Fast Segmentation Research Articles

Synchronizing DDoS detection and mitigation based graph learning with programmable data plane, SDN

The availability of SD-IoT is now under complex and serious cyber threats, especially distributed denial-of-service attacks. However, traditional defense schemes suffer from coarse-grained centralized sampling approaches, low accuracy of detection models, and inefficient mitigation methods. In this paper, a novel DDoS defense scheme is proposed, which consists of a high-accuracy detection mechanism based on a Graph Convolutional Neural Network learning model and a mitigation mechanism based on fast traffic migration. In the detection stage, a fine-grained INT sampling approach is utilized to obtain multidimensional network topology and status information. The Graph Convolutional Neural Network learning model detects switches containing DDoS attack traffic with high accuracy because the detection model not only extracts and utilizes multiple temporal and spatial features of the collected information, but also has a better learning and representation capability. In the mitigation stage, the enhanced whitelist with dynamic threshold-based values is automatically adapted to the real-time state of the network environment for enhanced mitigation flexibility. The fast programmable segment rerouting strategy can block attack traffic in time and ensure the continuity of network services. The results of several comparison experiments show that the proposed scheme can detect DDoS attacks more accurately and mitigate them more effectively than traditional schemes.

Implementing a deep learning model for automatic tongue tumour segmentation in ex-vivo 3-dimensional ultrasound volumes

Three-dimensional (3D) ultrasound can assess the margins of resected tongue carcinoma during surgery. Manual segmentation (MS) is time-consuming, labour-intensive, and subject to operator variability. This study aims to investigate use of a 3D deep learning model for fast intraoperative segmentation of tongue carcinoma in 3D ultrasound volumes. Additionally, it investigates the clinical effect of automatic segmentation. A 3D No New U-Net (nnUNet) was trained on 113 manually annotated ultrasound volumes of resected tongue carcinoma. The model was implemented on a mobile workstation and clinically validated on 16 prospectively included tongue carcinoma patients. Different prediction settings were investigated. Automatic segmentations with multiple islands were adjusted by selecting the best-representing island. The final margin status (FMS) based on automatic, semi-automatic, and manual segmentation was computed and compared with the histopathological margin. The standard 3D nnUNet resulted in the best-performing automatic segmentation with a mean (SD) Dice volumetric score of 0.65 (0.30), Dice surface score of 0.73 (0.26), average surface distance of 0.44 (0.61) mm, Hausdorff distance of 6.65 (8.84) mm, and prediction time of 8 seconds. FMS based on automatic segmentation had a low correlation with histopathology (r = 0.12, p = 0.67); MS resulted in a moderate but insignificant correlation with histopathology (r = 0.4, p = 0.12, n = 16).Implementing the 3D nnUNet yielded fast, automatic segmentation of tongue carcinoma in 3D ultrasound volumes. Correlation between FMS and histopathology obtained from these segmentations was lower than the moderate correlation between MS and histopathology.

Rapid automated lumen segmentation of coronary optical coherence tomography images followed by 3D reconstruction of coronary arteries.

Optical coherence tomography has emerged as an important intracoronary imaging technique for coronary artery disease diagnosis as it produces high-resolution cross-sectional images of luminal and plaque morphology. Precise and fast lumen segmentation is essential for efficient OCT morphometric analysis. However, due to the presence of various image artifacts, including side branches, luminal blood artifacts, and complicated lesions, this remains a challenging task. Our research study proposes a rapid automatic segmentation method that utilizes nonuniform rational B-spline to connect limited pixel points and identify the edges of the OCT lumen. The proposed method suppresses image noise and accurately extracts the lumen border with a high correlation to ground truth images based on the area, minimal diameter, and maximal diameter. We evaluated the method using 3300 OCT frames from 10 patients and found that it achieved favorable results. The average time taken for automatic segmentation by the proposed method is 0.17s per frame. Additionally, the proposed method includes seamless vessel reconstruction following the lumen segmentation. The developed automated system provides an accurate, efficient, robust, and user-friendly platform for coronary lumen segmentation and reconstruction, which can pave the way for improved assessment of the coronary artery lumen morphology.

A COVID-19 Prediction Using a Blockchain Approach Integrated With UV-NET for Urban Management

Growing cities contributed to the increase in the COVID-19 virus. Consequently, many researchers are exploring the dynamics of the pandemic and to analyse the impacts of pandemic on such cities. The main aim of this research is to understand impacts of the pandemic in Vellore city, Tamil Nadu, India by building a viable solution which can be beneficial for the medical fraternity. A blockchain based approach integrating Artificial Intelligence (AI) is proposed for secure access and storage of Electronic Health Records (EHR) of COVID-19 patients in Vellore city. The blockchain follows the principle of absolute privacy and anonymity of medical records. The decentralized architecture is built to secure from different attacks as the hash of the records are stored in the blockchain. The proposed approach consists of a U-net and V-net model, one for segmenting lungs from the x-rays and second one for segmenting COVID-19 infection patches. The UV-net model is a Convolutional Neural Network (CNN) for fast and precise image segmentation. Experimental analysis is provided on nearly 33,920 chest X-ray images and text records gathered from a hospital in the Vellore city. The proposed model resulted in a precision, recall and F-score of 0.91, 0.87 and 0.89 respectively. The predicted results are manually analysed by the doctor in their login to finally cross verify and conclude the results which are stored in blockchain. This will aid doctors to centrally diagnose the patients and assist in proper treatment for faster recovery.

ContinUNet: fast deep radio image segmentation in the Square Kilometre Array era with U-Net

ContinUNet: fast deep radio image segmentation in the Square Kilometre Array era with U-Net

DCTC: Fast and Accurate Contour-Based Instance Segmentation With DCT Encoding for High-Resolution Remote Sensing Images

DCTC: Fast and Accurate Contour-Based Instance Segmentation With DCT Encoding for High-Resolution Remote Sensing Images

In situ monitoring of toxic effects of algal toxin on cells by a novel microfluidic flow cytometry instrument

Algal toxins produced by microalgae, such as domoic acid (DA)11(DA) domoic acid, have toxic effects on humans. However, toxicity tests using mice only yield lethal doses of algal toxins without providing insights into the mechanism of action on cells. In this study, a fast segmentation of microfluidic flow cytometry cell images based on the bidirectional background subtraction (BBS)22(BBS) bidirectional background subtraction method was developed to get the visual evidence of apoptosis in both bright-field and fluorescence images. This approach enables mapping of changes in cell morphology and activity under algal toxins, allowing for fast (within 60 s) and automated biological detection. By combining microfluidics with flow cytometry, the intricate cellular-level reaction process can be observed in micro samples of 293 T cells and mouse spleen cells, offering potential for future in vitro experiments.

Dual-resolution transformer combined with multi-layer separable convolution fusion network for real-time semantic segmentation

Environmental perception is crucial for unmanned mobile platforms such as autonomous vehicles and robots. Precise and fast semantic segmentation of the surrounding scene is a key task to enhance this capability. Existing real-time semantic segmentation networks are typically based on convolutional neural networks (CNNs), which have achieved good results, but they still lack control over global context features. In recent years, the Transformer architecture has achieved significant success in capturing global context, which is beneficial for improving segmentation accuracy. However, Transformers tend to ignore local connections, and their computational complexity makes real-time segmentation challenging. We propose a lightweight real-time semantic segmentation network called DTMC-Net, which combines the advantages of CNNs and Transformers. We design a special residual convolution module called the Lightweight Multi-layer Separable Convolution Attention module (LMSCA) to reduce the parameter count and perform multi-scale feature fusion to capture local features effectively. We introduce the Simple Dual-Resolution Transformer (SDR Transformer) that utilizes lightweight attention mechanisms and residual feed forward networks to capture and maintain features, with multiple bilateral fusions between two branches to exchange information. The proposed Anti-artifact Aggregation Pyramid Pooling Module (AAPPM) optimizes the upsampling process, refines features, and performs multi-scale feature fusion again. DTMC-Net only contains 4.2M parameters and achieves good performance on multiple public datasets with different scenarios.

Lightweight Techniques to Improve Generalization and Robustness of U-Net Based Networks for Pulmonary Lobe Segmentation.

Lung lobe segmentation in chest CT is relevant to a wide range of clinical applications. However, existing segmentation pipelines often exhibit vulnerabilities and performance degradations when applied to external datasets. This is usually attributed to the size of the available dataset or model. We show that it is possible to enhance generalizability without huge resources by carefully curating the dataset and combining machine learning with medical expertise. Multiple machine learning techniques (self-supervision (SSL), attention (A), and data augmentation (DA)) are used to train a fast and fully-automated lung lobe segmentation model based on 2D U-Net. Our study involved evaluating these techniques on a diverse dataset collected under the RACOON project, encompassing 100 CT chest scans from patients with bacterial, viral, or SARS-CoV2 infections. We compare our model to a baseline U-Net trained on the same dataset. Our approach significantly improved segmentation accuracy (Dice score of 92.8% vs. 82.3%, p < 0.001). Moreover, our model achieved state-of-the-art performance (Dice score of 92.8% vs. 90.8% for the literature's state-of-the-art, p = 0.102) with reduced training examples (69 vs. 231 CT Scans). Among the techniques, data augmentation with expert knowledge displayed the most significant impact, enhancing the Dice score by +0.056. Notably, these enhancements are not limited to lobe segmentation but can be seamlessly integrated into various medical imaging segmentation tasks, demonstrating their versatility and potential for broader applications.

Three-Dimensional Point Cloud Segmentation Algorithm Based on Depth Camera for Large Size Model Point Cloud Unsupervised Class Segmentation.

This paper proposes a 3D point cloud segmentation algorithm based on a depth camera for large-scale model point cloud unsupervised class segmentation. The algorithm utilizes depth information obtained from a depth camera and a voxelization technique to reduce the size of the point cloud, and then uses clustering methods to segment the voxels based on their density and distance to the camera. Experimental results show that the proposed algorithm achieves high segmentation accuracy and fast segmentation speed on various large-scale model point clouds. Compared with recent similar works, the algorithm demonstrates superior performance in terms of accuracy metrics, with an average Intersection over Union (IoU) of 90.2% on our own benchmark dataset.

SC-UneXt: Nested UNeXt Architecture based on Medical Image Segmentation

UNet and its various variants are commonly used methods in medical image segmentation tasks; however, many network parameters, complex calculations, and slow usage are problems that need to be overcome. These problems hinder the specific application of fast image segmentation in real-time tasks. At the same time, the lesion area has problems such as small size, irregular shape, and blurred edges, which makes the network feature extraction difficult and the segmentation accuracy needs to be improved. At the same time, medical image segmentation provides a variety of effective methods for the accuracy and robustness of organ segmentation, lesion detection, and classification. Medical images have fixed structures, simple semantics, and diverse details, so integrating rich multi-scale features can improve segmentation accuracy. Given that the density of diseased tissue may be comparable to that of surrounding normal tissue, both global and local information are crucial to segmentation results. To this end, we propose an image segmentation method (SC -UNe X t) based on edge feature extraction and multi-scale feature fusion of convolutional multi-layer perceptron (MLP). The network is a deeply supervised encoder-decoder network, in which the encoder and decoder pass through a series of nested, multiple jump paths to reduce the semantic gap between the feature maps of the encoder and decoder sub-networks.; Multi - scale feature fusion is introduced based on the UNe Finally, we evaluate our model approach on the LIDC dataset public dataset. Experiments have proven the effectiveness of this method. Our model's similarity coefficient and intersection ratio reached 86.44% and 90.86% respectively. Compared with UNet and UNe X t, the network proposed in this article has improved in accuracy, intersection ratio of real values and predicted values, similarity coefficient, and segmentation effect.

CPFTransformer: transformer fusion context pyramid medical image segmentation network.

The application of U-shaped convolutional neural network (CNN) methods in medical image segmentation tasks has yielded impressive results. However, this structure's single-level context information extraction capability can lead to problems such as boundary blurring, so it needs to be improved. Additionally, the convolution operation's inherent locality restricts its ability to capture global and long-distance semantic information interactions effectively. Conversely, the transformer model excels at capturing global information. Given these considerations, this paper presents a transformer fusion context pyramid medical image segmentation network (CPFTransformer). The CPFTransformer utilizes the Swin Transformer to integrate edge perception for segmentation edges. To effectively fuse global and multi-scale context information, we introduce an Edge-Aware module based on a context pyramid, which specifically emphasizes local features like edges and corners. Our approach employs a layered Swin Transformer with a shifted window mechanism as an encoder to extract contextual features. A decoder based on a symmetric Swin Transformer is employed for upsampling operations, thereby restoring the resolution of feature maps. The encoder and decoder are connected by an Edge-Aware module for the extraction of local features such as edges and corners. Experimental evaluations on the Synapse multi-organ segmentation task and the ACDC dataset demonstrate the effectiveness of our method, yielding a segmentation accuracy of 79.87% (DSC) and 20.83% (HD) in the Synapse multi-organ segmentation task. The method proposed in this paper, which combines the context pyramid mechanism and Transformer, enables fast and accurate automatic segmentation of medical images, thereby significantly enhancing the precision and reliability of medical diagnosis. Furthermore, the approach presented in this study can potentially be extended to image segmentation of other organs in the future.

Investigation of an efficient multi-modal convolutional neural network for multiple sclerosis lesion detection

In this study, an automated 2D machine learning approach for fast and precise segmentation of MS lesions from multi-modal magnetic resonance images (mmMRI) is presented. The method is based on an U-Net like convolutional neural network (CNN) for automated 2D slice-based-segmentation of brain MRI volumes. The individual modalities are encoded in separate downsampling branches without weight sharing, to leverage the specific features. Skip connections input feature maps to multi-scale feature fusion (MSFF) blocks at every decoder stage of the network. Those are followed by multi-scale feature upsampling (MSFU) blocks which use the information about lesion shape and location. The CNN is evaluated on two publicly available datasets: The ISBI 2015 longitudinal MS lesion segmentation challenge dataset containing 19 subjects and the MICCAI 2016 MSSEG challenge dataset containing 15 subjects from various scanners. The proposed multi-input 2D architecture is among the top performing approaches in the ISBI challenge, to which open-access papers are available, is able to outperform state-of-the-art 3D approaches without additional post-processing, can be adapted to other scanners quickly, is robust against scanner variability and can be deployed for inference even on a standard laptop without a dedicated GPU.

Global flood extent segmentation in optical satellite images

Floods are among the most destructive extreme events that exist, being the main cause of people affected by natural disasters. In the near future, estimated flood intensity and frequency are projected to increase. In this context, automatic and accurate satellite-derived flood maps are key for fast emergency response and damage assessment. However, current approaches for operational flood mapping present limitations due to cloud coverage on acquired satellite images, the accuracy of flood detection, and the generalization of methods across different geographies. In this work, a machine learning framework for operational flood mapping from optical satellite images addressing these problems is presented. It is based on a clouds-aware segmentation model trained in an extended version of the WorldFloods dataset. The model produces accurate and fast water segmentation masks even in areas covered by semitransparent clouds, increasing the coverage for emergency response scenarios. The proposed approach can be applied to both Sentinel-2 and Landsat 8/9 data, which enables a much higher revisit of the damaged region, also key for operational purposes. Detection accuracy and generalization of proposed model is carefully evaluated in a novel global dataset composed of manually labeled flood maps. We provide evidence of better performance than current operational methods based on thresholding spectral indices. Moreover, we demonstrate the applicability of our pipeline to map recent large flood events that occurred in Pakistan, between June and September 2022, and in Australia, between February and April 2022. Finally, the high-resolution (10-30m) flood extent maps are intersected with other high-resolution layers of cropland, building delineations, and population density. Using this workflow, we estimated that approximately 10 million people were affected and 700k buildings and 25,000 km^2 of cropland were flooded in 2022 Pakistan floods.

A Deep Learning Pipeline for Assessing Ventricular Volumes from a Cardiac MRI Registry of Patients with Single Ventricle Physiology.

Purpose To develop an end-to-end deep learning (DL) pipeline for automated ventricular segmentation of cardiac MRI data from a multicenter registry of patients with Fontan circulation (Fontan Outcomes Registry Using CMR Examinations [FORCE]). Materials and Methods This retrospective study used 250 cardiac MRI examinations (November 2007-December 2022) from 13 institutions for training, validation, and testing. The pipeline contained three DL models: a classifier to identify short-axis cine stacks and two U-Net 3+ models for image cropping and segmentation. The automated segmentations were evaluated on the test set (n = 50) by using the Dice score. Volumetric and functional metrics derived from DL and ground truth manual segmentations were compared using Bland-Altman and intraclass correlation analysis. The pipeline was further qualitatively evaluated on 475 unseen examinations. Results There were acceptable limits of agreement (LOA) and minimal biases between the ground truth and DL end-diastolic volume (EDV) (bias: -0.6 mL/m2, LOA: -20.6 to 19.5 mL/m2) and end-systolic volume (ESV) (bias: -1.1 mL/m2, LOA: -18.1 to 15.9 mL/m2), with high intraclass correlation coefficients (ICCs > 0.97) and Dice scores (EDV, 0.91 and ESV, 0.86). There was moderate agreement for ventricular mass (bias: -1.9 g/m2, LOA: -17.3 to 13.5 g/m2) and an ICC of 0.94. There was also acceptable agreement for stroke volume (bias: 0.6 mL/m2, LOA: -17.2 to 18.3 mL/m2) and ejection fraction (bias: 0.6%, LOA: -12.2% to 13.4%), with high ICCs (>0.81). The pipeline achieved satisfactory segmentation in 68% of the 475 unseen examinations, while 26% needed minor adjustments, 5% needed major adjustments, and in 0.4%, the cropping model failed. Conclusion The DL pipeline can provide fast standardized segmentation for patients with single ventricle physiology across multiple centers. This pipeline can be applied to all cardiac MRI examinations in the FORCE registry. Keywords: Cardiac, Adults and Pediatrics, MR Imaging, Congenital, Volume Analysis, Segmentation, Quantification Supplemental material is available for this article. © RSNA, 2023.

Automatic cochlear multimodal 3D image segmentation and analysis using atlas–model-based method

Objectives To propose an automated fast cochlear segmentation, length, and volume estimation method from clinical 3D multimodal images which has a potential role in the choice of cochlear implant type, surgery planning, and robotic surgeries. Methods: Two datasets from different countries were used. These datasets include 219 clinical 3D images of cochlea from 3 modalities: CT, CBCT, and MR. The datasets include different ages, genders, and types of cochlear implants. We propose an atlas–model-based method for cochlear segmentation and measurement based on high-resolution μCT model and A-value. The method was evaluated using 3D landmarks located by two experts. Results: The average error was 0.61 ± 0.22 mm and the average time required to process an image was 5.21 ± 0.93 seconds (P<0.001). The volume of the cochlea ranged from 73.96 mm 3 to 106.97 mm 3 , the cochlear length ranged from 36.69 to 45.91 mm at the lateral wall and from 29.12 to 39.05 mm at the organ of Corti. Discussion: We propose a method that produces nine different automated measurements of the cochlea: volume of scala tympani, volume of scala vestibuli, central lengths of the two scalae, the scala tympani lateral wall length, and the organ of Corti length in addition to three measurements related to A-value. Conclusion: This automatic cochlear image segmentation and analysis method can help clinician process multimodal cochlear images in approximately 5 seconds using a simple computer. The proposed method is publicly available for free download as an extension for 3D Slicer software.

A unified hybrid Ritz-SEA acoustic vibration coupling method of a rectangular plate coupled with fast multipole boundary integration

The Ritz method, based on a segmental strategy, is known for its fast convergence and ability to handle arbitrary boundary conditions while maintaining accuracy comparable to benchmark solutions. It is particularly effective in calculating vibrations in composite laminates, functionally graded plates, and other novel plate types. However, this method faces challenges in accurately calculating the mid-frequency problems that arise between plate structures and acoustic cavities. To fill this gap, this paper proposes a Ritz and statistical energy analysis (Ritz-SEA) hybrid method for calculating rectangular plate acoustic vibration coupling in the mid-frequency range for both deterministic and random loads. This method utilizes the fast multi-pole boundary element integral equation and region segmentation mapping as the governing equation for the coupling boundaries. The power flow equation of the statistical energy analysis (SEA) method is incorporated to solve for the average sound pressure level and sound power level of the coupled acoustic cavity. A method that combines the CHIEF and Burton-Miller methods has been proposed to address the issue of non-unique solutions. Validation and parametric studies are conducted. The results demonstrate that this approach can effectively filter out random fluctuations in mid-frequency domains while exhibiting exceptional stability and precision.

Research on Fast Multi-Threshold Image Segmentation Technique Using Histogram Analysis

This paper investigates a method for the multi-threshold segmentation of grayscale imaging using the local minimum points of a histogram curve as the segmentation threshold. By smoothing the histogram curve and judging the conditions, the expected peaks and valleys are identified, and the corresponding minimum points are used as segmentation thresholds to achieve fast multi-threshold image segmentation. Compared to the OTSU method (maximum between-class variance) for multi-threshold segmentation and the region growing method, this method has less computational complexity. In the recognition and segmentation process of solder pads with adhesion of underfill in LED Chips, the segmentation time is less than one percent of that of the OTSU method and the region growing method. The segmentation effect is better than the OTSU method and the region growing method, and it can achieve fast multi-threshold segmentation of images. Moreover, it has strong adaptability to the differences in the overall grayscale of images, meeting the requirements for high UPH (Units Per Hour) in industrial production lines.

New media art design based on fast visual segmentation and 3D image processing

Acquiring innovative styles and compositions from intricate and heterogeneous artistic imagery has emerged as a pivotal research quandry within contemporary new media art image conception. In a concerted effort to adeptly distill the quintessence of artistic styles and elements embedded within these visuals, an innovative methodology is posited herein, underpinned by an enhanced U-net segmentation framework and harmoniously fused with the surface extraction image reconstruction algorithm. This meticulous amalgamation endeavors to attain accurate segmentation and tridimensional reconstruction of the artistry encapsulated in these images. Primarily, the imagery is meticulously partitioned, culminating in an output that artfully encapsulates the inherent artistic attributes. Subsequently, this segmentation outcome is adeptly reconstituted, bestowing form to a three-dimensional artistry model. Empirical validation substantiates the efficacy of this approach, with the method’s Mean Intersection over the Union (MIoU) parameter yielding an impressive score of 0.939 in segmentation performance. Moreover, the peak signal-to-noise ratio and structural similarity attain commendable zeniths of 38.16 and 0.9808, respectively, underscoring the excellence of the reconstruction process. The proposed methodology demonstrates its prowess in exacting segmentation and comprehensive reconstruction of semantic intricacies and nuanced features pervading the realm of artistic imagery. Consequently, this novel methodology augments artists’ capacity to discern diverse artistic paradigms and fabricate superlative new media art compositions of heightened caliber.

Hybrid conservative central/WENO finite difference scheme for two-dimensional detonation problems

In the present work, a hybrid finite difference scheme is proposed and tested for the study of two-dimensional detonation problems. The hybrid scheme consists of a fifth-order weighted essentially nonoscillatory (WENO) method for discontinuous regions and a fourth or sixth-order robust conservative central finite difference scheme for the remaining domain. An arbitrary shock sensor is used to identify the discontinuities. The proposed shock sensor is based on the absolute value of the density gradient with an arbitrary threshold computed at each time step using a fast image segmentation technique. The sensor is complemented with a Ducros sensor to avoid the selection of vortices as discontinuities. The hybrid scheme is tested for several benchmark examples, including a two-dimensional transverse detonation wave, detonation wave diffraction, and a multiple obstacles test case. The obtained results show that the proposed sensor detects discontinuities adequately and the hybrid schemes give the same results as the fifth-order WENO in faster computational time.