Level Set Approach For Segmentation Research Articles

Design of deep learning reaction–diffusion level set segmentation approach for health care related to automatic kidney stone detection analysis

Design of deep learning reaction–diffusion level set segmentation approach for health care related to automatic kidney stone detection analysis

A Level Set Approach for Segmentation of Intensity Inhomogeneous Image Based on Region Decomposition

Medical images like magnetic resonance angiogram (MRA) images have inhomogeneous intensities. When such images are segmented using active contour models, they do not produce desired results. Hence, segmenting an image with inhomogeneous intensities is a challenge. In this paper, the problem of segmenting medical images with intensity inhomogeneity has been addressed. Here, we propose a method which uses the concept of region decomposition along with combination of region-based segmentation and edge-detector function. In this process, the input image is divided into four quadrants and checked for segmentation. If the segmentation of any sub-image is not as desired, it is further decomposed into four more sub-regions. The process continues until each sub-image is properly segmented. In the end, all the segmented parts are merged to obtain the desired segmented image. The proposed method has been implemented and desired results are obtained by the same and compared with existing results.

Microarray Image Analysis: From Image Processing Methods to Gene Expression Levels Estimation

Microarray image processing leads to the characterization of gene expression levels simultaneously, for all cellular transcripts (mRNAs) in a single experiment. The calculation of expression levels for each microarray spot/gene is a crucial step to extract valuable information. By measuring the mRNA levels for the whole genome, the microarray experiments are capable to study functionality, pathological phenotype, and response of cells to a pharmaceutical treatment. The processing of the extensive number of non-homogeneous data contained in microarray images is still a challenge. We propose a density based spatial clustering procedure driven by a level-set approach for microarray spot segmentation together with a complete set of quality measures used to evaluate the proposed method compared with existing approaches for gene expression levels estimation. The set of quality measures used for evaluation include: regression ratios, intensity ratios, mean absolute error, coefficient of variation and fold change factor. We applied the proposed image processing pipeline to a set of microarray images and compared our results with the ones delivered by Genepix, using the aforementioned quality measures. The advantage of our proposed method is highlighted by a selection of up-regulated genes that had been identified exclusively by our approach. These genes prove to add valuable information regarding the biological mechanism activated as a response of Arabidopsis T to pathogen infection.

Extraction of road features from UAV images using a novel level set segmentation approach

ABSTRACTA novel hybrid technique for road extraction from UAV imagery is presented in this paper. The suggested analysis begins with image segmentation via Trainable Weka Segmentation. This step uses an immense range of image features, such as detectors for edge detection, filters for texture, filters for noise depletion and a membrane finder. Then, a level set method is performed on the segmented images to extract road features. Next, morphological operators are applied on the images for improving extraction precision. Eventually, the road extraction precision is calculated on the basis of manually digitized road layers. Obtained results indicated that the average proportions of completeness, correctness and quality were 93.52%, 85.79% and 81.01%, respectively. Therefore, experimental results validated the superior performance of the proposed hybrid approach in road extraction from UAV images.

A cascaded Mura defect detection method based on mean shift and level set algorithm for active‐matrix OLED display panel

AbstractActive‐matrix OLED (AMOLED), as the next‐generation display technology, is being commercially promoted rapidly. And Mura defects occur unavoidable during different phases of the AMOLED panel production process. In this paper, a cascaded Mura detection method leveraging the mean shift and the level set algorithm is proposed. First, we use the mean shift algorithm to find the general contour of the Mura defects that circumvent the issue in established level set segmentation approach wherein the use of the local image information is sensitive to the initial contour. Then, we improve the level set model that combines global and local information to segment Mura defects accurately. The integration of local image information can levitate the challenges in the global image model, which cannot separate the local intensity inhomogeneity and texture background individually. The experiments show that the cascaded method has a superior capability in terms of both accuracy and efficiency.

A Novel Skin Lesion Detection Approach Using Neutrosophic Clustering and Adaptive Region Growing in Dermoscopy Images

This paper proposes novel skin lesion detection based on neutrosophic clustering and adaptive region growing algorithms applied to dermoscopic images, called NCARG. First, the dermoscopic images are mapped into a neutrosophic set domain using the shearlet transform results for the images. The images are described via three memberships: true, indeterminate, and false memberships. An indeterminate filter is then defined in the neutrosophic set for reducing the indeterminacy of the images. A neutrosophic c-means clustering algorithm is applied to segment the dermoscopic images. With the clustering results, skin lesions are identified precisely using an adaptive region growing method. To evaluate the performance of this algorithm, a public data set (ISIC 2017) is employed to train and test the proposed method. Fifty images are randomly selected for training and 500 images for testing. Several metrics are measured for quantitatively evaluating the performance of NCARG. The results establish that the proposed approach has the ability to detect a lesion with high accuracy, 95.3% average value, compared to the obtained average accuracy, 80.6%, found when employing the neutrosophic similarity score and level set (NSSLS) segmentation approach.

Camera-based photoplethysmography in an intraoperative setting

BackgroundCamera-based photoplethysmography (cbPPG) is a measurement technique which enables remote vital sign monitoring by using cameras. To obtain valid plethysmograms, proper regions of interest (ROIs) have to be selected in the video data. Most automated selection methods rely on specific spatial or temporal features limiting a broader application. In this work, we present a new method which overcomes those drawbacks and, therefore, allows cbPPG to be applied in an intraoperative environment.MethodsWe recorded 41 patients during surgery using an RGB and a near-infrared (NIR) camera. A Bayesian skin classifier was employed to detect suitable regions, and a level set segmentation approach to define and track ROIs based on spatial homogeneity.ResultsThe results show stable and homogeneously illuminated ROIs. We further evaluated their quality with regards to extracted cbPPG signals. The green channel provided the best results where heart rates could be correctly estimated in 95.6% of cases. The NIR channel yielded the highest contribution in compensating false estimations.ConclusionsThe proposed method proved that cbPPG is applicable in intraoperative environments. It can be easily transferred to other settings regardless of which body site is considered.

Multi-Scale Segmentation and Surface Fitting for Measuring 3-D Macular Holes.

Macular holes are blinding conditions, where a hole develops in the central part of retina, resulting in reduced central vision. The prognosis and treatment options are related to a number of variables, including the macular hole size and shape. High-resolution spectral domain optical coherence tomography allows precise imaging of the macular hole geometry in three dimensions, but the measurement of these by human observers is time-consuming and prone to high inter- and intra-observer variability, being characteristically measured in 2-D rather than 3-D. We introduce several novel techniques to automatically retrieve accurate 3-D measurements of the macular hole, including: surface area, base area, base diameter, top area, top diameter, height, and minimum diameter. Specifically, we introduce a multi-scale 3-D level set segmentation approach based on a state-of-the-art level set method, and we introduce novel curvature-based cutting and 3-D measurement procedures. The algorithm is fully automatic, and we validate our extracted measurements both qualitatively and quantitatively, where our results show the method to be robust across a variety of scenarios. Our automated processes are considered a significant contribution for clinical applications.

An Automated Level Set Segmentation Approach for Lesion Detection in Dental Radiograph for Endodontic Treatment

An Automated Level Set Segmentation Approach for Lesion Detection in Dental Radiograph for Endodontic Treatment

Adaptive Estimation of Active Contour Parameters Using Convolutional Neural Networks and Texture Analysis.

In this paper, we propose a generalization of the level set segmentation approach by supplying a novel method for adaptive estimation of active contour parameters. The presented segmentation method is fully automatic once the lesion has been detected. First, the location of the level set contour relative to the lesion is estimated using a convolutional neural network (CNN). The CNN has two convolutional layers for feature extraction, which lead into dense layers for classification. Second, the output CNN probabilities are then used to adaptively calculate the parameters of the active contour functional during the segmentation process. Finally, the adaptive window size surrounding each contour point is re-estimated by an iterative process that considers lesion size and spatial texture. We demonstrate the capabilities of our method on a dataset of 164 MRI and 112 CT images of liver lesions that includes low contrast and heterogeneous lesions as well as noisy images. To illustrate the strength of our method, we evaluated it against state of the art CNN-based and active contour techniques. For all cases, our method, as assessed by Dice similarity coefficients, performed significantly better than currently available methods. An average Dice improvement of 0.27 was found across the entire dataset over all comparisons. We also analyzed two challenging subsets of lesions and obtained a significant Dice improvement of 0.24 with our method (p <;0.001, Wilcoxon).

Single STE-MR Acquisition in MR-Based Attenuation Correction of Brain PET Imaging Employing a Fully Automated and Reproducible Level-Set Segmentation Approach.

The aim of this study is to introduce a fully automatic and reproducible short echo-time (STE) magnetic resonance imaging (MRI) segmentation approach for MR-based attenuation correction of positron emission tomography (PET) data in head region. Single STE-MR imaging was followed by generating attenuation correction maps (μ-maps) through exploiting an automated clustering-based level-set segmentation approach to classify head images into three regions of cortical bone, air, and soft tissue. Quantitative assessment was performed by comparing the STE-derived region classes with the corresponding regions extracted from X-ray computed tomography (CT) images. The proposed segmentation method returned accuracy and specificity values of over 90% for cortical bone, air, and soft tissue regions. The MR- and CT-derived μ-maps were compared by quantitative histogram analysis. The results suggest that the proposed automated segmentation approach can reliably discriminate bony structures from the proximal air and soft tissue in single STE-MR images, which is suitable for generating MR-based μ-maps for attenuation correction of PET data.

Simultaneous extraction of endocardial and epicardial contours of the left ventricle by distance regularized level sets.

Segmentation of the cardiac left ventricle (LV) is still an open problem and is challenging due to the poor contrast between tissues around the epicardium and image artifacts. To extract the endocardium and epicardium of the cardiac left ventricle accurately, the authors propose a two-layer level set approach for segmentation of the LV from cardiac magnetic resonance short-axis images. In the proposed method, the endocardium and epicardium are represented by two specified level contours of a level set function. Segmentation of the LV is formulated as a problem of optimizing the level set function such that these two level contours best fit the epicardium and endocardium, subject to a distance regularization (DR) term to preserve a smoothly varying distance between them. The DR term introduces a desirable interaction between the two level contours of a single level set function, which contributes to preserve the anatomical geometry of the epicardium and endocardium of the LV. In addition, the proposed method has an intrinsic ability to deal with intensity inhomogeneity in MR images, which is a common image artifact in MRI. Their method is quantitatively validated by experiments on the datasets for the MICCAI 2009 grand challenge on left ventricular segmentation and the MICCAI 2013 challenge workshop on segmentation: algorithms, theory and applications (SATA). To overcome discontinuity of 2D segmentation results at some adjacent slices for a few cases, the authors extend distance regularized two-layer level set to 3D to refine the segmentation results. The corresponding metrics for their method are better than the methods in the MICCAI 2009 challenge. Their method was ranked at the first place in terms of Hausdorff distance and the second place in terms of Dice similarity coefficient in the MICCAI 2013 challenge. Experimental results demonstrate the advantages of their method in terms of segmentation accuracy and consistency with the heart anatomy.

A fully automated and reproducible level-set segmentation approach for generation of MR-based attenuation correction map of PET images in the brain employing single STE-MR imaging modality.

Generating MR-based attenuation correction map (μ-map) for quantitative reconstruction of PET images still remains a challenge in hybrid PET/MRI systems, mainly because cortical bone structures are indistinguishable from proximal air cavities in conventional MR images. Recently, development of short echo-time (STE) MR imaging sequences, has shown promise in differentiating cortical bone from air. However, on STE-MR images, the bone appears with discontinuous boundaries. Therefore, segmentation techniques based on intensity classification, such as thresholding or fuzzy C-means, fail to homogeneously delineate bone boundaries, especially in the presence of intrinsic noise and intensity inhomogeneity. Consequently, they cannot be fully automatized, must be fine-tuned on the case-by-case basis, and require additional morphological operations for segmentation refinement. To overcome the mentioned problems, in this study, we introduce a new fully automatic and reproducible STE-MR segmentation approach exploiting level-set in a clustering-based intensity inhomogeneity correction framework to reliably delineate bone from soft tissue and air. MR images were acquired on a clinical 1.5T MRI System, MAGNETOM Avanto, using a FLASH 3D pulse sequence with TE=1.1ms, TR=12ms, flip angle=18°, voxel size=1.2×1.2×2mm3. For segmentation of the STE-MR images into three regions, consisting of bone, air and soft tissue, a region-based level-set segmentation algorithm was applied. In this technique, k-means clustering is applied to estimate the intensity properties of each region for bias field correction simultaneously with the level-set segmentation. This algorithm incorporates both intensity and spatial information to define continuous boundaries. The quantitative assessment outcomes of the segmentation performance yielded an average of 89%, 82%, 91%, and 73% for the accuracy, sensitivity, specificity and dice scores in bone segmentation, respectively. The results suggest that the proposed fully automatic segmentation approach can reliably discriminate bony structures from the neighboring air and soft tissue in STE-MR images, which is suitable for generating accurate μ-maps in clinical PET/MR applications.

3D cerebrovascular segmentation combining fuzzy vessel enhancement and level-sets with anisotropic energy weights

The aim of this work is to present and evaluate a level-set segmentation approach with vesselness-dependent anisotropic energy weights, which focuses on the exact segmentation of malformed as well as small vessels from time-of-flight (TOF) magnetic resonance angiography (MRA) datasets.In a first step, a vesselness filter is used to calculate the vesselness dataset, which quantifies the likeliness of each voxel to belong to a bright tubular-shaped structure and estimate the corresponding vessel directions from a given TOF dataset. The vesselness and TOF datasets are then combined using fuzzy-logic and used for initialization of a variational level-set method. The proposed level-set model has been extended in a way that the weight of the internal energy is locally adapted based on the vessel direction information. Here, the main idea is to weight the internal energy lower if the gradient direction of the level-set is similar to the direction of the eigenvector extracted by the vesselness filter. Furthermore, an additional vesselness force has been integrated in the level-set formulation.The proposed method was evaluated based on ten TOF MRA datasets from patients with an arteriovenous malformation. Manual segmentations from two observers were available for each dataset and used for quantitative comparison. The evaluation revealed that the proposed method yields significantly better segmentation results than four other state-of-the-art segmentation methods tested. Furthermore, the segmentation results are within the range of the inter-observer variation.In conclusion, the proposed method allows an improved delineation of small vessels, especially of those represented by low intensities and high surface curvatures.

The Feasibility of Hybrid Automatic Segmentation of Axillary Lymph Nodes from a 3-D Sonogram

The use of manual segmentation of lymph nodes, within an ultrasound image, is challenging due to operator dependency and speckle. A group of 23 healthy female volunteers consented to a short imaging session to capture a maximum of three axillary lymph nodes. A feasibility study was completed using both automatic and manual segmentation techniques to analyze a sample of 45, three-dimensional (3-D) nodal volume sets. Level-set segmentation based on geodesic active contours and shape-space learning based on a level-set segmentation approach was used to capture global node shapes. Most of the image feature based segmentation methods failed; however, a more precise automatic segmentation algorithm was obtained using a superimposed shape model. Shape model based segmentation significantly improved the segmentation compared with standard level sets. The best segmentation results were achieved when an experienced sonographer assisted with setting seed surfaces. The initialization of seed surfaces improved the capture of the global shape and lymphatic vessels.

Automatic system for 3D reconstruction of the chick eye based on digital photographs

The geometry of anatomical specimens is very complex and accurate 3D reconstruction is important for morphological studies, finite element analysis (FEA) and rapid prototyping. Although magnetic resonance imaging, computed tomography and laser scanners can be used for reconstructing biological structures, the cost of the equipment is fairly high and specialised technicians are required to operate the equipment, making such approaches limiting in terms of accessibility. In this paper, a novel automatic system for 3D surface reconstruction of the chick eye from digital photographs of a serially sectioned specimen is presented as a potential cost-effective and practical alternative. The system is designed to allow for automatic detection of the external surface of the chick eye. Automatic alignment of the photographs is performed using a combination of coloured markers and an algorithm based on complex phase order likelihood that is robust to noise and illumination variations. Automatic segmentation of the external boundaries of the eye from the aligned photographs is performed using a novel level-set segmentation approach based on a complex phase order energy functional. The extracted boundaries are sampled to construct a 3D point cloud, and a combination of Delaunay triangulation and subdivision surfaces is employed to construct the final triangular mesh. Experimental results using digital photographs of the chick eye show that the proposed system is capable of producing accurate 3D reconstructions of the external surface of the eye. The 3D model geometry is similar to a real chick eye and could be used for morphological studies and FEA.

Optimisation of orthopaedic implant design using statistical shape space analysis based on level sets

Statistical shape analysis techniques have shown to be efficient tools to build population specific models of anatomical variability. Their use is commonplace as prior models for segmentation, in which case the instance from the shape model that best fits the image data is sought. In certain cases, however, it is not just the most likely instance that must be searched, but rather the whole set of shape instances that meet certain criterion. In this paper we develop a method for the assessment of specific anatomical/morphological criteria across the shape variability found in a population. The method is based on a level set segmentation approach, and used on the parametric space of the statistical shape model of the target population, solved via a multi-level narrow-band approach for computational efficiency. Based on this technique, we develop a framework for evidence-based orthopaedic implant design. To date, implants are commonly designed and validated by evaluating implant bone fitting on a limited set of cadaver bones, which not necessarily span the whole variability in the population. Based on our framework, we can virtually fit a proposed implant design to samples drawn from the statistical model, and assess which range of the population is suitable for the implant. The method highlights which patterns of bone variability are more important for implant fitting, allowing and easing implant design improvements, as to fit a maximum of the target population. Results are presented for the optimisation of implant design of proximal human tibia, used for internal fracture fixation.

A New User Dependent Iris Recognition System Based on an Area Preserving Pointwise Level Set Segmentation Approach

This paper presents a new user dependent approach in iris recognition systems. In the proposed method, consistent bits of iris code are calculated, based on the user specifications, using the user's mask. Another contribution of our work is in the iris segmentation phase, where a new pointwise level set approach with area preserving has been used for determining inner and outer iris boundaries, both exclusively performed in one step. Thanks to the special properties of this segmentation technique, there is no constraint about angles of head tilt. Furthermore, we showed that this algorithm is robust in noisy situations and can locate irises which are partly occluded by eyelid and eyelashes. Experimental results, on three renowned iris databases (CASIAIrisV3, Bath, and Ubiris), show that our method outperforms some of the existing methods, both in terms of accuracy and response time.

Level Set Hyperspectral Image Classification Using Best Band Analysis

We present a supervised hyperspectral classification procedure consisting of an initial distance-based segmentation method that uses best band analysis (BBA), followed by a level set enhancement that forces localized region homogeneity. The proposed method is tested on two hyperspectral images of an urban and rural nature. The proposed method is compared to the maximum likelihood (ML) method using BBA. Quantitative results are compared using segmentation and classification accuracies. Results show that both the initial classification using BBA features and the level set enhancement produced high-quality ground cover maps and outperformed the ML method, as well as previous studies by the authors. For example, with the compact airborne spectrographic imager image, the ML method resulted in accuracies les95.5%, whereas the level set segmentation approach resulted in accuracies as high as 99.7%.