume: 41Issue: 3pp. 840-857Current Applications and Future Impact of Machine Learning in RadiologyRadiology2018Volume: 288Issue: 2pp. 318-328Deep Generative Adversarial Networks: Applications in Musculoskeletal ImagingRadiology: Artificial Intelligence2021Volume: 3Issue: 3See More RSNA Education Exhibits A Multidisciplinary Approach for Program Development with Artificial Intelligence in Pancreatic Cancer: How We Fit InDigital Posters2019Abnormal Changes After Radiation Therapy: What Radiologists Should KnowDigital Posters2018Artificial Intelligence in Diagnostic Imaging: Current Applications and Future PerspectiveDigital Posters2019 RSNA Case Collection Acute Radiation EnteropathyRSNA Case Collection2021Small Bowel LymphomaRSNA Case Collection2021Hirschsprung DiseaseRSNA Case Collection2021 Vol. 2, No. 2 Metrics Downloaded 310 times Altmetric Score

PET-guided radiation therapy treatment planning, clinical diagnosis, assessment of tumor growth, and therapy response rely on the accurate delineation of the tumor volume and quantification of tracer uptake. Most PET image segmentation techniques proposed thus far are suboptimal in the presence of heterogeneity of tracer uptake within the lesion. This work presents an active contour model approach based on the method of Chan and Vese ["Active contours without edges," IEEE Trans. Image Process. 10, 266-277 (2001)] designed to take into account the high level of statistical uncertainty (noise) and to handle the heterogeneity of tumor uptake typically present in PET images. In the proposed method, the fitting terms in the Chan-Vese formulation are modified by introducing new input images, including the smoothed version of the original image using anisotropic diffusion filtering (ADF) and the contourlet transform of the image. The advantage of utilizing ADF for image smoothing is that it avoids blurring the object's edges and preserves the average activity within a region, which is important for accurate PET quantification. Moreover, incorporating the contourlet transform of the image into the fitting terms makes the energy functional more effective in directing the evolving curve toward the object boundaries due to the enhancement of the tumor-to-background ratio (TBR). The proper choice of the energy functional parameters has been formulated by making a clear consensus based on tumor heterogeneity and TBR levels. This cautious parameter selection leads to proper handling of heterogeneous lesions. The algorithm was evaluated using simulated phantom and clinical studies, where the ground truth and histology, respectively, were available for accurate quantitative analysis of the segmentation results. The proposed technique was also compared to a number of previously reported image segmentation techniques. The results were quantitatively analyzed using three evaluation metrics, including the spatial overlap index (SOI), the mean relative error (MRE), and the mean classification error (MCE). Although the performance of the proposed method was analogous to other methods for some datasets, overall the proposed algorithm outperforms all other techniques. In the largest clinical group comprising nine datasets, the proposed approach improved the SOI from 0.41±0.14 obtained using the best-performing algorithm to 0.54±0.12 and reduced the MRE from 54.23±103.29 to 0.19±16.63 and the MCE from 112.86±69.07 to 60.58±18.43. The proposed segmentation technique is superior to other representative segmentation techniques in terms of highest overlap between the segmented volume and the ground truth∕histology and minimum relative and classification errors. Therefore, the proposed active contour model can result in more accurate tumor volume delineation from PET images.

Today's technological advances in medical imaging have given rise to efficient diagnostic procedures. Segmentation identifies and defines individual objects with various attributes such as size, shape, texture, spatial location, contrast, brightness, noise, and context. Deformable segmentation methods are Active contours, which are used to match and track images of an atomic structure by determining constraints derived from the image data. Level set method is an integral part of active contour family, considerable work towards level set methods has identified two main disadvantages i.e., initialization of controlling parameters and time complexity. In this paper, the methodology employed proposes an enhanced Variational level set methodology for Magnetic Resonance (MR) brain image segmentation with heterogeneous intensity. Core concept of IFCM is based on Intuitionistic fuzzy set. Both the values of membership and non membership values for the purpose of labelling are utilized together. As the result of experimentation reveals the efficiency of the recommended IFCM algorithm and Lattice Boltzmann Method (LBM) to overcome the drawbacks of Level Set methods by using the energy function to reduce the processing time which addresses the time complexity issue. The proposed system combines of both IFCM and LBM to form a novel approach. The system is tested on a large set of MRI brain images, extensive research and experiments were carried over on the standard dataset and the results are found to be improved in identification of tumor size detection with respect to time complexity.

Image segmentation is a fundamental task in image analysis which is responsible for partitioning an image into multiple sub-regions based on a desired feature. Active contours have been widely used as attractive image segmentation methods because they always produce sub-regions with continuous boundaries, while the kernel-based edge detection methods, e.g. Sobel edge detectors, often produce discontinuous boundaries. The use of level set theory has provided more flexibility and convenience in the implementation of active contours. However, traditional edge-based active contour models have been applicable to only relatively simple images whose sub-regions are uniform without internal edges. Here in this paper we attempt to brief the taxonomy and current state of the art in Image segmentation and usage of Active Contours. The goal of medical image segmentation is to partition a medical image in to separate regions, usually anatomic structures that are meaningful for a specific task. In many medical applications, such as diagnosis, surgery planning, and radiation treatment planning determining of the volume and position of an anatomic structure is required and plays a critical role in the treatment outcome.