Active Contour Approach Research Articles

Incremental prognostic value of fully automatic LVEF measured at stress using machine learning

Abstract Background Cardiovascular magnetic resonance (CMR) is the gold standard to measure left ventricular ejection fraction (LVEF), and novel artificial intelligence-based automatic analyses have been proposed for less user interaction and time saving. However, whether automatic LVEF delivers similar information for risk stratification remains unknown. Purpose To assess the prognostic value for all-cause mortality of LVEF measured by stress CMR using a fully automatic machine learning algorithm without human correction. Methods Between 2016 and 2018, all consecutive patients referred for vasodilator stress CMR were included and followed for the occurrence of all-cause death. A fully automatic machine learning algorithm was trained on 3,700 scans and validated on 1,719 unseen CMR studies (MAGNETOM Aera and Skyra, Siemens Healthcare, Erlangen, Germany) to identify end-diastolic and end-systolic phases and segment LV volumes from short-axis cine images at stress. The algorithm combines multiple deep learning networks for detection and segmentation with an active contours approach. Manual and automatic LVEF measured at stress were compared with the paired Wilcoxon test, Pearson correlation and Bland-Altman analysis. Cox regressions were performed to determine the prognostic value of automatic LVEF measured at stress. Results Among 9,883 included patients included to this study, the automatic LVEF was successfully computed in 9,712 (98.3%) patients (66.6% male, mean age 66±12 years). The agreement between manual and automatic LVEF was good (bias = -0.01%, 95% limits of agreement, -6.7% to 6.7%; Pearson’s correlation coefficient r=0.94). A total of 504 (5.2%) deaths were observed during a median (IQR) follow-up period of 4.5 (3.7-5.2) years. Both manual and automatic volumetric assessments showed similar impact on outcome in univariate analyses (manual LVEF per 5%: hazard ratio [HR], 0.80 [95% CI 0.77–0.83]; p<0.001; automatic LVEF per 5%: HR, 0.84 [95% CI, 0.81–0.86]; p<0.001) and multivariable analyses (manual LVEF per 5%: HR, 0.81 [95% CI, 0.78–0.84]; p<0.001; automatic LVEF per 5%: HR, 0.84 [95% CI, 0.82–0.87]; p<0.001). Fully automatic stress LVEF showed an incremental prognostic value to predict all-cause mortality above all traditional risk factors, LVEF measured at rest, the presence of inducible ischemia and LGE (C-statistic improvement: 0.04; NRI=0.221; IDI=0.049; all p<0.001). Conclusions Automatic LVEF is equally predictive of all-cause mortality compared to manual LVEF, and has an incremental prognostic value compared to traditional risk factors, and other stress CMR parameters. Figures: Figure 1: Linear regression plots (A) and Bland-Altman plots (B) comparing stress LVEF measured by experts (LVEFexpert) and computed by fully-automated artificial-intelligence algorithms (LVEFAI). Figure 2: Kaplan-Meier curves for MACE stratified by fully-automated LVEF value. Test comparing the three groups is based on the log-rank test.

Incremental prognostic value of fully-automatic machine-learning based global circumferential strain during a stress CMR exam

Abstract Background Left ventricular global circumferential strain using cardiovascular magnetic resonance (CMR) is an accurate indicator to predict cardiovascular events. Although several studies have shown the excellent prognostic value of stress CMR, the prognostic value of stress global circumferential strain (sGCS) remains unknown. Purpose To investigate the prognostic value of sGCS for predicting cardiovascular events using a fully automatic machine learning algorithm without human correction in consecutive patients referred for stress CMR. Methods Between 2016 and 2018, all consecutive patients referred for stress CMR were included and followed for the occurrence of major adverse cardiovascular events (MACE), defined by cardiovascular death or nonfatal myocardial infarction (MI). A fully automatic machine learning algorithm was trained and validated on unseen CMR studies (MAGNETOM Aera and Skyra, Siemens Healthcare, Erlangen, Germany) to assess the sGCS from short-axis cine images at stress. The algorithm combines multiple deep learning networks for detection and segmentation with an active contours approach. Cox regressions were performed to determine the prognostic value of sGCS. Results Among 2,906 consecutive patients who underwent stress CMR, the automatic sGCS was successfully computed in 2,859 (98.4%) patients (68% male, mean age 64±12 years). A total of 256 (8.8%) MACEs were observed during a median (IQR) follow-up period of 4.5 (3.7-5.3) years. Using Kaplan-Meier analysis, sGCS and the presence of inducible ischemia were significantly associated with the occurrence of MACE (hazard ratio, HR: 1.12 [95% CI, 1.08-1.17]; and HR: 8.48 [95% CI, 6.05-11.91], both p<0.001; respectively). After adjustment for traditional risk factors, inducible ischemia and late gadolinium enhancement (LGE), sGCS was an independent predictor of a higher incidence of MACE (adjusted HR: 1.12 [95% CI, 1.05-1.20]). Finally, sGCS showed an incremental prognostic value to predict MACE compared to a multivariable model including traditional risk factors, the presence of inducible ischemia and LGE (C-statistic improvement: 0.05, p=0.007; NRI= 0.169; IDI= 0.097; both p<0.001). Conclusions Automatic sGCS has an incremental prognostic value to predict MACE above traditional risk factors, and other stress CMR parameters.Survival curvesIncremental prognostic value

Fully automated assessment of global longitudinal strain by machine learning predicts death in patients undergoing stress CMR

Abstract Background Several studies described the independent prognostic value of left ventricular global longitudinal strain (GLS) using cardiovascular magnetic resonance (CMR) to predict death and cardiovascular events. While routine GLS evaluation is a time consuming and partially operator-dependent process, the potential interest of GLS using a fully automated method has not yet been established. Purpose To assess the feasibility and prognostic value of GLS to predict all-cause death using a fully automated machine-learning algorithm without human correction in consecutive patients referred for stress CMR. Methods Between 2016 and 2018, all consecutive patients referred for stress CMR were included and followed for the occurrence of all-cause death. A fully automated machine learning algorithm was trained and validated on unseen CMR studies (MAGNETOM Aera and Skyra) to assess the GLS from long-axis cine images acquired at rest. The algorithm combines multiple deep learning networks for detection and segmentation with an active contours approach. Cox regressions were performed to determine the prognostic value of GLS. Results In a retrospective study of 9,883 consecutive patients who underwent stress CMR between 2016 and 2018, automated GLS was successfully computed in 9,638 (97.5%) patients (67% male, mean age 66±12 years). A total of 510 (5.3%) deaths were observed during a median follow-up period of 4.5 years (interquartile range: 3.7-5.2). GLS, the presence of inducible ischemia and late gadolinium enhancement (LGE) were significantly associated with the occurrence of death (hazard ratio, HR: 1.22 [95% CI, 1.17-1.26]; HR: 2.23 [95% CI, 1.61-3.10]; and HR: 2.04 [95% CI, 1.41-2.95], respectively, all p<0.001). After adjustment for traditional risk factors, inducible ischemia and LGE, GLS was an independent predictor of a higher incidence of death (adjusted HR: 1.14 [95% CI, 1.08-1.20]). Automated GLS showed an incremental prognostic value to predict death compared to traditional risk factors, inducible ischemia and LGE (C-statistic improvement: 0.05; NRI=0.146; IDI=0.244; all p<0.001). Conclusions Fully automated GLS measured at rest has an incremental prognostic value to predict all-cause death above traditional risk factors, and other stress CMR parameters. This finding suggests that unsupervised GLS measurements are accurate and allow improved risk stratification.

Incremental prognostic value of fully-automatic machine-learning based global circumferential strain during a stress CMR exam

Abstract Funding Acknowledgements Type of funding sources: None. Background Left ventricular global circumferential strain using cardiovascular magnetic resonance (CMR) is an accurate indicator to predict cardiovascular events. Although several studies have shown the excellent prognostic value of stress CMR, the prognostic value of stress global circumferential strain (sGCS) remains unknown. Aim To investigate the prognostic value of sGCS for predicting cardiovascular events using a fully automatic machine learning algorithm without human correction in consecutive patients referred for stress CMR. Methods Between 2016 and 2018, all consecutive patients referred for stress CMR were included and followed for the occurrence of major adverse cardiovascular events (MACE), defined by cardiovascular death or nonfatal myocardial infarction (MI). A fully automatic machine learning algorithm was trained and validated on unseen CMR studies (MAGNETOM Aera and Skyra, Siemens Healthcare, Erlangen, Germany) to assess the sGCS from short-axis cine images at stress. The algorithm combines multiple deep learning networks for detection and segmentation with an active contours approach. Cox regressions were performed to determine the prognostic value of sGCS. Results Among 2,906 consecutive patients who underwent stress CMR, the automatic sGCS was successfully computed in 2,859 (98.4%) patients (68% male, mean age 64±12 years). A total of 256 (8.8%) MACEs were observed during a median (IQR) follow-up period of 4.5 (3.7–5.3) years. Using Kaplan-Meier analysis, sGCS and the presence of inducible ischemia were significantly associated with the occurrence of MACE (hazard ratio, HR: 1.12 [95% CI, 1.08–1.17]; and HR: 8.48 [95% CI, 6.05–11.91], both p<0.001; respectively). After adjustment for traditional risk factors, inducible ischemia and late gadolinium enhancement (LGE), sGCS was an independent predictor of a higher incidence of MACE (adjusted HR: 1.12 [95% CI, 1.05–1.20]). Finally, sGCS showed an incremental prognostic value to predict MACE compared to a multivariable model including traditional risk factors, the presence of inducible ischemia and LGE (C-statistic improvement: 0.05, p = 0.007; NRI= 0.169; IDI= 0.097; both p<0.001). Conclusions Automatic sGCS has an incremental prognostic value to predict MACE above traditional risk factors, and other stress CMR parameters.

Additional prognostic value of fully-automatic Global Longitudinal Strain using machine learning

Abstract Funding Acknowledgements Type of funding sources: None. Background Several studies described the independent prognostic value of left ventricular global longitudinal strain (GLS) using cardiovascular magnetic resonance (CMR) to predict cardiovascular events. However, the potential interest of GLS using a fully automatic method assessed at rest during a stress CMR exam was not well established. Aim To assess the prognostic value of GLS to predict all-cause death using a fully automatic machine learning algorithm without human correction in consecutive patients referred for stress CMR. Methods Between 2016 and 2018, all consecutive patients referred for stress CMR were included and followed for the occurrence of all-cause death. A fully automatic machine learning algorithm was trained and validated unseen CMR studies (MAGNETOM Aera and Skyra, Siemens Healthcare, Erlangen, Germany) to assess the GLS from long-axis cine images acquired at rest. The algorithm combines multiple deep learning networks for detection and segmentation with an active contours approach. Cox regressions were performed to determine the prognostic value of GLS. Results Among 9,883 consecutive patients who underwent stress CMR between 2016 and 2018 retrospectively included, the automatic GLS was successfully computed in 9,638 (97.5%) patients (67% male, mean age 66±12 years). A total of 510 (5.3%) deaths were observed during a median (IQR) follow-up period of 4.5 (3.7–5.2) years. GLS, the presence of inducible ischemia and late gadolinium enhancement (LGE) were significantly associated with the occurrence of death (hazard ratio, HR: 1.22 [95% CI, 1.17–1.26]; HR: 2.23 [95% CI, 1.61–3.10]; and HR: 2.04 [95% CI, 1.41–2.95], respectively, all p<0.001). After adjustment for traditional risk factors, inducible ischemia and LGE, GLS was an independent predictor of a higher incidence of death (adjusted HR: 1.14 [95% CI, 1.08–1.20]). Automatic GLS showed an incremental prognostic value to predict death compared to traditional risk factors, inducible ischemia and LGE (C-statistic improvement: 0.05; NRI=0.146; IDI=0.244; all p<0.001). Conclusions Automatic GLS measured at rest has an incremental prognostic value to predict all-cause death above traditional risk factors, and other stress CMR parameters.

A Fully Convolutional Network with Waterfall Atrous Spatial Pooling and Localized Active Contour Loss for Fish Segmentation

Accurate measurements and statistics of fish data are important for sustainable development of aqua-enviroment and marine fisheries. For data measurements and statistics, automatic segmentation of fish is one of key tasks. The fish segmentation however is a challenging task due to arterfacts in underwater images. In this study, we introduce a deep-learning approach, namely FCN-WRN-WASP for automatic fish segmentation from the underwater images. In particular, we introduce a computational-efficient variation called Waterfall Atrous Spatial Pooling (WASP) module into a Fully convolutional network with Wide ResNet baseline. We also proposed a loss function inspired from active contour approach that can exploit the local intensity information from the input image. The approach has been validated on the DeepFish data and the SIUM data set. The results are promissing for fish segmentation, with higher Intersection over Union (IoU) scores compared to state of the arts. The evaluation results showed that the incorporation of the image based active contour loss helps increase the segmentation performance. In addition, the use of the WASP in the architecture is effective especially for forground fish segmentation.

Foveal avascular zone segmentation using deep learning-driven image-level optimization and fundus photographs.

The foveal avascular zone (FAZ) is a retinal area devoid of capillaries and associated with multiple retinal pathologies and visual acuity. Optical Coherence Tomography Angiography (OCT-A) is a very effective means of visualizing retinal vascular and avascular areas, but its use remains limited to research settings due to its complex optics limiting availability. On the other hand, fundus photography is widely available and often adopted in population studies. In this work, we test the feasibility of estimating the FAZ from fundus photos using three different approaches. The first two approaches rely on pixel-level and image-level FAZ information to segment FAZ pixels and regress FAZ area, respectively. The third is a training mask-free pipeline combining saliency maps with an active contours approach to segment FAZ pixels while being trained on image-level measures of the FAZ areas. This enables training FAZ segmentation methods without manual alignment of fundus and OCT-A images, a time-consuming process, which limits the dataset that can be used for training. Segmentation methods trained on pixel-level labels and image-level labels had good agreement with masks from a human grader (respectively DICE of 0.45 and 0.4). Results indicate the feasibility of using fundus images as a proxy to estimate the FAZ when angiography data is not available.

Semi-supervised COVID-19 volumetric pulmonary lesion estimation on CT images using probabilistic active contour and CNN segmentation

PurposeA semi-supervised two-step methodology is proposed to obtain a volumetric estimation of COVID-19-related lesions on Computed Tomography (CT) images. MethodsFirst, damaged tissue was segmented from CT images using a probabilistic active contours approach. Second, lung parenchyma was extracted using a previously trained U-Net. Finally, volumetric estimation of COVID-19 lesions was calculated considering the lung parenchyma masks.Our approach was validated using a publicly available dataset containing 20 CT COVID-19 images previously labeled and manually segmented. Then, it was applied to 295 COVID-19 patients CT scans admitted to an intensive care unit. We compared the lesion estimation between deceased and survived patients for high and low-resolution images. ResultsA comparable median Dice similarity coefficient of 0.66 for the 20 validation images was achieved. For the 295 images dataset, results show a significant difference in lesion percentages between deceased and survived patients, with a p-value of 9.1 × 10−4 in low-resolution and 5.1 × 10−5 in high-resolution images. Furthermore, the difference in lesion percentages between high and low-resolution images was 10 % on average. ConclusionThe proposed approach could help estimate the lesion size caused by COVID-19 in CT images and may be considered an alternative to getting a volumetric segmentation for this novel disease without the requirement of large amounts of COVID-19 labeled data to train an artificial intelligence algorithm. The low variation between the estimated percentage of lesions in high and low-resolution CT images suggests that the proposed approach is robust, and it may provide valuable information to differentiate between survived and deceased patients.

Volume Exploration Using Multidimensional Bhattacharyya Flow.

We present a novel approach for volume exploration that is versatile yet effective in isolating semantic structures in both noisy and clean data. Specifically, we describe a hierarchical active contours approach based on Bhattacharyya gradient flow which is easier to control, robust to noise, and can incorporate various types of statistical information to drive an edge-agnostic exploration process. To facilitate a time-bound user-driven volume exploration process that is applicable to a wide variety of data sources, we present an efficient multi-GPU implementation that (1) is approximately 400 times faster than a single thread CPU implementation, (2) allows hierarchical exploration of 2D and 3D images, (3) supports customization through multidimensional attribute spaces, and (4) is applicable to a variety of data sources and semantic structures. The exploration system follows a 2-step process. It first applies active contours to isolate semantically meaningful subsets of the volume. It then applies transfer functions to the isolated regions locally to produce clear and clutter-free visualizations. We show the effectiveness of our approach in isolating and visualizing structures-of-interest without needing any specialized segmentation methods on a variety of data sources, including 3D optical microscopy, multi-channel optical volumes, abdominal and chest CT, micro-CT, MRI, simulation, and synthetic data. We also gathered feedback from a medical trainee regarding the usefulness of our approach and discussion on potential applications in clinical workflows.

Recognition of Kannada Character Scripts Using Hybrid Feature Extraction and Ensemble Learning Approaches

An automated handwritten script identification system seeks more attention in the academic research field and commercial applications. Recognizing the handwritten Kannada scripts in recent years is an active research area. But, it is a much more challenging one in the pattern recognition field owing to the complexity of structural hierarchy, huge vocabulary count, and distinct people’s diverse handwriting styles. Therefore, this paper aims to develop Kannada handwritten script recognition framework by ensemble methods. Initially, the essential Kannada handwritten text images are collected. These collected images are used for pre-processing with the CLAHE and filtering techniques and followed by segmentation with the active contour approach. The segmented images are utilized using the Adaptive Local Tetra Pattern with freeman chain code histogram techniques. Here, the parameters in the LTrP are tuned with Hybrid Honey Badger Henry Gas Solubility Optimization. Finally, the handwritten recognition is performed by Hybrid Feature Extraction with Ensemble Deep Learning (HFE-EDH). Further, the recognition rate is elevated with the parameter optimization in deep learning approaches using the HGSO + HBA algorithm. Throughout the result analysis, the accuracy of the designed method attains 96%. Thus, the proposed method reveals better performance regarding various performance measures.

An active contour model driven by adaptive local pre-fitting energy function based on Jeffreys divergence for image segmentation

Active contour model (ACM) has been a competitive tool in image segmentation because of its desired segmentation result and accuracy. Nevertheless, it may become unstable while handling images with uneven intensity, different initial contours and noise. In addition, the computation process of the majority of existing ACMs is complex, which makes it time-consuming and less efficient. To resolve above issues, this paper puts forward an active contour approach driven by adaptive local pre-fitting energy function based on Jeffreys divergence (APFJD) for image segmentation. Although the computation process of the proposed model is also complex, the authors design pre-fitting functions that are computed ahead of iteration process, which reduces a great amount of computation time and increases segmentation accuracy. The key idea of utilizing pre-fitting energy is to firstly select a local region at a specific point of the entire image region and compute its median intensity. Next, this local region is grouped into two sub-regions based on this pre-computed median intensity. Afterwards, the mean intensities of these two sub-regions are calculated by averaging their image intensities respectively. Lastly, the same process is repeated at next point until all points in the whole image region are computed. After that, these two pre-fitting functions will be incorporated into a Jeffreys divergence model to construct the proposed energy function. To further improve system stability and robustness, a regularization function is defined to optimize and normalize the data-driven term and level set function. Compared with local region-based models and recently developed models, the proposed APFJD model not only greatly decreases computation cost, but also improves segmentation accuracy. Experimental results also confirm that this model is robust to initial contours with different positions as well as Gaussian noise, and effectively segments images with unevenly distributed intensity.

An Automatic Detection of Liver Tumor from CT Abdominal Images—A Comparative Approach

The liver is a vital organ in human body. Liver performs an important function including metabolism, digestion, and detoxification. Liver is a significant organ in an abdomen, and is connected to the nearby organ such as spleen, pancreas, gallbladder, abdomen, and gut through blood vessels. Specific approaches such as image gradient and region growing are not quite reliable for the segmentation of the liver tumor. A level-set approach is evaluated in this paper compared with the active contour approach of segmentation of the liver imaging from the image of the CT abdomen and Unified level set method, spatial Fuzzy C-means method for segmenting tumor from segmented liver images is appraised. The proposed approach is implemented by using the 3DIRCADB dataset available to the public as well as non-public datasets taken from Arthi Hospital, Chennai and Tirunelveli scanning centre. For validating the system based on the diverse quantitative measures, including space overlap, coefficient of similarity, Jaccard indices, using ground truth images, which are available in the public data set 3DIRCADB and the expert segmentation results which are manually identified by the clinical partner for nonpublic datasets. The analysis of the algorithm shows the better results for segmenting liver using level set system and spatial segmentation of Fuzzy C means of the tumor segmentation.

Multimodal Object Segmentation Using Geodesic Distance and Regional Marker Points in Active Contour Approach

Multimodal Object Segmentation Using Geodesic Distance and Regional Marker Points in Active Contour Approach

A statistical active contour model for interactive clutter image segmentation using graph cut optimization

This paper presents a statistical region based Active Contour Model (ACM) considering the correlation between local and global image statistics to segment cluttered images. Generally, cluttered images do not have constant intensity distribution; rather, the intensity may follow near constant variation in different regions. To quantify this variation, we have considered the Coefficient of Variation (CoV) of the regions interior and exterior to the contour as global statistics and the CoV in the local patches as local statistics. Subsequently, the region energy term of the proposed ACM is designed such that it minimizes the difference between the local and global statistics i.e. it encourages CoV for all the local patches inside and outside of the final contour to be nearly homogeneous. Further, we have verified that the energy formulation can be efficiently discretized and solved using graph cut optimization. The main advantages of graph-based formulation over level set formulation are the existence of a global optimal solution and lesser sensitivity to contour initialization. Additionally, the former formulation is significantly faster being non-iterative or convergable with very few iterations. Experimental results demonstrate the superior performance of our approach against other state-of-the-art active contour approaches and also over its level set counterpart.

Robot-assisted Ultrasound-guided Tracking of Anatomical Structures for the Application of Focused Ultrasound

Abstract High intensity focused ultrasound is used as a surgical tool to treat completely non-invasively several diseases. Examples of clinical applications are uterine fibroids, prostate cancer, thyroid nodules, and varicose veins. Precise targeting is key for improving the treatment outcome. A method for an automated, robot-assisted tracking system was developed and evaluated. A wireless ultrasound scanner was used to acquire images of the target, in this case, a blood vessel. The active contour approach by Chan and Vese was used to segment and track while moving the scanner along the target structure with a collaborative robotic arm. The performance was assessed using a custom made Agar phantom. The mean tracking error, which is defined as the remaining distance of the lesion to the images’ centre line, was 0.27 mm ± 0.18 mm.

An Adaptive and Extensible System for Satellite-Based, Large Scale Burnt Area Monitoring in Near-Real Time

In the case of ongoing wildfire events, timely information on current fire parameters is crucial for informed decision making. Satellite imagery can provide valuable information in this regard, since thermal sensors can detect the exact location and intensity of an active fire at the moment the satellite passes over. This information can be derived and distributed in near-real time, allowing for a picture of current fire activity. However, the derivation of the size and shape of an already affected area is more complex and therefore most often not available within a short time frame. For urgent decision making though, it would be desirable to have this information available in near-real time, and on a large scale. The approach presented here works fully automatic and provides perimeters of burnt areas within two hours after the satellite scene acquisition. It uses the red and near-infrared bands of mid-resolution imagery to facilitate continental-scale monitoring of recently occurred burnt areas. To allow for a high detection capacity independent of the affected vegetation type, segmentation thresholds are derived dynamically from contextual information. This is done by using a Morphological Active Contour approach for perimeter determination. The results are validated against semi-automatically derived burnt areas for five wildfire incidents in Europe. Furthermore, these results are compared with three widely used burnt area datasets on a country-wide scale. It is shown that a high detection quality can be reached in near real-time. The large-scale inter-comparison shows that the results coincide with 63% to 76% of the burnt area in the reference datasets. While these established datasets are only available with a time lag of several months or are created by using manual interaction, the presented approach produces results in near-real time fully automatically. This work is therefore supposed to represent a valuable improvement in wildfire related rapid damage assessment.

Active Contours Driven by Local and Global Region-Based Information for Image Segmentation

Intensity inhomogeneity and noise are two major parts in image segmentation. Aiming at these problems, this work proposes a novel hybrid active contour method which combines local and global statistical information into an improved signed pressure force (SPF) function. First, by considering the global information extracted from a region of interest, a new global-based SPF function is created that effectively adjusts the signs of the pressure force inside and outside the evolving curve. Second, a new local-based SPF function utilizes the normalized local intensity differences as the coefficients of local internal and external regions, which can segment complicated areas easily. Third, by combing the global-based SPF and the local-based SPF functions, an improved hybrid SPF function is constructed based on active contour approach. Experiments on many kinds of real and synthetic images show that our method makes superior segmentation accuracy and is more robust to initial contour and noises.

Classification and Localization of Naval Mines With Superellipse Active Contours

In this paper, an approach for the classification and localization of geometric shapes, e.g., man-made objects or different types of geological features, in sonar images is presented. It is applied to a concrete application case, namely the detection and classification of naval mines. The approach consists of three steps. In the first step, the sonar image is segmented by a new active contours algorithm. To deal with the significant noise on sonar images, the assumption is used that the segmenting contours of highlight and shadow areas of objects are geometric shapes that can be described by superellipses. It is shown here that this superellipse constraint, which can cover a wide range from box-shaped to round objects, can directly be incorporated into an active contours method without an additional edge framework. In addition to its robustness to noise, our superellipse-driven active contours approach has the advantage that it is adaptable to the intensity distribution properties of sonar images. The second step consists of the actual classification including a pose estimation using a standard naive Bayes classifier on the superellipse parameters that are computed by the segmentation in the first step. Robustness is further boosted in a novel third step in which the classification is verified in a top-down process. Based on the results of the bottom-up processes, i.e., the segmentation in step one and the pose estimation from the superellipse parameters plus the class estimation by the classifier in step two, it is possible to simulate what the input sonar image should look like if the results are correct. If this model-based top-down simulation is similar to the original sensor image, the classification result is accepted; otherwise it is rejected. To this end, different measures are compared to compute the similarity between the real sensor image and the anticipated image generated from the classification and localization hypothesis. Finally, our approach is evaluated with a challenging real-world data set of 213 synthetic aperture sonar sidescan images from sea trials with mock-up mines.

Active contour‐based clutter defiance scheme for correlation filters

The negative impact of clutters on correlation output still remains the problem not handled in correlation pattern recognition (CPR) paradigm. Some of the known impacts caused by the presence of clutters include pronounced side-lobe generation and reduction in height of correlation peak. The occurrence of the side-lobes results in the distortion of actual correlation output while making the class decision a difficult task. Whereas, reduction in correlation height may cause class decisions to go wrong. The authors propose a novel clutter defiance strategy based on object segmentation through active contours approach thus evading a negative effect on the correlation output. Instead of allowing clutters to participate in CPR-based classification decision they recommend blocking irrelevant details to avoid distortion in the correlation process. An appropriate tweaking in the optimal logarithmic maximum average correlation height filter design yields a performance gain up to 80% in the correlation peak to side-lobe ratio, thus making it well pronounced to classify the true class objects correctly. The improvement remains consistent throughout the range of in-plane angular distortions against synthetically cluttered challenging images.

In brief

PAGE 558 Two researchers from India have devised an oil-spill detection method using hybrid-pol data carried out through a reconstruction technique. The novel method tested on two different datasets demonstrated improved detection over competing state-of-the methods, utilising Oil Spill Index (OSI) as a new parameter. PAGE 525 The current correlation pattern recognition (CPR) paradigm does not account for the negative impact of clusters on correlation output. A team of researchers from Pakistan has proposed a clutter defiance strategy based on object segmentation through an active contour approach, with consistent improvement across a range of challenging distorted images. An annotated RGB decomposed AIRSAR image. PAGE 548 A team of researchers from China have developed a compact substrate integrated waveguide three-state diplexer which operates at three frequency bands by integrating three diplexers in three different states on a single circuit. A ‘+’ shaped slot etched onto the waveguide cavity further improves design flexibility and can be used to independently control the resonant frequencies. Added complexity cluttered test images. PAGE 540 In cloud systems, malicious users can initiate side channel attacks to steal private information through virtualisation. Researchers from India present a multi-objective load balancing framework to minimise attack likelihood by reducing the number of shared servers, with this approach drastically improving resource and power usage. TE102 mode current distribution in cavity. PAGE 508 A collaboration of researchers from France have designed and fabricated a split ring resonator antenna integrated in textiles by embroidery. The textile antenna exhibited a radiation pattern similar to that of a dipole antenna and evidenced three operating modes dependent on the individual resonance frequency of either the dipole or resonator. Chromosome encoding and mutation operation. Schematic and image views of embroidered antenna.