Synthetic Domain Research Articles

A partitioning Monte Carlo approach for consensus tasks in crowdsourcing

The planner’s role in crowdsourcing involves determining the time to stop collecting information (i.e., timed decision, TD). Previous studies have modeled the uncertain crowdsourcing environment as Partially Observable Markov Decision Processes (POMDPs) and utilized the value of information (VOI) to balance the utilities and costs of information collection. However, there is still room for optimization in solving the TD problem within single-agent POMDPs. In this paper, we propose a partitioning Monte Carlo approach for consensus tasks based on the option-candidate (OC) model partitioning. We simplify the state representation for the OC model and introduce a multi-agent POMDP representation. We establish a correspondence between the single-agent and multi-agent models using two consistency theorems. We propose three progressively improved partitioning Monte Carlo (PMC) algorithms to solve the TD problem within the multi-agent POMDP. We conducted experiments in synthetic domains and a citizen science project, demonstrating that the proposed algorithms exhibit continuous improvements in runtime advantages and consistently outperform the SOTA single-agent Monte Carlo sampling-based algorithm while providing nearly consistent output results.

Domain adaptation strategies for 3D reconstruction of the lumbar spine using real fluoroscopy data

In this study, we address critical barriers hindering the widespread adoption of surgical navigation in orthopedic surgeries due to limitations such as time constraints, cost implications, radiation concerns, and integration within the surgical workflow. Recently, our work X23D showed an approach for generating 3D anatomical models of the spine from only a few intraoperative fluoroscopic images. This approach negates the need for conventional registration-based surgical navigation by creating a direct intraoperative 3D reconstruction of the anatomy. Despite these strides, the practical application of X23D has been limited by a significant domain gap between synthetic training data and real intraoperative images.In response, we devised a novel data collection protocol to assemble a paired dataset consisting of synthetic and real fluoroscopic images captured from identical perspectives. Leveraging this unique dataset, we refined our deep learning model through transfer learning, effectively bridging the domain gap between synthetic and real X-ray data. We introduce an innovative approach combining style transfer with the curated paired dataset. This method transforms real X-ray images into the synthetic domain, enabling the in-silico-trained X23D model to achieve high accuracy in real-world settings.Our results demonstrated that the refined model can rapidly generate accurate 3D reconstructions of the entire lumbar spine from as few as three intraoperative fluoroscopic shots. The enhanced model reached a sufficient accuracy, achieving an 84% F1 score, equating to the benchmark set solely by synthetic data in previous research. Moreover, with an impressive computational time of just 81.1 ms, our approach offers real-time capabilities, vital for successful integration into active surgical procedures.By investigating optimal imaging setups and view angle dependencies, we have further validated the practicality and reliability of our system in a clinical environment. Our research represents a promising advancement in intraoperative 3D reconstruction. This innovation has the potential to enhance intraoperative surgical planning, navigation, and surgical robotics.

Examining the emergence of the ‘AI eye’ and its effect on the ‘creative treatment of actuality’ in computational non-fiction

ABSTRACT Documentaries have frequently captured journeys to places audiences might not have seen before. The first documentary film Nanook of the North (1922), often referred to as a travel film, took viewers to the Canadian Artic for the first time. In 1929, The Man with a Movie Camera revealed the rhythm of the Soviet cities through the Kino-Eye. Now the documentary film genre, the City Film is taking viewers on a virtual tour into new digital synthetic domains as they contain artificially generated images produced by GenAI. In response to this emergence of the ‘AI eye’, a computational vision of the world, the following attributes of AI as an asset, tool and collaborator shape the discussion of novel creative documentary processes that are emerging when Gen AI is integrated into computational non-fiction. This article explores a computational vision of the world in relation to the City Film documentary genre.

De novo DNA-based catch bonds.

All primary chemical interactions weaken under mechanical stress, which imposes fundamental mechanical limits on the materials constructed from them. Biological materials combine plasticity with strength, for which nature has evolved a unique solution-catch bonds, supramolecular interactions that strengthen under tension. Biological catch bonds use force-gated conformational switches to convert weak bonds into strong ones. So far, catch bonds remain exclusive to nature, leaving their potential as mechanoadaptive elements in synthetic systems untapped. Here we report the design and realization of artificial catch bonds. Starting from a minimal set of thermodynamic design requirements, we created a molecular motif capable of catch bonding. It consists of a DNA duplex featuring a cryptic domain that unfolds under tension to strengthen the interaction. We show that these catch bonds recreate force-enhanced rolling adhesion, a hallmark feature of biological catch bonds in bacteria and leukocytes. This Article introduces catch bonds into the synthetic domain, and could lead to the creation of artificial catch-bonded materials.

Controlled Supramolecular Polymerization via Bioinspired, Liquid-Liquid Phase Separation of Monomers.

Dynamic supramolecular assemblies, driven by noncovalent interactions, pervade the biological realm. In the synthetic domain, their counterparts, supramolecular polymers, endowed with remarkable self-repair and adaptive traits, are often realized through bioinspired designs. Recently, controlled supramolecular polymerization strategies have emerged, drawing inspiration from protein self-assembly. A burgeoning area of research involves mimicking the liquid-liquid phase separation (LLPS) observed in proteins to create coacervate droplets and recognizing their significance in cellular organization and diverse functions. Herein, we introduce a novel perspective on synthetic coacervates, extending beyond their established role in synthetic biology as dynamic, membraneless phases to enable structural control in synthetic supramolecular polymers. Drawing parallels with the cooperative growth of amyloid fibrils through LLPS, we present metastable coacervate droplets as dormant monomer phases for controlled supramolecular polymerization. This is achieved via a π-conjugated monomer design that combines structural characteristics for both coacervation through its terminal ionic groups and one-dimensional growth via a π-conjugated core. This design leads to a unique temporal LLPS, resulting in a metastable coacervate phase, which subsequently undergoes one-dimensional growth via nucleation within the droplets. In-depth spectroscopic and microscopic characterization provides insights into the temporal evolution of disordered and ordered phases. Furthermore, to modulate the kinetics of liquid-to-solid transformation and to achieve precise control over the structural characteristics of the resulting supramolecular polymers, we invoke seeding in the droplets, showcasing living growth characteristics. Our work thus opens up new avenues in the exciting field of supramolecular polymerization, offering general design principles and controlled synthesis of precision self-assembled structures in confined environments.

Synthetic imputation methods for domain mean under simple random sampling

The estimation of domain mean in presence of missing data is a significant issue in sample surveys. Literature contains no imputation method to estimate the domain mean in the presence of missing data using bivariate auxiliary information. The present study uses simple random sampling to propose several novel synthetic domain mean imputation methods and the corresponding resulting estimators based on bivariate auxiliary information in the case of missing data. To evaluate how well the suggested novel imputation methods and the resulting estimators perform, the mathematical equation of mean square errors is derived. A thorough simulation experiment is also carried out using a population drawn artificially from a normal distribution. Furthermore, an application is also offered based on real data.

A parallel programming application of the A* algorithm in digital rock physics

Pore-scale analysis and characterization of reservoir rocks provide valuable information for the definition and management of underground hydrogen storage and CO2 storage or sequestration.This article presents an optimized implementation of the A* algorithm, the most popular pathfinding method in the presence of obstacles. In this context, the algorithm is applied to recognize the minimum length connected paths through each flow direction of 3D images of a porous medium representative of a reservoir rock. The identification of the main paths allows the characterization of the pore space and the calculation of fundamental petrophysical properties such as tortuosity and effective porosity, which can be used for permeability estimation. Compared to other algorithms available for pore-scale characterization, such as the pore centroid, A* provides a better approximation of the pore space available for the flow and, therefore, a reliable characterization of the petrophysical properties. On the other hand, path identification is significantly consuming in terms of time and memory. In this paper, an efficient and optimized implementation based on C++/OpenMP programming language is presented.The proposed implementation aims to the analysis of large-scale models profiting from parallelization, memory optimization, and enhanced managing of dead paths. Three test cases of increasing sizes are presented, to analyze the advantages and the disadvantages of the algorithm as the number of explored points increases. The 3D binary images analyzed are related to a synthetic domain (1 million voxels) and two actual sandstone samples (about 4 and 64 million voxels respectively). The code is validated against a Matlab serial implementation, showing a significant improvement in efficiency. Remarkable test cases of several millions of voxels were afforded, overcoming the memory and execution slowness issues. Moreover, the proposed implementation is suitable for large pore-scale models run in HPC environments.

Class-conditional domain adaptation for semantic segmentation

Semantic segmentation is an important sub-task for many applications. However, pixel-level ground-truth labeling is costly, and there is a tendency to overfit to training data, thereby limiting the generalization ability. Unsupervised domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain (including less expensive synthetic domain) to be adapted to a novel target domain. The conventional approach involves automatic extraction and alignment of the representations of source and target domains globally. One limitation of this approach is that it tends to neglect the differences between classes: representations of certain classes can be more easily extracted and aligned between the source and target domains than others, limiting the adaptation over all classes. Here, we address this problem by introducing a Class-Conditional Domain Adaptation (CCDA) method. This incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and adaptation. Together, they measure the segmentation, shift the domain in a class-conditional manner, and equalize the loss over classes. Experimental results demonstrate that the performance of our CCDA method matches, and in some cases, surpasses that of state-of-the-art methods.

FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems

This article presents FRCSyn-onGoing, an ongoing challenge for face recognition where researchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases and standard experimental protocols. FRCSyn-onGoing is based on the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at WACV 2024. This is the first face recognition international challenge aiming to explore the use of real and synthetic data independently, and also their fusion, in order to address existing limitations in the technology. Specifically, FRCSyn-onGoing targets concerns related to data privacy issues, demographic biases, generalization to unseen scenarios, and performance limitations in challenging scenarios, including significant age disparities between enrollment and testing, pose variations, and occlusions. To enhance face recognition performance, FRCSyn-onGoing strongly advocates for information fusion at various levels, starting from the input data, where a mix of real and synthetic domains is proposed for specific tasks of the challenge. Additionally, participating teams are allowed to fuse diverse networks within their proposed systems to improve the performance. In this article, we provide a comprehensive evaluation of the face recognition systems and results achieved so far in FRCSyn-onGoing. The results obtained in FRCSyn-onGoing, together with the proposed public ongoing benchmark, contribute significantly to the application of synthetic data to improve face recognition technology.

Advancing Carbon Fiber Composite Inspection: Deep Learning-Enabled Defect Localization and Sizing via 3-D U-Net Segmentation of Ultrasonic Data.

In nondestructive evaluation (NDE), accurately characterizing defects within components relies on accurate sizing and localization to evaluate the severity or criticality of defects. This study presents for the first time a deep learning (DL) methodology using 3-D U-Net to localize and size defects in carbon fiber reinforced polymer (CFRP) composites through volumetric segmentation of ultrasonic testing (UT) data. Using a previously developed approach, synthetic training data, closely representative of experimental data, was used for the automatic generation of ground truth segmentation masks. The model's performance was compared to the conventional amplitude 6 dB drop analysis method used in the industry against ultrasonic defect responses from 40 defects fabricated in CFRP components. The results showed good agreement with the 6 dB drop method for in-plane localization and excellent through-thickness localization, with mean absolute errors (MAEs) of 0.57 and 0.08 mm, respectively. Initial sizing results consistently oversized defects with a 55% higher mean average error than the 6 dB drop method. However, when a correction factor was applied to account for variation between the experimental and synthetic domains, the final sizing accuracy resulted in a 35% reduction in MAE compared to the 6 dB drop technique. By working with volumetric ultrasonic data (as opposed to 2-D images), this approach reduces preprocessing (such as signal gating) and allows for the generation of 3-D defect masks which can be used for the generation of computer-aided design files; greatly reducing the qualification reporting burden of NDE operators.

Supervised Bayesian specification inference from demonstrations

When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of a task’s execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring specifications, with over 90% similarity observed between the inferred specification and the ground truth—both within a synthetic domain and during a real-world table setting task.

DUA: A Domain-Unified Approach for Cross-Dataset 3D Human Pose Estimation.

Human pose estimation is an important Computer Vision problem, whose goal is to estimate the human body through joints. Currently, methods that employ deep learning techniques excel in the task of 2D human pose estimation. However, the use of 3D poses can bring more accurate and robust results. Since 3D pose labels can only be acquired in restricted scenarios, fully convolutional methods tend to perform poorly on the task. One strategy to solve this problem is to use 2D pose estimators, to estimate 3D poses in two steps using 2D pose inputs. Due to database acquisition constraints, the performance improvement of this strategy can only be observed in controlled environments, therefore domain adaptation techniques can be used to increase the generalization capability of the system by inserting information from synthetic domains. In this work, we propose a novel method called Domain Unified approach, aimed at solving pose misalignment problems on a cross-dataset scenario, through a combination of three modules on top of the pose estimator: pose converter, uncertainty estimator, and domain classifier. Our method led to a 44.1mm (29.24%) error reduction, when training with the SURREAL synthetic dataset and evaluating with Human3.6M over a no-adaption scenario, achieving state-of-the-art performance.

Allelic compatibility in plant immune receptors facilitates engineering of new effector recognition specificities.

Engineering the plant immune system offers genetic solutions to mitigate crop diseases caused by diverse agriculturally significant pathogens and pests. Modification of intracellular plant immune receptors of the nucleotide-binding leucine-rich repeat (NLR) receptor superfamily for expanded recognition of pathogen virulence proteins (effectors) is a promising approach for engineering disease resistance. However, engineering can cause NLR autoactivation, resulting in constitutive defense responses that are deleterious to the plant. This may be due to plant NLRs associating in highly complex signaling networks that coevolve together, and changes through breeding or genetic modification can generate incompatible combinations, resulting in autoimmune phenotypes. The sensor and helper NLRs of the rice (Oryza sativa) NLR pair Pik have coevolved, and mismatching between noncoevolved alleles triggers constitutive activation and cell death. This limits the extent to which protein modifications can be used to engineer pathogen recognition and enhance disease resistance mediated by these NLRs. Here, we dissected incompatibility determinants in the Pik pair in Nicotiana benthamiana and found that heavy metal-associated (HMA) domains integrated in Pik-1 not only evolved to bind pathogen effectors but also likely coevolved with other NLR domains to maintain immune homeostasis. This explains why changes in integrated domains can lead to autoactivation. We then used this knowledge to facilitate engineering of new effector recognition specificities, overcoming initial autoimmune penalties. We show that by mismatching alleles of the rice sensor and helper NLRs Pik-1 and Pik-2, we can enable the integration of synthetic domains with novel and enhanced recognition specificities. Taken together, our results reveal a strategy for engineering NLRs, which has the potential to allow an expanded set of integrations and therefore new disease resistance specificities in plants.

Visual transformer with stable prior and patch-level attention for single image dehazing

Single-image dehazing aims to recover blurred image details and improve image quality, which is a challenging ill-posed problem due to severe information degradation. In the image dehazing task, extracting local features from adjacent regions is particularly important. However, Transformer-based methods lack relative awareness of patch-level features. Furthermore, due to the sensitivity of self-attention to textcolorreddata distribution, the model suffers severe performance degradation when migrating from synthetic domain to real domain. To alleviate the above problems, we propose visual transformer with stable prior and patch-level attention (VSPPA) for image dehazing. Firstly, we propose a region-aware patch-level attention module to obtain the positional correlation between local patches and contexts, which can enhance the concentration of local patch-related features. Next, due to the instability problem caused by distribution shifts, we introduce dataset-independent prior to guide the transformer model, thereby preventing feature drift thus to improve the robustness of the model. Finally, domain-drift leads to insufficient dehazing when the model trained on synthetic data while migrates to the real environment, we come up with a introduce a patch filling strategy (PFS) for fuzzy data to narrow the domain gap and realize the generalization in real scenes. Extensive experiments show that the model achieves State-of-the-Art on the SOTS synthetic dataset and effective generalization to real-world scenarios.

Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation

This paper introduces an adaptive Convolutional Neural Network (CNN)-based Unscented Kalman Filter for the pose estimation of uncooperative spacecraft. The validation is carried out at Stanford’s robotic Testbed for Rendezvous and Optical Navigation on the Satellite Hardware-In-the-loop Rendezvous Trajectories (SHIRT) dataset, which simulates vision-based rendezvous trajectories of a servicer spacecraft to PRISMA’s Tango spacecraft. The proposed navigation system is stress-tested on synthetic as well as realistic lab imagery by simulating space-like illumination conditions on-ground. The validation is performed at different levels of the navigation system by first training and testing the adopted CNN on SPEED+, Stanford’s spacecraft pose estimation dataset with specific emphasis on domain shift between a synthetic domain and an Hardware-In-the-Loop domain. A novel data augmentation scheme based on light randomization is proposed to improve the CNN robustness under adverse viewing conditions, reaching centimeter-level and 10 degree-level pose errors in 80% of the SPEED+ lab images. Next, the entire navigation system is tested on the SHIRT dataset. Results indicate that the inclusion of a new scheme to adaptively scale the heatmaps-based measurement error covariance based on filter innovations improves filter robustness by returning centimeter-level position errors and moderate attitude accuracies, suggesting that a proper representation of the measurements uncertainty combined with an adaptive measurement error covariance is key in improving the navigation robustness.

UAVStereo: A Multiple Resolution Dataset for Stereo Matching in UAV Scenarios

Stereo matching is a fundamental task in three-dimensional scene reconstruction. Recently, deep learning-based methods have proven effective on some benchmark datasets, such as KITTI and SceneFlow. Unmanned aerial vehicles (UAVs) are commonly used for surface observation, and the images captured are frequently used for detailed 3D reconstruction because of their high resolution and low-altitude acquisition. Currently, mainstream supervised learning networks require a significant amount of training data with ground-truth labels to learn model parameters. However, owing to the scarcity of UAV stereo-matching datasets, learning-based stereo matching methods in UAV scenarios is not fully investigated yet. To facilitate further research, this study proposes a pipeline for generating accurate and dense disparity maps using detailed meshes reconstructed based on UAV images and LiDAR point clouds. Through the proposed pipeline, we constructed a multi-resolution UAV scenario dataset called UAVStereo, with over 34,000 stereo image pairs covering three typical scenes. To the best of our knowledge, UAVStereo is the first stereo matching dataset for UAV low-altitude scenarios. The dataset includes synthetic and real stereo pairs to enable generalization from the synthetic domain to the real domain. Furthermore, our UAVStereo dataset provides multi-resolution and multi-scene image pairs to accommodate various sensors and environments. In this study, we evaluated traditional and state-of-the-art deep learning methods, highlighting their limitations in addressing challenges in UAV scenarios and offering suggestions for future research. Our dataset is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/rebecca0011/UAVStereo.git.</uri>

Learning Generalized Knowledge From a Single Domain on Urban-Scene Segmentation

Deep neural networks have made significant progress in various tasks under the assumption of the same distribution between training and testing data. However, the obtained domain-specific knowledge often suffers from performance degradation when facing out-of-distribution data. Towards addressing the degradation, a critical requirement of such networks is the generalization capability to unseen domains, which is the goal of domain generalization (DG). This paper attempts to learn generalized knowledge from a single synthetic domain and then apply it to real and unknown scenarios. Specifically, we propose a contour-aware instance normalization module to effectively learn domain-invariant features via a novel weight-updating strategy, which can largely exploit the generalized information from the observed data. In addition, a category-level contrastive learning mechanism is proposed through understanding the semantic discrepancy and relevance among samples to mitigate the interference of domain-specific features on classification. Extensive experiments together with ablation studies on widely-adopted datasets are conducted to demonstrate the effectiveness of our design and show the superiority of our method over other state-of-the-art schemes on the task of urban-scene segmentation. The source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/leelxh/DG-LGK</uri> .

GridDehazeNet+: An Enhanced Multi-Scale Network With Intra-Task Knowledge Transfer for Single Image Dehazing

Adverse weather conditions such as haze can deteriorate the performance of autonomous driving and intelligent transport systems. As a potential remedy, we propose an enhanced multi-scale network, dubbed GridDehazeNet+, for single image dehazing. The proposed dehazing method does not rely on the Atmosphere Scattering Model (ASM), and an explanation as to why it is not necessarily performing the dimension reduction offered by this model is provided. GridDehazeNet+ consists of three modules: pre-processing, backbone, and post-processing. The trainable pre-processing module can generate learned inputs with better diversity and more pertinent features as compared to those derived inputs produced by hand-selected pre-processing methods. The backbone module implements multi-scale estimation with two major enhancements: 1) a novel grid structure that effectively alleviates the bottleneck issue via dense connections across different scales; 2) a spatial-channel attention block that can facilitate adaptive fusion by consolidating dehazing-relevant features. The post-processing module helps to reduce the artifacts in the final output. Due to domain shift, the model trained on synthetic data may not generalize well on real data. To address this issue, we shape the distribution of synthetic data to match that of real data, and use the resulting translated data to finetune our network. We also propose a novel intra-task knowledge transfer mechanism that can memorize and take advantage of synthetic domain knowledge to assist the learning process on the translated data. Experimental results demonstrate that the proposed method outperforms the state-of-the-art on several synthetic dehazing datasets, and achieves the superior performance on real-world hazy images after finetuning.

Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data

Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground-truth annotations for depth completion settings can be difficult and, at the same time, a significant domain gap between real LiDAR measurements and synthetic data has prevented from successful training of models in virtual settings. We propose a domain adaptation approach for sparse-to-dense depth completion that is trained from synthetic data, without annotations in the real domain or additional sensors. Our approach simulates the real sensor noise in an RGB + LiDAR set-up, and consists of three modules: simulating the real LiDAR input in the synthetic domain via projections, filtering the real noisy LiDAR for supervision and adapting the synthetic RGB image using a CycleGAN approach. We extensively evaluate these modules in the KITTI depth completion benchmark.

C2 -GAN: Content-consistent generative adversarial networks for unsupervised domain adaptation in medical image segmentation.

In clinical practice, medical image analysis has played a key role in disease diagnosis. One of the important steps is to perform an accurate organ or tissue segmentation for assisting medical professionals in making correct diagnoses. Despite the tremendous progress in the deep learning-based medical image segmentation approaches, they often fail to generalize to test datasets due to distribution discrepancies across domains. Recent advances aligning the domain gaps by using bi-directional GANs (e.g., CycleGAN) have shown promising results, but the strict constraints of the cycle consistency hamper these methods from yielding better performance. The purpose of this study is to propose a novel bi-directional GAN-based segmentation model with fewer constraints on the cycle consistency to improve the generalized segmentationresults. We propose a novel unsupervised domain adaptation approach by designing content-consistent generative adversarial networks ( ) for medical image segmentation. First, we introduce content consistency instead of cycle consistency to relax the constraint of the invertibility map to encourage the synthetic domain generated with a large domain transportation distance. The synthetic domain is thus pulled close to the target domain for the reduction of domain discrepancy. Second, we suggest a novel style transfer loss based on the difference in low-frequency magnitude to further mitigate the appearance shifts acrossdomains. We validate our proposed approach on three public X-ray datasets, including the Montgomery, JSRT, and Shenzhen datasets. For an accurate evaluation, we randomly divided the images of each dataset into 70% for training, 10% for evaluation, and 20% for testing. The mean Dice was 95.73 ± 0.22%, 95.16 ± 1.42% for JSRT and Shenzhen datasets, respectively. For the recall and precision metrics, our model also achieved better or comparable performance than the state-of-the-art CycleGAN-based UDAapproaches. The experimental results validate the effectiveness of our method in mitigating the domain gaps and improving generalized segmentation results for X-ray imagesegmentation.