Unseen Subject Research Articles

Reading Challenges

The researcher of “Reading’ challenges” study focuses on extending the scope of slingshot of Reading. Whichever arise sentence, message, section and also novels and scenes and gaming “The researcher of this study focused on educating the people how to read and get Reading slag in practice learning and in education specifically. Reading must smash the fog of a theme writes. It really produces Reading slag and that slag all the rocks to bang into the unseen subject to make its existence felt and known. Poison darts and explosives must be fully aware and highly practiced to many trials and tribulations to get used of it. Reading has a positive effect of education to raise them into a great educated and knowledgeable y, and sagacious education in how life deals them in any situation, the primary source of research data shall be obtained through questionnaire, books, forums.

Dual Attention Relation Network With Fine-Tuning for Few-Shot EEG Motor Imagery Classification.

Recently, motor imagery (MI) electroencephalography (EEG) classification techniques using deep learning have shown improved performance over conventional techniques. However, improving the classification accuracy on unseen subjects is still challenging due to intersubject variability, scarcity of labeled unseen subject data, and low signal-to-noise ratio (SNR). In this context, we propose a novel two-way few-shot network able to efficiently learn how to learn representative features of unseen subject categories and classify them with limited MI EEG data. The pipeline includes an embedding module that learns feature representations from a set of signals, a temporal-attention module to emphasize important temporal features, an aggregation-attention module for key support signal discovery, and a relation module for final classification based on relation scores between a support set and a query signal. In addition to the unified learning of feature similarity and a few-shot classifier, our method can emphasize informative features in support data relevant to the query, which generalizes better on unseen subjects. Furthermore, we propose to fine-tune the model before testing by arbitrarily sampling a query signal from the provided support set to adapt to the distribution of the unseen subject. We evaluate our proposed method with three different embedding modules on cross-subject and cross-dataset classification tasks using brain-computer interface (BCI) competition IV 2a, 2b, and GIST datasets. Extensive experiments show that our model significantly improves over the baselines and outperforms existing few-shot approaches.

High-accuracy machine learning techniques for functional connectome fingerprinting and cognitive state decoding.

The human brain is a complex network comprised of functionally and anatomically interconnected brain regions. A growing number of studies have suggested that empirical estimates of brain networks may be useful for discovery of biomarkers of disease and cognitive state. A prerequisite for realizing this aim, however, is that brain networks also serve as reliable markers of an individual. Here, using Human Connectome Project data, we build upon recent studies examining brain-based fingerprints of individual subjects and cognitive states based on cognitively demanding tasks that assess, for example, working memory, theory of mind, and motor function. Our approach achieves accuracy of up to 99% for both identification of the subject of an fMRI scan, and for classification of the cognitive state of a previously unseen subject in a scan. More broadly, we explore the accuracy and reliability of five different machine learning techniques on subject fingerprinting and cognitive state decoding objectives, using functional connectivity data from fMRI scans of a high number of subjects (865) across a number of cognitive states (8). These results represent an advance on existing techniques for functional connectivity-based brain fingerprinting and state decoding. Additionally, 16 different functional connectome (FC) matrix construction pipelines are compared in order to characterize the effects of different aspects of the production of FCs on the accuracy of subject and task classification, and to identify possible confounds.

A novel approach for cross-subject unfavorable driving state detection by cooperation between phase-based functional connectivity and convolutional neural network

Driving under unfavorable driving state (UDS) is the primary factor inducing the soaring incidence of road accidents. Recently, Electroencephalography (EEG) with high time resolution is regarded as the “gold standard” for identifying drivers' UDS because it directly reflects the neural activity of human brain. However, EEG recordings are heavily influenced by individuals, resulting in poor generality and fair recognition performance on unseen subject. To handle the issue, an EEG-based cross-subject UDS detection framework is proposed, which combines model-driven and data-driven approaches. Concretely, EEG recordings collected from the driving simulation are first decomposed into six classical frequency bands. Interactive relation of all EEG channels is estimated by the phase transfer entropy (PTE). Subsequently, a novel meta-heuristic algorithm called equilibrium optimizer (EO) is employed as a PTE-based functional connectivity feature selection method. A customized 14-layer CNN model is further developed to extract hidden feature from PTE-EO-based functional connectivity and to perform UDS and NUDS classification tasks. Statistical analysis demonstrates that equilibrium optimizer significantly outperforms binary dragonfly algorithm (BDA) and whale optimization algorithm (WOA) in terms of UDS detection. The best recognition outcome is achieved using PTE-EO-CNN model, yielding a mean ACC of 90.19 %, a mean PRE of 89.20 %, a mean SEN of 91.75 %, and a mean SPE of 88.63 % on 16 subjects using LOSO-CV strategy. Conclusively, our findings suggest that PTE-EO-CNN is a promising framework with excellence reliability and generalizability, which has a new perspective and practical significance to solve the road safety issue.

Benchmarking framework for machine learning classification from fNIRS data.

While efforts to establish best practices with functional near infrared spectroscopy (fNIRS) signal processing have been published, there are still no community standards for applying machine learning to fNIRS data. Moreover, the lack of open source benchmarks and standard expectations for reporting means that published works often claim high generalisation capabilities, but with poor practices or missing details in the paper. These issues make it hard to evaluate the performance of models when it comes to choosing them for brain-computer interfaces. We present an open-source benchmarking framework, BenchNIRS, to establish a best practice machine learning methodology to evaluate models applied to fNIRS data, using five open access datasets for brain-computer interface (BCI) applications. The BenchNIRS framework, using a robust methodology with nested cross-validation, enables researchers to optimise models and evaluate them without bias. The framework also enables us to produce useful metrics and figures to detail the performance of new models for comparison. To demonstrate the utility of the framework, we present a benchmarking of six baseline models [linear discriminant analysis (LDA), support-vector machine (SVM), k-nearest neighbours (kNN), artificial neural network (ANN), convolutional neural network (CNN), and long short-term memory (LSTM)] on the five datasets and investigate the influence of different factors on the classification performance, including: number of training examples and size of the time window of each fNIRS sample used for classification. We also present results with a sliding window as opposed to simple classification of epochs, and with a personalised approach (within subject data classification) as opposed to a generalised approach (unseen subject data classification). Results show that the performance is typically lower than the scores often reported in literature, and without great differences between models, highlighting that predicting unseen data remains a difficult task. Our benchmarking framework provides future authors, who are achieving significant high classification scores, with a tool to demonstrate the advances in a comparable way. To complement our framework, we contribute a set of recommendations for methodology decisions and writing papers, when applying machine learning to fNIRS data.

Detection of Microsleep Events With a Behind-the-Ear Wearable System

Every year, the U.S. economy loses more than <inline-formula><tex-math notation="LaTeX">${\$}$</tex-math></inline-formula> 411 billion because of work performance reduction, injuries, and traffic accidents caused by microsleep. To mitigate microsleep's consequences, an unobtrusive, reliable, and socially acceptable microsleep detection solution throughout the day, every day is required. Unfortunately, existing solutions do not meet these requirements. In this paper, we propose WAKE, a novel behind-the-ear wearable device for microsleep detection. By monitoring biosignals from the brain, eye movements, facial muscle contractions, and sweat gland activities from behind the user's ears, WAKE can detect microsleep with a high temporal resolution. We introduce a Three-fold Cascaded Amplifying (3CA) technique to tame the motion artifacts and environmental noises for capturing high fidelity signals. Through our prototyping, we show that WAKE can suppress motion and environmental noise in real-time by 9.74-19.47 dB while walking, driving, or staying in different environments, ensuring that the biosignals are captured reliably. We evaluated WAKE using gold-standard devices on 19 sleep-deprived and narcoleptic subjects. The Leave-One-Subject-Out Cross-Validation results show the feasibility of WAKE in microsleep detection on an unseen subject with average precision and recall of 76 and 85 percent, respectively.

Inter-subject cognitive workload estimation based on a cascade ensemble of multilayer autoencoders

Machine learning approaches can build a computational model to predict cognitive workload levels by using electroencephalogram (EEG) feature inputs at the same time instant. However, when the EEG signals are recorded on different people, the accuracy of such a model could be impaired due to its incapability of fitting varied statistical distributions across different individuals. To this end, we propose an individual-independent workload estimator, a cascade ensemble of multilayer autoencoders to tackle the individual difference within the EEG features. It could assess the workload levels of an unseen subject by adapting the EEG data recorded from non-overlapped existing subjects. We first construct a deep stacked denoising autoencoder to abstract EEG features from a specific individual. Its shallow weights are optimized with individual-specific geometrical information of the features. Then, to find generalizable feature properties, we introduce Q-statistics to measure the independence between base learners. Finally, a regularized extreme learning machine is used as a cascade meta-classifier to fuse and filter high-level EEG abstractions and determine workload levels. We employ databases from two different experiments to validate our approach. The proposed framework can lead to acceptable accuracy and computational complexity compared to several existing workload classifiers.

Prototype-based Domain Generalization Framework for Subject-Independent Brain-Computer Interfaces.

Brain-computer interface (BCI) is challenging to use in practice due to the inter/intra-subject variability of electroencephalography (EEG). The BCI system, in general, necessitates a calibration technique to obtain subject/session-specific data in order to tune the model each time the system is utilized. This issue is acknowledged as a key hindrance to BCI, and a new strategy based on domain generalization has recently evolved to address it. In light of this, we've concentrated on developing an EEG classification framework that can be applied directly to data from unknown domains (i.e. subjects), using only data acquired from separate subjects previously. For this purpose, in this paper, we proposed a framework that employs the open-set recognition technique as an auxiliary task to learn subject-specific style features from the source dataset while helping the shared feature extractor with mapping the features of the unseen target dataset as a new unseen domain. Our aim is to impose cross-instance style in-variance in the same domain and reduce the open space risk on the potential unseen subject in order to improve the generalization ability of the shared feature extractor. Our experiments showed that using the domain information as an auxiliary network increases the generalization performance. Clinical relevance-This study suggests a strategy to improve the performance of the subject-independent BCI systems. Our framework can help to reduce the need for further calibration and can be utilized for a range of mental state monitoring tasks (e.g. neurofeedback, identification of epileptic seizures, and sleep disorders).

Facial Expressions Based Automatic Pain Assessment System

Pain assessment is used to improve patients’ treatment outcomes. Human observers may be influenced by personal factors, such as inexperience and medical organizations are facing a shortage of experts. In this study, we developed a facial expressions-based automatic pain assessment system (FEAPAS) to notify medical staff when a patient suffers pain by activating an alarm and recording the incident and pain level with the date and time. The model consists of two identical concurrent subsystems, each of which takes one of the two inputs of the model, i.e., “full face” and “the upper half of the same face”. The subsystems extract the relevant input features via two pre-trained convolutional neural networks (CNNs), using either VGG16, InceptionV3, ResNet50, or ResNeXt50, while freezing all convolutional blocks and replacing the classifier layer with a shallow CNN. The concatenated outputs in this stage is then sent to the model’s classifier. This approach mimics the human observer method and gives more importance to the upper part of the face, which is similar to the Prkachin and Soloman pain intensity (PSPI). Additionally, we further optimized our models by applying four optimizers (SGD/ADAM/RMSprop/RAdam) to each model and testing them on the UNBC-McMaster shoulder pain expression archive dataset to find the optimal combination, InceptionV3-SGD. The optimal model showed an accuracy of 99.10% on 10-fold cross-validation, thus outperforming the state-of-the-art model on the UNBC-McMaster database. It also scored 90.56% on unseen subject data. To speed up the system response time and reduce unnecessary alarms associated with temporary facial expressions, a select but effective subset of frames was inspected and classified. Two frame-selection criteria were reported. Classifying only two frames at the middle of 30-frame sequence was optimal, with an average reaction time of at most 6.49 s and the ability to avoid unnecessary alarms.

Population-based 3D respiratory motion modelling from convolutional autoencoders for 2D ultrasound-guided radiotherapy.

Radiotherapy is a widely used treatment modality for various types of cancers. A challenge for precise delivery of radiation to the treatment site is the management of internal motion caused by the patient's breathing, especially around abdominal organs such as the liver. Current image-guided radiation therapy (IGRT) solutions rely on ionising imaging modalities such as X-ray or CBCT, which do not allow real-time target tracking. Ultrasound imaging (US) on the other hand is relatively inexpensive, portable and non-ionising. Although 2D US can be acquired at a sufficient temporal frequency, it doesn't allow for target tracking in multiple planes, while 3D US acquisitions are not adapted for real-time. In this work, a novel deep learning-based motion modelling framework is presented for ultrasound IGRT. Our solution includes an image similarity-based rigid alignment module combined with a deep deformable motion model. Leveraging the representational capabilities of convolutional autoencoders, our deformable motion model associates complex 3D deformations with 2D surrogate US images through a common learned low dimensional representation. The model is trained on a variety of deformations and anatomies which enables it to generate the 3D motion experienced by the liver of a previously unseen subject. During inference, our framework only requires two pre-treatment 3D volumes of the liver at extreme breathing phases and a live 2D surrogate image representing the current state of the organ. In this study, the presented model is evaluated on a 3D+t US data set of 20 volunteers based on image similarity as well as anatomical target tracking performance. We report results that surpass comparable methodologies in both metric categories with a mean tracking error of 3.5±2.4mm, demonstrating the potential of this technique for IGRT.

Lighting-and Personal Characteristic-Aware Markov Random Field Model for Facial Image Relighting System

A learning-based image relighting framework is proposed for automatically changing the lighting conditions of facial images from one lighting source to another. Given only a 2D unseen facial testing image, the framework automatically infers the highlight or shadow areas in the relighted image in accordance with the specific facial characteristics of the input image using a learned non-parametric Markov random field model of the facial appearance correlation between the source and target lighting conditions. The proposed framework first decomposes the input image into its global and local components, where these components relate mainly to the lighting and detailed facial appearance characteristics of the image, respectively. The two components are then processed independently to ease the problem of insufficient training samples and to properly analyze the local contrast, overall lighting direction effects, and personal feature characteristics of the unseen subject. Specifically, the global and local components are processed by a lighting–aware classifier and a personal characteristic–aware classifier, respectively, in order to determine the semantic factors of the facial region. The semantic factors of the facial region are then used to update the Markov random field model of the facial appearance correlation between the source and target lighting conditions and to produce lighting enhancement matrices for the lighting components and facial characteristic components, respectively. Finally, the lighting enhancement matrices are applied to the original decomposition images, which are then integrated to obtain the final relighted result. The experimental results show that the proposed image relighting framework generates vivid and recognizable results despite the scarcity of training samples. Furthermore, the relighted results successfully simulate the individual lighting effects produced by the specific personal characteristics of the input image, such as the nose and cheek shadows. The effectiveness of the proposed framework is demonstrated by means of face verification tests, in which input images taken under side-lighting conditions are transformed to normal lighting conditions and are then matched with a dataset of ground truth images also taken under normal lighting conditions.

Unobtrusive patient identification using smart pill-bottle systems

Accurately accounting for medication use is important for the efficacy and safety of patients and family members. Monitoring is also important for medication adherence. This work investigates passive identification of persons taking medication using a sensor-equipped pill-bottle. The bottle is equipped with inertial and switch sensors in both the cap and body, making the added hardware unobtrusive, low-cost, and wireless. Our system uses inertial data to build a patient discrimination model using classification techniques. We evaluated the system using two datasets that we collected from 36 subjects. Our results show that using binary Support Vector Machine (SVM), the system can discriminate one individual among 3 people with > 90% accuracy and recall, and has > 80% accuracy and recall, using a single sensor. Using the same technique, our system has 85% accuracy and 72% recall for discriminating one subject in a population of 16. Identifying the exact person in a set of 3 subjects has an accuracy higher than 91%. We also show that we can infer the correct class for a previously unseen subject in a group of 3 subjects by using one-class SVM, with 75% average overall accuracy and 83% average recall.

Deep Convolutional and LSTM Networks on Multi-Channel Time Series Data for Gait Phase Recognition.

With an ageing society comes the increased prevalence of gait disorders. The restriction of mobility leads to a considerable reduction in the quality of life, because associated falls increase morbidity and mortality. Consideration of gait analysis data often alters surgical recommendations. For that reason, the early and systematic diagnostic treatment of gait disorders can spare a lot of suffering. As modern gait analysis systems are, in most cases, still very costly, many patients are not privileged enough to have access to comparable therapies. Low-cost systems such as inertial measurement units (IMUs) still pose major challenges, but offer possibilities for automatic real-time motion analysis. In this paper, we present a new approach to reliably detect human gait phases, using IMUs and machine learning methods. This approach should form the foundation of a new medical device to be used for gait analysis. A model is presented combining deep 2D-convolutional and LSTM networks to perform a classification task; it predicts the current gait phase with an accuracy of over 92% on an unseen subject, differentiating between five different phases. In the course of the paper, different approaches to optimize the performance of the model are presented and evaluated.

Deep relightable textures

The increasing demand for 3D content in augmented and virtual reality has motivated the development of volumetric performance capture systemsnsuch as the Light Stage. Recent advances are pushing free viewpoint relightable videos of dynamic human performances closer to photorealistic quality. However, despite significant efforts, these sophisticated systems are limited by reconstruction and rendering algorithms which do not fully model complex 3D structures and higher order light transport effects such as global illumination and sub-surface scattering. In this paper, we propose a system that combines traditional geometric pipelines with a neural rendering scheme to generate photorealistic renderings of dynamic performances under desired viewpoint and lighting. Our system leverages deep neural networks that model the classical rendering process to learn implicit features that represent the view-dependent appearance of the subject independent of the geometry layout, allowing for generalization to unseen subject poses and even novel subject identity. Detailed experiments and comparisons demonstrate the efficacy and versatility of our method to generate high-quality results, significantly outperforming the existing state-of-the-art solutions.

Subjective Evaluation of Performance in a Collaborative Task Is Better Predicted From Autonomic Response Than From True Achievements.

Whereas the fundamental role of the body in social cognition seems to be generally accepted, elucidating the bodily mechanisms associated with non-verbal communication and cooperation between two or more persons is still a challenging endeavor. In this article we propose a fresh approach for investigating the function of the autonomic nervous system that is reflected in parameters of heart rate variability, respiration, and electrodermal activity in a social setting. We analyzed autonomic parameters of dyads solving a target-tracking task together with the partner or individually. A machine classifier was trained to predict the subjects' rating of performance and collaboration either from tracking error data or from the set of autonomic parameters. When subjects collaborated, this classifier could predict the subjective performance ratings better from the autonomic response than from the objective performance of the subjects. However, when they solved the task individually, predictability from autonomic parameters dropped to the level of objective performance, indicating that subjects were more rational in rating their performance in this condition. Moreover, the model captured general knowledge about the population that allows it to predict the performance ratings of an unseen subject significantly better than chance. Our results suggest that, in particular in situations that require collaboration with others, evaluation of performance is shaped by the bodily processes that are quantified by autonomic parameters. Therefore, subjective performance assessments appear to be modulated not only by the output of a rational or discriminative system that tracks the objective performance but to a significant extent also by interoceptive processes.

Recurrence quantification analysis of resting state EEG signals in autism spectrum disorder \u2013 a systematic methodological exploration of technical and demographic confounders in the search for biomarkers

BackgroundAutism spectrum disorder (ASD) is a neurodevelopmental disorder with a worldwide prevalence of 1–2%. In low-resource environments, in particular, early identification and diagnosis is a significant challenge. Therefore, there is a great demand for ‘language-free, culturally fair’ low-cost screening tools for ASD that do not require highly trained professionals. Electroencephalography (EEG) has seen growing interest as an investigational tool for biomarker development in ASD and neurodevelopmental disorders. One of the key challenges is the identification of appropriate multivariate, next-generation analytical methodologies that can characterise the complex, nonlinear dynamics of neural networks in the brain, mindful of technical and demographic confounders that may influence biomarker findings. The aim of this study was to evaluate the robustness of recurrence quantification analysis (RQA) as a potential biomarker for ASD using a systematic methodological exploration of a range of potential technical and demographic confounders.MethodsRQA feature extraction was performed on continuous 5-second segments of resting state EEG (rsEEG) data and linear and nonlinear classifiers were tested. Data analysis progressed from a full sample of 16 ASD and 46 typically developing (TD) individuals (age 0–18 years, 4802 EEG segments), to a subsample of 16 ASD and 19 TD children (age 0–6 years, 1874 segments), to an age-matched sample of 7 ASD and 7 TD children (age 2–6 years, 666 segments) to prevent sample bias and to avoid misinterpretation of the classification results attributable to technical and demographic confounders. A clinical scenario of diagnosing an unseen subject was simulated using a leave-one-subject-out classification approach.ResultsIn the age-matched sample, leave-one-subject-out classification with a nonlinear support vector machine classifier showed 92.9% accuracy, 100% sensitivity and 85.7% specificity in differentiating ASD from TD. Age, sex, intellectual ability and the number of training and test segments per group were identified as possible demographic and technical confounders. Consistent repeatability, i.e. the correct identification of all segments per subject, was found to be a challenge.ConclusionsRQA of rsEEG was an accurate classifier of ASD in an age-matched sample, suggesting the potential of this approach for global screening in ASD. However, this study also showed experimentally how a range of technical challenges and demographic confounders can skew results, and highlights the importance of probing for these in future studies. We recommend validation of this methodology in a large and well-matched sample of infants and children, preferably in a low- and middle-income setting.

Woke-ish

Woke-ish Allyson Nadia Field (bio) For Glamour's celebration of International Day of the Girl on October 11, 2017, television star and Harvard freshman Yara Shahidi wore a sweatshirt by the clothing brand HSTRY, co-founded by Kiran Goraya and Nas (celebrated rapper and Shahidi's cousin).1 She posted a photo taken against the event's publicity banner on Instagram, as did her stylist, Jason Bolden, who tagged it "When Ur #Glamour Is Woke!!!"2 The idea of woke style was picked up by Channing Hargrove on Refinery 29, who called Shahidi's top a "woke sweatshirt."3 A week earlier, Vanessa Friedman had asked the readers of the New York Times, "What Does a 'Woke Woman' Wear?" in her (under-whelmed) review of Paris Fashion Week (Spring 2018 Ready-to-Wear).4 Bolden and Shahidi could be seen as answering this query, at least offering a model of what one actress/activist would wear. The $38 sweatshirt displays a graphic of two Black women's faces in adjacent blue color-blocks. One face looks upward aspirationally, while its twin holds a knife and menaces an unseen subject. The lines "respect existence" and "or expect resistance" frame the color blocks, aligning "resistance" with the second figure. Shahidi's stylist paired the sweatshirt with a bright red angora-blend skirt patterned with contrast turquoise bead embroidery of a grain motif from Prada's Fall 2017 collection ($3,390.00). If the sweatshirt connoted wokeness, its pairing with the skirt suggested woke glamour. Click for larger view View full resolution Figure 1. Photo of Yara Shahidi wearing a HSTRY sweatshirt (October 11, 2017). Photo by Craig Barritt, permission of Getty Images. As Sarah Mower noted in Vogue, the collection recalls Miuccia Prada's student days when she [End Page 217] was "wrapped up for a time in the left-wing Italian politics of the '70s," for the collection draws from the past both in its style and staging, as the movie posters that adorned the Fall 2017 Ready-to-Wear runway show suggested. For instance, a poster at the mouth of the runway declared, "We have decided to look at the role women had in the shaping of modern society, their political participation and social achievements." To the Vogue reporter, Prada merely said, "I don't want to be political. Not officially political. […] I have to … sneak it in."5 Prada escalated this commitment with the Spring 2018 collection. This collection also was covered by Mower for Vogue, and she opened her review of the show with the exhortation, "The time has come to put away bourgeois, girly playthings and get militant." Prada's political ambitions were aligned with, and perhaps more successful than, those of the other houses, whose Paris Fashion Week debuts left Friedman uninspired. As Mower noted, "These Prada riot girls were in sync with the 'woke' generation's sensibilities."6 Prada might be the woke luxe couturier of the moment, though the house has a long history of anti-snobbery design (if not corresponding commercial practice). The pairing of the red angora skirt with the HSTRY sweatshirt makes a certain degree of sense in relation to this history. But what is this outfit actually conveying? The skirt, in combination with Shahidi's polished look (makeup, jewelry, beige heels), softens the wokeness of the ensemble, making it more accessible for consumption (as the publicity backdrop labeled with Glamour, Condé Nast, and Maybelline likewise brand her appearance). But we could think about this outfit further. The botanical design evoking a staple crop seems at odds with the sweatshirt's assertive appeal. Aesthetically, the turquoise beading riffs on the sweatshirt's blue color blocks and the bright red skirt underscores—literally—the aggressive visage of the "or expect resistance" figure. But considering the agrarian allusion of the skirt, its price-point and juxtaposition with the sweatshirt seem grotesque. The high/low contrast of the pairing is troubled by the reference to agrarian life—and thereby to labor. Further, the slogan "respect existence or expect resistance" has long been invoked by labor movements. Shahidi's outfit prompts one to ask, "Is woke glamour resistance or collusion?" Or does it instead...

Non-rigid free-form 2D–3D registration using a B-spline-based statistical deformation model

This paper presents a non-rigid free-from 2D–3D registration approach using a B-spline-based statistical deformation model (SDM). In our approach the B-spline-based SDM is first constructed from a set of training data using a non-rigid registration algorithm based on B-spline free-form deformation to encode a priori information about the underlying anatomy. A novel intensity-based non-rigid 2D–3D registration algorithm is then presented to iteratively fit the 3D B-spline-based SDM to the 2D X-ray images of an unseen subject, which requires a computationally expensive inversion of the instantiated deformation in each iteration. In this paper, we propose to solve this challenge with a fast 3D B-spline pseudo-inversion algorithm that is implemented on graphics processing unit (GPU). Comprehensive experiments on simulated images of patient data sets, on calibrated C-arm and on X-ray images of cadaveric femurs are designed and conducted to evaluate the performance of the proposed approach. The experimental results demonstrate the efficacy of the present approach.

Face model fitting on video sequences based on incremental virtual active appearance model

It has been proved that the performance of a person-specific active appearance model (AAM) built to model the appearance variation of a single person across pose, illumination, and expression is substantially better than the performance of a generic AAM built to model the appearance variation of many faces. However, it is not practical to build a personal AAM before tracking an unseen subject. A virtual person-specific AAM is proposed to tackle the problem. The AAM is constructed from a set of virtual personal images with different poses and expressions which are synthesized from the annotated first frame via regressions. To preserve personal facial details on the virtual images, a poison fusion strategy is designed and applied to the virtual facial images generated via bilinear kernel ridge regression. Furthermore, the AAM subspace is sequentially updated during tracking based on sequential Karhunen---Loeve algorithm, which helps the AAM adaptive to the facial context variation. Experiments show the proposed virtual personal AAM is robust to facial context changes during tracking, and outperforms other state-of-the-art AAM on facial feature tracking accuracy and computation cost.

Personalising population-based respiratory motion models of the heart using neighbourhood approximation based on learnt anatomical features.

Respiratory motion models have been proposed for the estimation and compensation of respiratory motion during image acquisition and image-guided interventions on organs in the chest and abdomen. However, such techniques are not commonly used in the clinic. Subject-specific motion models require a dynamic calibration scan that interrupts the clinical workflow and is often impractical to acquire, while population-based motion models are not as accurate as subject-specific motion models. To address this lack of accuracy, we propose a novel personalisation framework for population-based respiratory motion models and demonstrate its application to respiratory motion of the heart. The proposed method selects a subset of the population sample which is more likely to represent the cardiac respiratory motion of an unseen subject, thus providing a more accurate motion model. The selection is based only on anatomical features of the heart extracted from a static image. The features used are learnt using a neighbourhood approximation technique from a set of training datasets for which respiratory motion estimates are available. Results on a population sample of 28 adult healthy volunteers show average improvements in estimation accuracy of 20% compared to a standard population-based motion model, with an average value for the 50th and 95th quantiles of the estimation error of 1.6mm and 4.7 mm respectively. Furthermore, the anatomical features of the heart most strongly correlated to respiratory motion are investigated for the first time, showing the features on the apex in proximity to the diaphragm and the rib cage, on the left ventricle and interventricular septum to be good predictors of the similarity in cardiac respiratory motion.