Pixel Connectivity Research Articles

An adaptive parameter-free seismic data denoising approach by combining general cross-validation thresholding and pixel connectivity in synchrosqueezed domain

High signal-to-noise ratio (SNR) seismic waveform data are conductive to various studies in seismology. Seismic denoising aims to enhance SNR by eliminating additive noise through signal processing while preserving important features of the seismic signal. Conventional parametric seismic denoising methods often require selecting appropriate parameters to achieve optimal results, which may be limiting when dealing with various types and scales of seismic data. Here, we develop an adaptive parameter-free denoising method by combining general cross-validation (GCV) thresholding and pixel connectivity in synchrosqueezed (SS) domain. In this denoising framework, the synchrosqueezed continuous wavelet transform (SS-CWT) is first applied to obtain a high-resolution time–frequency representation. Then, the GCV approach, which allows for choosing the (nearly) optimal threshold without relying on any prior knowledge about the noise level, is employed to attenuate most of the low-energy noise. After that, the relatively isolated high-energy residual noise remaining in the SS-CWT spectrum is removed using pixel connectivity thresholding. Finally, the inverse SS-CWT is applied to the thresholded spectrum to obtain the denoised seismic record. As the thresholds for GCV and pixel connectivity are derived from the spectrum characteristics of the data being analyzed, the proposed denoising approach is highly adaptive and parameter-free. We demonstrate the effectiveness and versatility of the proposed denoising framework using synthetic data and real seismic data from diverse monitoring scenarios, including land, ocean, and emerging distributed acoustic sensing (DAS). The results indicate that the method is a stable and efficient tool for seismic data denoising.Graphical

WFSS: weighted fusion of spectral transformer and spatial self-attention for robust hyperspectral image classification against adversarial attacks

The emergence of adversarial examples poses a significant challenge to hyperspectral image (HSI) classification, as they can attack deep neural network-based models. Recent adversarial defense research tends to establish global connections of spatial pixels to resist adversarial attacks. However, it cannot yield satisfactory results when only spatial pixel information is used. Starting from the premise that the spectral band is equally important for HSI classification, this paper explores the impact of spectral information on model robustness. We aim to discover potential relationships between different spectral bands and establish global connections to resist adversarial attacks. We design a spectral transformer based on the transformer structure to model long-distance dependency relationships among spectral bands. Additionally, we use a self-attention mechanism in the spatial domain to develop global relationships among spatial pixels. Based on the above framework, we further explore the influence of both spectral and spatial domains on the robustness of the model against adversarial attacks. Specifically, a weighted fusion of spectral transformer and spatial self-attention (WFSS) is designed to achieve the multi-scale fusion of spectral and spatial connections, which further improves the model’s robustness. Comprehensive experiments on three benchmarks show that the WFSS framework has superior defensive capabilities compared to state-of-the-art HSI classification methods.

Effective Invasiveness Recognition of Imbalanced Data by Semi-Automated Segmentations of Lung Nodules.

Over the past few decades, recognition of early lung cancers was researched for effective treatments. In early lung cancers, the invasiveness is an important factor for expected survival rates. Hence, how to effectively identify the invasiveness by computed tomography (CT) images became a hot topic in the field of biomedical science. Although a number of previous works were shown to be effective on this topic, there remain some problems unsettled still. First, it needs a large amount of marked data for a better prediction, but the manual cost is high. Second, the accuracy is always limited in imbalance data. To alleviate these problems, in this paper, we propose an effective CT invasiveness recognizer by semi-automated segmentation. In terms of semi-automated segmentation, it is easy for doctors to mark the nodules. Just based on one clicked pixel, a nodule object in a CT image can be marked by fusing two proposed segmentation methods, including thresholding-based morphology and deep learning-based mask region-based convolutional neural network (Mask-RCNN). For thresholding-based morphology, an initial segmentation is derived by adaptive pixel connections. Then, a mathematical morphology is performed to achieve a better segmentation. For deep learning-based mask-RCNN, the anchor is fixed by the clicked pixel to reduce the computational complexity. To incorporate advantages of both, the segmentation is switched between these two sub-methods. After segmenting the nodules, a boosting ensemble classification model with feature selection is executed to identify the invasiveness by equalized down-sampling. The extensive experimental results on a real dataset reveal that the proposed segmentation method performs better than the traditional segmentation ones, which can reach an average dice improvement of 392.3%. Additionally, the proposed ensemble classification model infers better performances than the compared method, which can reach an area under curve (AUC) improvement of 5.3% and a specificity improvement of 14.3%. Moreover, in comparison with the models with imbalance data, the improvements of AUC and specificity can reach 10.4% and 33.3%, respectively.

Connected pixels-based image smoothing filter

Digital image processing heavily relies on the connectivity of pixels, as it is a vital component for accurate object identification and analysis within an image. Grouping together pixels with similar features such as colour and intensity, allows for the formation of meaningful patterns or objects, which is essential for object recognition and segmentation. This approach is particularly valuable in photogrammetric imaging, video surveillance, deep learning as it facilitates the isolation of regions of interest and object tracking. Image smoothing is also a crucial aspect in enhancing visual quality by reducing noise and enhancing details, especially in applications such as aerial mapping, medical imaging, video compression, image resizing and computer vision. The absence of connected pixels and image smoothing would make image processing tasks more challenging and less reliable, making them fundamental to digital image processing and critical to various applications in diverse fields. This paper introduces a novel image smoothing filter called Connected Pixels Based Image Smoothing Filter (CPF), which is based on gray connected pixels. The success of the CPF was compared to that of the Non-Local Means Filter (NLMF) in terms of Structural Similarity Index (SSIM) for the same Mean Squared Error (MSE). The experimental results showed that CPF has a better ability to preserve image details compared to NLMF.

Directional Connectivity-based Segmentation of Medical Images.

Anatomical consistency in biomarker segmentation is crucial for many medical image analysis tasks. A promising paradigm for achieving anatomically consistent segmentation via deep networks is incorporating pixel connectivity, a basic concept in digital topology, to model inter-pixel relationships. However, previous works on connectivity modeling have ignored the rich channel-wise directional information in the latent space. In this work, we demonstrate that effective disentanglement of directional sub-space from the shared latent space can significantly enhance the feature representation in the connectivity-based network. To this end, we propose a directional connectivity modeling scheme for segmentation that decouples, tracks, and utilizes the directional information across the network. Experiments on various public medical image segmentation benchmarks show the effectiveness of our model as compared to the state-of-the-art methods. Code is available at https://github.com/Zyun-Y/DconnNet.

Seg-Road: A Segmentation Network for Road Extraction Based on Transformer and CNN with Connectivity Structures

Acquiring road information is important for smart cities and sustainable urban development. In recent years, significant progress has been made in the extraction of urban road information from remote sensing images using deep learning (DL) algorithms. However, due to the complex shape, narrowness, and high span of roads in the images, the results are often unsatisfactory. This article proposes a Seg-Road model to improve road connectivity. The Seg-Road uses a transformer structure to extract the long-range dependency and global contextual information to improve the fragmentation of road segmentation and uses a convolutional neural network (CNN) structure to extract local contextual information to improve the segmentation of road details. Furthermore, a novel pixel connectivity structure (PCS) is proposed to improve the connectivity of road segmentation and the robustness of prediction results. To verify the effectiveness of Seg-Road for road segmentation, the DeepGlobe and Massachusetts datasets were used for training and testing. The experimental results show that Seg-Road achieves state-of-the-art (SOTA) performance, with an intersection over union (IoU) of 67.20%, mean intersection over union (MIoU) of 82.06%, F1 of 91.43%, precision of 90.05%, and recall of 92.85% in the DeepGlobe dataset, and achieves an IoU of 68.38%, MIoU of 83.89%, F1 of 90.01%, precision of 87.34%, and recall of 92.86% in the Massachusetts dataset, which is better than the values for CoANet. Further, it has higher application value for achieving sustainable urban development.

Microseismic data denoising in the sychrosqueezed domain by integrating the wavelet coefficient thresholding and pixel connectivity

SUMMARY Microseismic monitoring is crucial for risk assessment in mining, fracturing and excavation. In practice, microseismic records are often contaminated by undesired noise, which is an obstacle to high-precision seismic locating and imaging. In this study, we develop a new denoising method to improve the signal-to-noise ratio (SNR) of seismic signals by combining wavelet coefficient thresholding and pixel connectivity thresholding. First, the pure background noise range in the seismic record is estimated using the ratio of variance (ROV) method. Then, the synchrosqueezed continuous wavelet transform (SS-CWT) is used to project the seismic records onto the time–frequency plane. After that, the wavelet coefficient threshold for each frequency is computed based on the empirical cumulative distribution function (ECDF) of the coefficients of the pure background noise. Next, hard thresholding is conducted to process the wavelet coefficients in the time–frequency domain. Finally, an image processing approach called pixel connectivity thresholding is introduced to further suppress isolated noise on the time–frequency plane. The wavelet coefficient threshold obtained by using pure background noise data is theoretically more accurate than that obtained by using the whole seismic record, because of the discrepancy in the power spectrum between seismic waves and background noise. After hard thresholding, the wavelet coefficients of residual noise exhibit isolated and lower pixel connectivity in the time–frequency plane, compared with those of seismic signals. Thus, pixel connectivity thresholding is utilized to deal with the residual noise and further improve the SNR of seismic records. The proposed new denoising method is tested by synthetic and real seismic data, and the results suggest its effectiveness and robustness when dealing with noisy data from different acquisition environments and sampling rates. The current study provides a useful tool for microseismic data processing.

Compact Pattern Reconfigurable Pixel Antenna With Diagonal Pixel Connections

An improved method to design compact pattern reconfigurable pixel antennas is described. The method introduces a new structure consisting of diagonal connections between pixels to enhance the pattern steering capability of the pixel antennas. These diagonal connections increase the number of independent degrees of freedom available in the design process which results in significantly improved performance when compared to designs with only horizontal and vertical connections between pixels. Furthermore, the diagonal structures enable the possible formation of new “cross-over” connections which provide a structure that allows currents to cross each other in the antenna geometry. Simulation and measurement results show that an antenna with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2\times $ </tex-math></inline-formula> 6 pixels can steer a beam over 150° in the azimuth plane and 300° beam steering range can be achieved with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3\times $ </tex-math></inline-formula> 6 pixels. The use of the diagonal elements increases gains by up to 3 dB and provides a much greater steering range when compared to pixel antenna design without the diagonal connections. Utilizing these diagonal pixel connections can also potentially enhance the performance of pixel antenna designs in a wide variety of other pixel antenna configurations.

RETRACTED: Design and development of SER-UNet model for glaucoma image analysis

Glaucoma is a life-threatening disease that must be diagnosed early before it causes blindness. It is a dangerous disease and challenging for ophthalmologists. Retinal diseases can be detected at earlier stages with the help of analyzing fundus images of the retina and through the retinal vessel segmentation process. However, traditional fully convolutional neural network-based equivalents have major drawbacks in segmentation such as a bifurcation breakup in the vascular map and lessening pixel connectivity of vessels. To overcome this drawback, we present the squeeze excitation residual UNet (SER-UNet) model for vessel segmentation. The proposed model uses a new type of residual block called SER residual blocks for vessel segmentation. Initially, the fundus image is read and downsampled by converting the input image into vector values. Then, it conducts segmentation by adding attention mechanism and residual structure into convolution blocks to find vessel regions accurately and aggregate the tiny vessel characteristics. It helps segment the image of the glaucoma affected region in the retina. Together with a pixelwise cross-entropy loss function, it shows excellent performance on fundus image segmentation. The performance of the proposed method is assessed with an accuracy of 98.90% and 98.31%, respectively, using the DRIVE and STARE datasets, respectively.

Graphical Image Region Extraction with K-Means Clustering and Watershed.

With a wide range of applications, image segmentation is a complex and difficult preprocessing step that plays an important role in automatic visual systems, which accuracy impacts, not only on segmentation results, but directly affects the effectiveness of the follow-up tasks. Despite the many advances achieved in the last decades, image segmentation remains a challenging problem, particularly, the segmenting of color images due to the diverse inhomogeneities of color, textures and shapes present in the descriptive features of the images. In trademark graphic images segmentation, beyond these difficulties, we must also take into account the high noise and low resolution, which are often present. Trademark graphic images can also be very heterogeneous with regard to the elements that make them up, which can be overlapping and with varying lighting conditions. Due to the immense variation encountered in corporate logos and trademark graphic images, it is often difficult to select a single method for extracting relevant image regions in a way that produces satisfactory results. Many of the hybrid approaches that integrate the Watershed and K-Means algorithms involve processing very high quality and visually similar images, such as medical images, meaning that either approach can be tweaked to work on images that follow a certain pattern. Trademark images are totally different from each other and are usually fully colored. Our system solves this difficulty given it is a generalized implementation designed to work in most scenarios, through the use of customizable parameters and completely unbiased for an image type. In this paper, we propose a hybrid approach to Image Region Extraction that focuses on automated region proposal and segmentation techniques. In particular, we analyze popular techniques such as K-Means Clustering and Watershedding and their effectiveness when deployed in a hybrid environment to be applied to a highly variable dataset. The proposed system consists of a multi-stage algorithm that takes as input an RGB image and produces multiple outputs, corresponding to the extracted regions. After preprocessing steps, a K-Means function with random initial centroids and a user-defined value for k is executed over the RGB image, generating a gray-scale segmented image, to which a threshold method is applied to generate a binary mask, containing the necessary information to generate a distance map. Then, the Watershed function is performed over the distance map, using the markers defined by the Connected Component Analysis function that labels regions on 8-way pixel connectivity, ensuring that all regions are correctly found. Finally, individual objects are labelled for extraction through a contour method, based on border following. The achieved results show adequate region extraction capabilities when processing graphical images from different datasets, where the system correctly distinguishes the most relevant visual elements of images with minimal tweaking.

Automatic coastline extraction through enhanced sea-land segmentation by modifying Standard U-Net

Sea-land segmentation (SLS) is an essential remote sensing task for various coastal and environmental studies such as coastline extraction, coastal erosion, coastal area monitoring, and ship or iceberg detection. This study aims at improving the SLS performance by modifying the Standard U-Net (SUN) model and developing an automatic coastline extraction framework. SUN generally has an acceptable performance in many applications. However, better SLS outputs are needed for reliable coastline extraction. In our proposed framework, we firstly analyzed three different input images, including Red-Green-Blue (RGB), Normalized Difference Water Index (NDWI), and Near-Infrared (NIR) images. Secondly, we modified the SUN architecture to improve the segmentation results. The main modifications are using different loss functions and two fusion methods for RGB and NIR images. The segmentation results were then passed into the subsequent automatic coastline extraction pipeline based on morphological operations and pixel connectivity analysis. The training and testing steps were accomplished utilizing a benchmark dataset of China’s coastal areas. Moreover, another dataset consisting of a time series of Landsat-8 imagery from the southern Caspian Sea coastlines was collected to evaluate coastline extraction efficiency. The results indicate that the proposed modifications could effectively enhance the performance of the SUN, with the most significant improvement to the Intersection over Union (IoU) score being as high as 1.68% and 8.95% in China and Caspian Sea datasets, respectively, while outperforming other state-of-the-art models including FC-DenseNet and DeepLabV3+.

Development of an efficient approach for detection and measurement of crack length in ceramic tile manufacturing using millimeter-wave imaging

The detection of crack and their measurement in the packed ceramic tiles is an important procedure for quality monitoring and testing in the tile manufacturing industry. In the investigation of undercover targets high-definition (HD) cameras or surface crack detection methods like eddy current testing, etc. fail but millimeter-wave imaging can be useful. In our experimental work, cracked tiles are covered with the packaging cardboard sheet, and the unknown crack is detected using Millimeter-Wave Imaging. In this paper, an adaptive and statistical approach is proposed for crack detection and a computer-aided non-invasive technique is developed to measure a crack length. After critically analyzing various available signal and image processing techniques, a line enhancement known as Frangi filtering is selected for crack detection. In the current scenario; the decision parameter for the Frangi filter known as the Frangi scale ratio is required to be fixed manually, to minimize the selection error automation of this process is done using a Genetic Algorithm (GA). In literature, the focus is limited to only the detection of cracks in the tile, but the estimation of the crack length is also essential. The possible use of image morphing techniques for the measurements of the crack length is explored. It is observed that the conventional Hough transform fails to measure the length of the individual crack segment, hence the pixel connectivity enforcement for hole filling and local intensity distribution equalization is proposed to extract the approximate coefficients belonging to the crack segment. The raw data collected previously from our laboratory is used and processed using the proposed methodology, the obtained results are satisfactory and very encouraging as compared to earlier results reported in the literature.

Reconstruction of Connected Digital Lines Based on Constrained Regularization.

This paper presents a new approach for reconstruction of disconnected digital lines (DDLs) based on a constrained regularization model which ensures connectivity of the digital lines (DLs) in the discrete image plane. The first step in this approach is to determine the order of given pixels of the DDL. To determine connectivity of pixels, we use the usual 8-neighbor connectivity in discrete images. For any neighboring pixels of the DDL that are not connected, we determine a number of new pixel values that need to be reconstructed between these pixels. Next, the integer-valued x - and y -coordinates of the location of the pixels of the DDLs are segregated into two 1D signal vectors. Then the x - and y -coordinates of the missing pixels of the DDLs are estimated using a new constrained regularization. While the solution of this constrained minimization problem provides real values for the x - and y -coordinates of pixels positions, the imposed constraint ensures connectivity of the resulting DLs in the image plane after transforming the computed values from [Formula: see text] to [Formula: see text]. The proposed regularization approach forces connected lines with small curvature. The experimental results demonstrate that the proposed technique improves DL intersection detection, as well. Moreover, this technique has a high potential to be used as a fast approach in binary image inpainting particularly overcoming the shortcomings of conventional methods which cause destruction of thin objects and blurring in the recovered regions.

Connectivity Approach for Detecting Unreliable DInSAR Ice Velocity Measurements

Differential synthetic aperture radar interferometry (DInSAR) allows for retrieval of ice velocity measurements of high resolution and accuracy. One of the main error sources in DInSAR is the phase unwrapping procedure. Unwrapping errors may be caused by several processes, including shear stresses associated with large motion gradients, which lead to loss of interferometric coherence. In many cases, unwrapping errors reach magnitudes corresponding to velocities of tens or even hundreds of meters per year. Traditional DInSAR implementations include pixel masking based on coherence thresholding; however, such a masking is not always sufficient. Consequently, the state-of-the-art for ice velocity retrievals involves either manual inspection of individual measurements or simply discarding measurements in regions where ice flow exceeds a predefined threshold. Here, we instead apply a masking based on thresholding of a pixel connectivity estimate with respect to a reference point, which aims to detect unwrapping errors based only on the estimated coherence pattern. The method is tested on both simulated and real data Sentinel-1 data from the Greenland Ice Sheet and effectively detects the majority of unwrapping errors (recall of 0.84 for the best performing threshold), although with a relatively low precision (0.52 for the best performing threshold). Importantly, higher magnitude unwrapping errors are associated with lower connectivity values, meaning that undetected errors have a significantly lower magnitude (median of 1.7 m/y, corresponding to a single phase cycle, compared with 40.5 m/y with no masking).

Pixel Antenna Optimization Based on Perturbation Sensitivity Analysis

Pixel antennas provide a straightforward method for antenna design that can meet a given set of specifications. A key step in the design of pixel antennas is the optimization of the hardwire connections between the pixels in the antenna. Due to the very large number of possible pixel connection combinations, this optimization needs to be performed by heuristic algorithms. In this work, the sensitivity analysis is proposed for the efficient optimization of pixel antennas. In the approach, each individual pixel of the antenna is perturbed in turn to obtain the sensitivity vector of the objective function. The sensitivity analysis at each step is performed efficiently through the use of algebraic simplification that avoids matrix inversion and leads to a significant saving in computational load. The optimization process then selects the perturbation with the greatest sensitivity. Two examples are provided to demonstrate the performance of the proposed optimization method. For both examples, the proposed approach performs the optimization with significantly fewer iterations and either achieves a better or similar minimum in the objective function compared to genetic algorithm approaches. Combined with the efficient computation of the sensitivity vector, significant savings in the computational load are achieved compared to existing approaches.

SibNet: Food instance counting and segmentation

Food computing has recently attracted considerable research attention due to its significance for health risk analysis. In the literature, the majority of research efforts are dedicated to food recognition. Relatively few works are conducted for food counting and segmentation, which are essential for portion size estimation. This paper presents a deep neural network, named SibNet, for simultaneous counting and extraction of food instances from an image. The problem is challenging due to varying size and shape of food as well as arbitrary viewing angle of camera, not to mention that food instances often occlude each other. SibNet is novel for proposal of learning seed map to minimize the overlap between instances. The map facilitates counting and can be completed as an instance segmentation map that depicts the arbitrary shape and size of individual instance under occlusion. To this end, a novel sibling relation sub-network is proposed for pixel connectivity analysis. Along with this paper, three new datasets covering Western, Chinese and Japanese food are also constructed for performance evaluation. The three datasets and SibNet source code are publicly available.

Connectivity-based deep learning approach for segmentation of the epithelium in in vivo human esophageal OCT images.

Optical coherence tomography (OCT) is used for diagnosis of esophageal diseases such as Barrett's esophagus. Given the large volume of OCT data acquired, automated analysis is needed. Here we propose a bilateral connectivity-based neural network for in vivo human esophageal OCT layer segmentation. Our method, connectivity-based CE-Net (Bicon-CE), defines layer segmentation as a combination of pixel connectivity modeling and pixel-wise tissue classification. Bicon-CE outperformed other widely used neural networks and reduced common topological prediction issues in tissues from healthy patients and from patients with Barrett's esophagus. This is the first end-to-end learning method developed for automatic segmentation of the epithelium in in vivo human esophageal OCT images.

Regularizer based on Euler characteristic for retinal blood vessel segmentation

Segmentation of retinal blood vessels is important for the analysis of diabetic retinopathy (DR). Existing methods do not prioritize the small and disconnected vessels for DR. With the aim of paying attention to the small and disconnected vessel regions, this study introduced Euler characteristics (EC) from topology to calculate the number of isolated objects on segmented vessel regions, which is the key contribution of this study. In addition, we utilized the number of isolated objects in a U-Net-like deep convolutional neural network (CNN) architecture as a regularizer to train the network for improving the connectivity between the pixels of the vessel regions. The proposed network performance of the regularizer based on EC in reconstructing vessel regions is compared over the network without our regularizer. Furthermore, the capacity of the proposed regularizer approach in enhancing the smoothness and pixel connectivity of the vessels is compared with graph-based smoothing (GS) and combined GS with isolated objects (GISO) regularizers for delineating blood vessel regions. The proposed approach achieved the area under the curve value of 0.982, which is much higher than the state-of-the-arts, and thus it is suggested that the proposed system could support accuracy and reliability in decision-making for DR detection.

Automatic tool segmentation and tracking during robotic intravascular catheterization for cardiac interventions.

Cardiovascular diseases resulting from aneurism, thrombosis, and atherosclerosis in the cardiovascular system are major causes of global mortality. Recent treatment methods have been based on catheterization of flexible endovascular tools with imaging guidance. While advances in robotic intravascular catheterization have led to modeling tool navigation approaches with data sensing and feedback, proper adaptation of image-based guidance for robotic navigation requires the development of sensitive segmentation and tracking models without specificity loss. Several methods have been developed to tackle non-uniform illumination, low contrast; however, presence of untargeted body organs commonly found in X-ray frames taken during angiography procedures still presents some major issues to be solved. In this study, a segmentation method was developed for automatic detection and tracking of guidewire pixels in X-ray angiograms. Image frames were acquired during robotic intravascular catheterization for cardiac interventions. For segmentation, multiscale enhancement filtering was applied on preprocessed X-ray angiograms, while morphological operations and filters were applied to refine the frames for pixel intensity adjustment and vesselness measurement. Minima and maxima extrema of the pixels were obtained to detect guidewire pixels in the X-ray frames. Lastly, morphological operation was applied for guidewire pixel connectivity and tracking in segmented pixels. Method validation was performed on 12 X-ray angiogram sequences which were acquired during in vivo intravascular catheterization trials in rabbits. The study outcomes showed that an overall accuracy of 0.995±0.001 was achieved for segmentation. Tracking performance was characterized with displacement and orientation errors observed as 1.938±2.429 mm and 0.039±0.040°, respectively. Evaluation studies performed against 9 existing methods revealed that this proposed method provides more accurate segmentation with 0.753±0.074 area under curve. Simultaneously, high tracking accuracy of 0.995±0.001 with low displacement and orientation errors of 1.938±2.429 mm and 0.039±0.040°, respectively, were achieved. Also, the method demonstrated higher sensitivity and specificity values compared to the 9 existing methods, with a relatively faster exaction time. The proposed method has the capability to enhance robotic intravascular catheterization during percutaneous coronary interventions (PCIs). Thus, interventionists can be provided with better tool tracking and visualization systems while also reducing their exposure to operational hazards during intravascular catheterization for cardiac interventions.

A shape-constraint adversarial framework with instance-normalized spatio-temporal features for inter-fetal membrane segmentation.

During Twin-to-Twin Transfusion Syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the fetuses. In the current practice, this syndrome is surgically treated by closing the abnormal connections using laser ablation. Surgeons commonly use the inter-fetal membrane as a reference. Limited field of view, low fetoscopic image quality and high inter-subject variability make the membrane identification a challenging task. However, currently available tools are not optimal for automatic membrane segmentation in fetoscopic videos, due to membrane texture homogeneity and high illumination variability. To tackle these challenges, we present a new deep-learning framework for inter-fetal membrane segmentation on in-vivo fetoscopic videos. The framework enhances existing architectures by (i) encoding a novel (instance-normalized) dense block, invariant to illumination changes, that extracts spatio-temporal features to enforce pixel connectivity in time, and (ii) relying on an adversarial training, which constrains macro appearance. We performed a comprehensive validation using 20 different videos (2000 frames) from 20 different surgeries, achieving a mean Dice Similarity Coefficient of 0.8780±0.1383. The proposed framework has great potential to positively impact the actual surgical practice for TTTS treatment, allowing the implementation of surgical guidance systems that can enhance context awareness and potentially lower the duration of the surgeries.