Graph Cut Research Articles

FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders.

This paper proposes a general spectral analysis framework that thwarts a security risk in federated Learning caused by groups of malicious Byzantine attackers or colluders, who conspire to upload vicious model updates to severely debase global model performances. The proposed framework delineates the strong consistency and temporal coherence between Byzantine colluders' model updates from a spectral analysis lens, and, formulates the detection of Byzantine misbehaviours as a community detection problem in weighted graphs. The modified normalized graph cut is then utilized to discern attackers from benign participants. Moreover, the Spectral heuristics is adopted to make the detection robust against various attacks. The proposed Byzantine colluder resilient method, i.e., FedCut, is guaranteed to converge with bounded errors. Extensive experimental results under a variety of settings justify the superiority of FedCut, which demonstrates extremely robust model accuracy (MA) under various attacks. It was shown that FedCut's averaged MA is 2.1% to 16.5% better than that of the state of the art Byzantine-resilient methods. In terms of the worst-case model accuracy (MA), FedCut is 17.6% to 69.5% better than these methods.

Deep learning-based segmentation of breast masses using convolutional neural networks

Automatic breast tumor segmentation based on convolutional neural networks (CNNs) is significant for the diagnosis and monitoring of breast cancers. CNNs have become an important method for early diagnosis of breast cancer and, thus, can help decrease the mortality rate. In order to assist medical professionals in breast cancer investigation a computerized system based on two encoder-decoder architectures for breast tumor segmentation has been developed. Two pre-trained DeepLabV3+ and U-Net models are proposed. The encoder generates a high-dimensional feature vector while the decoder analyses the low-resolution feature vector provided by the encoder and generates a semantic segmentation mask. Semantic segmentation based on deep learning techniques can overcome the limitations of traditional algorithms. To assess the efficiency of breast ultrasound image segmentation, we compare the segmentation results provided by CNNs against the Local Graph Cut technique (a semi-automatic segmentation method) in the Image Segmenter application. The output segmentation results have been evaluated by using the Dice similarity coefficient that compares the ground truth images provided by the specialists against the predicted segmentation results provided by the CNNs and Local Graph Cut algorithm. The proposed approach is validated on 780 breast ultrasonographic images of the BUSI public database of which 437 are benign and 210 are malignant. The BUSI database provides classification (benign or malignant) labels for ground truth in binary mask images. The average Dice scores computed between the ground truth images against CNNs were as follows: 0.9360 (malignant) and 0.9325 (benign) for the DeepLabV3+ architecture and of 0.6251 (malignant) and 0.6252 (benign) for the U-Net, respectively. When the segmentation results provided by CNNs were compared with the Local Graph Cut segmented images, the Dice scores were 0.9377 (malignant) and 0.9204 (benign) for DeepLabV3+ architecture and 0.6115 (malignant) and 0.6119 (benign) for U-Net, respectively. The results show that the DeepLabV3+ has significantly better segmentation performance and outperforms the U-Net network.

NeuralPUMA: Learning to Phase Unwrap Through Differentiable Graph Cuts

NeuralPUMA: Learning to Phase Unwrap Through Differentiable Graph Cuts

Automation and acceleration of graph cut based image segmentation utilizing U-net

Automation and acceleration of graph cut based image segmentation utilizing U-net

Dental bitewing radiographs segmentation using deep learning-based convolutional neural network algorithms.

Dental radiographs, particularly bitewing radiographs, are widely used in dental diagnosis and treatment Dentalimage segmentation is difficult for various reasons, such as intricate structures, low contrast, noise, roughness, andunclear borders, resulting in poor image quality. Recent developments in deep learning models have improvedperformance in analyzing dental images. In this research, our primary objective is to determine the most effectivesegmentation technique for bitewing radiographs based on different metrics: accuracy, training time, and thenumber of training parameters as a reflection of architectural cost. In this research, we employ several deep learning models, namely Resnet-18, Resnet-50, Xception, InceptionResnet v2, and Mobilenetv2, to segment bitewing radiographs. The process begins by importing the radiographsinto MATLAB®(MathWorks Inc), where the images are first improved, then segmented using the graph cut methodbased on regions to produce a binary mask that distinguishes the background from the original X-ray. The deep learning models were trained on 298 and 99 radiograph training and validation sets and were evaluatedusing 99 images from the testing set. We also compare the segmentation model using several criteria, includingaccuracy, speed, and size, to determine which network is superior. Furthermore, we compare our findings with priorresearch to provide a comprehensive understanding of the advancements made in dental image segmentation. Theaccurate segmentation achieved was 93.67% and 94.42% by the Resnet-18 and Resnet-50 models, respectively. This research advances dental image analysis and facilitates more accurate diagnoses and treatment planning bydetermining the best segmentation technique. The outcomes of this study can guide researchers and practitionersin selecting appropriate segmentation methods for practical dental image analysis.

Prominent expression method for line features in multiview reconstruction

In multi-view reconstruction, mesh models are one of the most important data carriers. However, existing reconstruction methods have not adequately considered the existence of real-world edge features, resulting in insufficient utilization of geometric feature information from images. This leads to issues such as surface distortion and a lack of prominent edge features in the reconstructed mesh models. To address these challenges, this paper proposes a method of line features prominent expression during the multi-view reconstruction process. This algorithm integrates image line features and the mesh model to enhance geometric features. Specifically, in this paper, the line features on the image are first extracted, and the 2D line features are sampled and fitted to synthesize 3D line features by depth map. Then, it clusters the 3D line features and establishes minimum bounding boxes. Finally, the mesh line features are determined based on graph cut methods and are prominently expressed in the mesh model. Experimental validation demonstrates that in terms of the accuracy of line feature expression, the average reprojection pass rate for line features in five datasets reaches 93.7 %. This proves that this method significantly mitigates the issue of unclear edge features on the model surface, greatly improving the visual quality of mesh models while maintaining a high accuracy.

An efficient framework for optic disk segmentation and classification of Glaucoma on fundus images

Accurately segmenting the Optic Disk is a crucial step in classifying Glaucoma using Fundus images. Machine learning and artificial intelligence techniques are widely used in Glaucoma detection, and the main indicators observed in Fundus images are the presence of Papillary Atrophy, Cup to Disc Ratio values, diminishing Neural Retinal Rim (NRR), the Inferior Superior Nasal Temporal (ISNT) rule, and Cup Diameter. In this research, we investigated various segmentation and classification techniques that can be applied to Optic disk segmentation and classification of normal and glaucomatous eyes. The proposed method will be beneficial to clinicians and healthcare workers in facilities with limited resources. In this paper, histogram processing is used to determine the type of image, and based on this information; we decide whether the image requires segmentation. Some datasets in the standard dataset contain complete retinal images while others include segmented optic disks. The segmented images are directly given as input for classification using the proposed Convolutional Neural Network (CNN). For complete retinal images, segmentation is performed using the Simple Linear Iterative clustering (SLIC) and normalized graph cut algorithm. The proposed framework's performance is compared with that of pretrained neural networks, including VGG19, InceptionV3, and ResNet50V2, using major metrics. We trained and tested these architectures with 3115 images from six standard datasets. Our proposed framework outperforms all with an accuracy of 96.33 %.

Brain Tumor Localization Using N-Cut

A brain tumor is an abnormal collection of tissue in the brain. When tumors form, they are classified as either malignant or benign. It is critical to notice and identify the existence of tumors in brain images since they can be life threatening. This paper illustrates a novel segmentation method in which threshold technique is combined with normalized cut (Ncut) for the segregation of the tumors from brain magnetic resonance (MR) images. Image segmentation is a technique for grouping images. It is a method of splitting an image into sections with comparable attributes such as intensity, texture, colour, and so on. In thresholding, an object is distinguished from the background, and for the proposed segmentation methodology, the threshold value is determined by normalized graph cut. A weighted graph is divided into disjointed sets (groups) in which the similarity within a group is high and the similarity across groups is low. A graph-cut is a grouping approach in which the total weight of edges eliminated between these two pieces is used to calculate the degree of dissimilarity between these two groups. The normalized cut criterion is used to calculate the total likeness within the groups as well as the dissimilarity between the different groups.

Generator Stator Partial Discharge Pattern Recognition Based on PRPD-Grabcut and DSC-GoogLeNet Deep Learning

Partial discharge (PD) pattern recognition of typical defects from generator stator bars is the basis of generator condition monitoring and fault diagnosis. A PD pattern recognition method for generator stator bars based on a phase-resolved partial discharge graph cut (PRPD-Grabcut) and Depthwise Separable Convolution GoogLeNet (DSC-GoogLeNet) deep learning neural network is proposed in this paper. First, five typical defects are designed on stator bars in the laboratory. A long-term high voltage test is carried out, and 37500 PRPD original graphs are obtained. Second, a PRPD-Grabcut method based on image segmentation is proposed, which is designed to extract key components of the PRPD map. Finally, a DSC-GoogLeNet based PD pattern recognition method is proposed, which combines the GoogLeNet inception module and depth-wise separable convolution. Experimental results show that the PRPD-Grabcut contributes to certain improvements in the recognition accuracy and training efficiency of the neural network. The DSC-GoogLeNet shows superiority in recognition accuracy, cross-entropy loss, and training time compared to a variety of existing lightweight neural networks. In addition, compared with other networks, the DSC-GoogLeNet greatly improves the recognition accuracy of PD types with similar but different risk levels for stator insulation.

Event-Based Motion Segmentation With Spatio-Temporal Graph Cuts.

Identifying independently moving objects is an essential task for dynamic scene understanding. However, traditional cameras used in dynamic scenes may suffer from motion blur or exposure artifacts due to their sampling principle. By contrast, event-based cameras are novel bio-inspired sensors that offer advantages to overcome such limitations. They report pixel-wise intensity changes asynchronously, which enables them to acquire visual information at exactly the same rate as the scene dynamics. We develop a method to identify independently moving objects acquired with an event-based camera, that is, to solve the event-based motion segmentation problem. We cast the problem as an energy minimization one involving the fitting of multiple motion models. We jointly solve two sub-problems, namely event-cluster assignment (labeling) and motion model fitting, in an iterative manner by exploiting the structure of the input event data in the form of a spatio-temporal graph. Experiments on available datasets demonstrate the versatility of the method in scenes with different motion patterns and number of moving objects. The evaluation shows state-of-the-art results without having to predetermine the number of expected moving objects. We release the software and dataset under an open source license to foster research in the emerging topic of event-based motion segmentation.

Automated system for detection and classification of cystoid macular oedema using OCT images

ABSTRACT Optical Coherence Tomography (OCT) is a non-invasive tool for imaging the cross-sectional view of the retina. Cystoid macular oedema (CME) is a pathological condition of the retina that can lead to significant visual impairment. In this paper, we propose an automated system for the detection and classification of CME. The first step includes pre-processing for the removal of speckle noise using edge preserving bilateral image filtering. Thereafter, four retinal layers (ILM, ELM, IS/OS and RPE) are segmented using graph cut theory. Macular thickness is measured for the detection of CME. The third step detects the presence of cystoid fluid inside the layers as positive CME cases followed by classification of CME. The algorithm is tested on 115 healthy and 115 CME-affected OCT images collected from publicly available and clinical databases. The proposed methodology shows promising results with sensitivity, specificity and accuracy of 95.81%, 98.73% and 98.12%, respectively.

An Efficient Cloudlet Deployment Method Based on Approximate Graph Cut in Large-scale WMANs

An Efficient Cloudlet Deployment Method Based on Approximate Graph Cut in Large-scale WMANs

A novel approach for neural networks based diagnosis and grading of stroke in tumor-affected brain MRIs

ABSTRACT Recognition and diagnosis of stroke from magnetic resonance Image (MRIs) are significant for medical procedures in therapeutic standards. The primary goal of this scheme is the discovery of stroke in tumour locale in brain tissues influenced image. The probability of stroke is categorized on brain tumour influenced images into mild, moderate, or serious cases. The mild and moderate phases of stroke are recognized as “Ahead of schedule” findings and serious cases are distinguished as “Advance” determination. The proposed Glioblastoma brain tumour recognition strategy used the Multifaceted Brain Tumour Image Segmentation test open-access dataset for evaluating the presentation. The brain images are classified utilizing the Deep Neural Networks classification algorithm as normal and abnormal images. The tumour region is segmented from the identified set of abnormal images using the normalized graph cut algorithm. The stroke likelihood is identified using the Deep Neural Networks by analysing the proximity of tumour section in brain matters. The proposed stroke analysis framework accurately groups 10 images as “Right on time” stroke probability images and accomplishes 90% order rate. The proposed stroke prediction framework effectively characterizes images as “Advance” stroke probability images and accomplishes 90% characterization rate.

Support Vector Machine Algorithm for Effective Lung Cancer Detection Using Fuzzy Clusters

Tuberculosis is considered the main health threat in several parts of the world. This ithe primary infectiousdisease causing this disease .When untreatedandundiagnosed, there ishigh mortalityrate in patients.Thismethodincludes an automatic method to recognize tubersT his approach requires automated tuberculosis identification techniques to reduce problematic illnesses. Extraction of the lung region is first performed using the Graph Cut segmentation system. We develop a collection of properties including textures, shapes, etc. in this area of the lung. You must use an SVM to identify X-rays as normal or abnormal. The systematic system proposed for analyzing TB segmentation provides better performance than the graph cut segmentation

Liver PDFF estimation using a multi-decoder water-fat separation neural network with a reduced number of echoes

ObjectiveTo accurately estimate liver PDFF from chemical shift-encoded (CSE) MRI using a deep learning (DL)-based Multi-Decoder Water-Fat separation Network (MDWF-Net), that operates over complex-valued CSE-MR images with only 3 echoes.MethodsThe proposed MDWF-Net and a U-Net model were independently trained using the first 3 echoes of MRI data from 134 subjects, acquired with conventional 6-echoes abdomen protocol at 1.5 T. Resulting models were then evaluated using unseen CSE-MR images obtained from 14 subjects that were acquired with a 3-echoes CSE-MR pulse sequence with a shorter duration compared to the standard protocol. Resulting PDFF maps were qualitatively assessed by two radiologists, and quantitatively assessed at two corresponding liver ROIs, using Bland Altman and regression analysis for mean values, and ANOVA testing for standard deviation (STD) (significance level: .05). A 6-echo graph cut was considered ground truth.ResultsAssessment of radiologists demonstrated that, unlike U-Net, MDWF-Net had a similar quality to the ground truth, despite it considered half of the information. Regarding PDFF mean values at ROIs, MDWF-Net showed a better agreement with ground truth (regression slope = 0.94, R2 = 0.97) than U-Net (regression slope = 0.86, R2 = 0.93). Moreover, ANOVA post hoc analysis of STDs showed a statistical difference between graph cuts and U-Net (p < .05), unlike MDWF-Net (p = .53).ConclusionMDWF-Net showed a liver PDFF accuracy comparable to the reference graph cut method, using only 3 echoes and thus allowing a reduction in the acquisition times.Clinical relevance statementWe have prospectively validated that the use of a multi-decoder convolutional neural network to estimate liver proton density fat fraction allows a significant reduction in MR scan time by reducing the number of echoes required by 50%.Key Points• Novel water-fat separation neural network allows for liver PDFF estimation by using multi-echo MR images with a reduced number of echoes.• Prospective single-center validation demonstrated that echo reduction leads to a significant shortening of the scan time, compared to standard 6-echo acquisition.• Qualitative and quantitative performance of the proposed method showed no significant differences in PDFF estimation with respect to the reference technique.

3D shape reconstruction of Japanese traditional puppet head from CT images by graph cut and machine learning methods

In this study, we discuss the digital archiving of Japanese traditional puppets. We propose two methods for extracting the puppet head shape from computed tomography (CT) images. The first is the graph cut method, and the second is a machine learning method based on U-Net. According to the experimental results of the extraction of puppet heads from CT images, the U-Net-based method can extract puppet heads more accurately than the graph cut method. Moreover, the U-Net-based method can extract puppet heads with multiple materials. However, the extraction of metal parts is inaccurate because of metal artefacts in the X-ray CT images and insufficient learning data.

Investigations of color image segmentation based on connectivity measure, shape priority and normalized fuzzy graph cut

A vital ingredient of image analysis and vision-based systems is color image segmentation studies. Because color images contain more information than gray images, they are more fascinating to segment. Finding the features and associated information of a certain object becomes a difficult operation as a result of the underlying data for color images. Segmentation is highly challenging since color images have a diversity of color image and intensities. In this study, we employ shape priority of color image and connectivity measure as just a thresholding theme to distinguish an object from the surrounding. To introduce a normalized fuzzy graph cut measure based on the common S membership function in order to enhance the segmentation of color images. The execution of the suggested technique, also known as the S-fuzzy normalized graph cut (S-FNGC) approach. The structural imperfections in color images have been handled using the S-fuzzy normalized graph cut. In this algorithm, a system of S fuzzy sets is used to provide information about the specific feature of participation of a particular object in the boundary of the image. In the color image segmentation, the trouble of wrongly segmentation and segmentation with low accuracy can identify with the aid of using this approach. This proposed set of rules is as compared with the mask threshold, Gabor filter, some adaptive techniques like Genetic algorithm (GA), and K-Means clustering algorithm. Moreover, we take a look at that during maximum cases, our set of rules offers the lowest error rate and misclassification error values that enhance the segmentation manner of color images.

The determination of optimum segmentation parameters using genetic algorithms: Application to different segmentation algorithms and transmission electron microscopy tomography reconstructed volumes.

A method for optimizing an automatic selection of values for parameters that feed segmentation algorithms is proposed. Evolutionary optimization techniques in combination with a fitness function based on a mutual information parameter have been used to find the optimal parameter values of region growing, fuzzy c-means and graph cut segmentation algorithms. To validate the method, the segmentation of two transmission electron microscopy tomography reconstructed volumes of a carbon black-reinforced rubber and a polylactic acid and clay nanocomposite is carried out (i) using evolutionary optimization techniques and (ii) manually by experts. The results confirm that the use of evolutionary optimization techniques, such as genetic algorithms, reduces the computational operation cost needed for a total grid search of segmentation parameters, reducing the probability of reaching a false optimum, and improving the segmentation quality. HIGHLIGHTS: A new approach to optimize 3D segmentation algorithms. Methodology to optimize segmentation parameters and improve segmentation quality. Improvement on the results when using region growing, fuzzy c-means and graph cuts algorithms.

A full-resolution convolutional network with a dynamic graph cut algorithm for skin cancer classification and detection

A robust medical decision support system for classifying skin lesions from dermoscopy images is a crucial instrument for determining skin cancer prognosis. In recent years, full resolution convolutional network has made significant progress in recognizing skin cancer types from Dermoscopic images despite their fine-grained changes in appearance. Recently, full resolution convolutional network have gained popularity as a solution to semantic segmentation issues. However, the hyper-parameters it chooses are what determine how well it performs, and manually fine-tuning these hyper-parameters takes time. Therefore, a hyper-parameter optimized full resolution convolutional network is suggested for dermoscopy picture segmentation in this research. The network’s hyper-parameters are optimized by a brand-new dynamic graph cut algorithm method. Hyper-parameters emphasize the proper balance between exploration and exploitation by combining the wolves’ individual haunting tactics with their global haunting strategies to generate a neighborhood-based searching strategy. The fundamental objective of this study is to develop a hyper-parameter-optimized Full resolution convolutional network-based model capable of reliably diagnosing skin cancer types using dermoscopy images. The computer-aided diagnosis could be more efficient and precise. The segmentation approach is the primary way to identify cancerous tumors with precision. This study introduces a dynamic graph cut algorithm -based method for accurate segmentation and improved skin cancer classification using a full resolution convolutional network. Experiments reveal that the proposed model effectively addresses the frequent over-segmentation and under-segmentation issues in graph cut and the subject of wrongly segmented small sections in the grab cut method. In addition, the results illustrate the utility of data augmentation in training and testing, with enhanced performance compared to the usage of fresh images. Multiple experiments were done using various transferring models, and the results of our recommended model showed superior performance in skin lesion categorization tasks relative to other architectures with an accuracy of 97.986%.

GNN at the Edge: Cost-Efficient Graph Neural Network Processing Over Distributed Edge Servers

Edge intelligence has arisen as a promising computing paradigm for supporting miscellaneous smart applications that rely on machine learning techniques. While the community has extensively investigated multi-tier edge deployment for traditional deep learning models (e.g. CNNs, RNNs), the emerging Graph Neural Networks (GNNs) are still under exploration, presenting a stark disparity to its broad edge adoptions such as traffic flow forecasting and location-based social recommendation. To bridge this gap, this paper formally studies the cost optimization for distributed GNN processing over a multi-tier heterogeneous edge network. We build a comprehensive modeling framework that can capture a variety of different cost factors, based on which we formulate a cost-efficient graph layout optimization problem that is proved to be NP-hard. Instead of trivially applying traditional data placement wisdom, we theoretically reveal the structural property of quadratic submodularity implicated in GNN’s unique computing pattern, which motivates our design of an efficient iterative solution exploiting graph cuts. Rigorous analysis shows that it provides parameterized constant approximation ratio, guaranteed convergence, and exact feasibility. To tackle potential graph topological evolution in GNN processing, we further devise an incremental update strategy and an adaptive scheduling algorithm for lightweight dynamic layout optimization. Evaluations with real-world datasets and various GNN benchmarks demonstrate that our approach achieves superior performance over de facto baselines with more than 95.8% cost reduction in a fast convergence speed.