Search

With the increasing interest in the content creation field in multiple sectors such as media, education, and entertainment, there is an increased trend in the papers that use AI algorithms to generate content such as images, videos, audio, and text. Generative Adversarial Networks (GANs) is one of the promising models that synthesizes data samples that are similar to real data samples. While the variations of GANs models in general have been covered to some extent in several survey papers, to the best of our knowledge, this is the first paper that reviews the state-of-the-art video GANs models. This paper first categorizes GANs review papers into general GANs review papers, image GANs review papers, and special field GANs review papers such as anomaly detection, medical imaging, or cybersecurity. The paper then summarizes the main improvements in GANs that are not necessarily applied in the video domain in the first run but have been adopted in multiple video GANs variations. Then, a comprehensive review of video GANs models are provided under two main divisions based on existence of a condition. The conditional models are then further classified according to the provided condition into audio, text, video, and image. The paper concludes with the main challenges and limitations of the current video GANs models. [ABSTRACT FROM AUTHOR]

Due to progression in cell-cycle or duration of storage, classification of morphological changes in human blood cells is important for correct and effective clinical decisions. Automated classification systems help avoid subjective outcomes and are more efficient. Deep learning and more specifically Convolutional Neural Networks have achieved state-of-the-art performance on various biomedical image classification problems. However, real-world data often suffers from the data imbalance problem, owing to which the trained classifier is biased towards the majority classes and does not perform well on the minority classes. This study presents an imbalanced blood cells classification method that utilises Wasserstein divergence GAN, mixup and novel nonlinear mixup for data augmentation to achieve oversampling of the minority classes. We also present a minority class focussed sampling strategy, which allows effective representation of minority class samples produced by all three data augmentation techniques and contributes to the classification performance. The method was evaluated on two publicly available datasets of immortalised human T-lymphocyte cells and Red Blood Cells. Classification performance evaluated using F1-score shows that our proposed approach outperforms existing methods on the same datasets. [ABSTRACT FROM AUTHOR]

Accurate and early detection of pneumoconiosis using chest X-rays (CXR) is important for preventing the progression of this incurable disease. It is also a challenging task due to large variations in appearance, size and location of lesions in the lung regions as well as inter-class similarity and intra-class variance. Compared to traditional methods, Convolutional Neural Networks-based methods have shown improved results; however, these methods are still not applicable in clinical practice due to limited performance. In some cases, limited computing resources make it impractical to develop a model using whole CXR images. To address this problem, the lung fields are divided into six zones, each zone is classified separately and the zone classification results are then aggregated into an image classification score, based on state-of-the-art. In this study, we propose a dual lesion attention network (DLA-Net) for the classification of pneumoconiosis that can extract features from affected regions in a lung. This network consists of two main components: feature extraction and feature refinement. Feature extraction uses the pre-trained Xception model as the backbone to extract semantic information. To emphasise the lesion regions and improve the feature representation capability, the feature refinement component uses a DLA module that consists of two sub modules: channel attention (CA) and spatial attention (SA). The CA module focuses on the most important channels in the feature maps extracted by the backbone model, and the SA module highlights the spatial details of the affected regions. Thus, both attention modules combine to extract discriminative and rich contextual features to improve classification performance on pneumoconiosis. Experimental results show that the proposed DLA-Net outperforms state-of-the-art methods for pneumoconiosis classification. [ABSTRACT FROM AUTHOR]

Classification and characterisation of cellular morphological states are vital for understanding cell differentiation, development, proliferation and diverse pathological conditions. As the onset of morphological changes transpires following genetic alterations in the chromatin configuration inside the nucleus, the nuclear texture as one of the low-level properties if detected and quantified accurately has the potential to provide insights on nuclear organisation and enable early diagnosis and prognosis. This study presents a three dimensional (3D) nuclear texture description method for cell nucleus classification and variation measurement in chromatin patterns on the transition to another phenotypic state. The proposed approach includes third plane information using hyperplanes into the design of the Sorted Random Projections (SRP) texture feature and is evaluated on publicly available 3D image datasets of human fibroblast and human prostate cancer cell lines obtained from the Statistics Online Computational Resource. Results show that 3D SRP and 3D Local Binary Pattern provide better classification results than other feature descriptors. In addition, the proposed metrics based on 3D SRP validate the change in intensity and aggregation of heterochromatin on transition to another state and characterise the intermediate and ultimate phenotypic states. [ABSTRACT FROM AUTHOR]

Artificial Intelligence is a rapidly expanding field within computer science that encompasses the emulation of human intelligence by machines. Machine learning and deep learning – two primary data-driven pattern analysis approaches under the umbrella of artificial intelligence – has created considerable interest in the last few decades. The evolution of technology has resulted in a substantial amount of artificial intelligence research on ophthalmic and neurodegenerative disease diagnosis using retinal images. Various artificial intelligence-based techniques have been used for diagnostic purposes, including traditional machine learning, deep learning, and their combinations. Presented here is a review of the literature covering the last 10 years on this topic, discussing the use of artificial intelligence in analysing data from different modalities and their combinations for the diagnosis of glaucoma and neurodegenerative diseases. The performance of published artificial intelligence methods varies due to several factors, yet the results suggest that such methods can potentially facilitate clinical diagnosis. Generally, the accuracy of artificial intelligence-assisted diagnosis ranges from 67–98%, and the area under the sensitivity-specificity curve (AUC) ranges from 0.71–0.98, which outperforms typical human performance of 71.5% accuracy and 0.86 area under the curve. This indicates that artificial intelligence-based tools can provide clinicians with useful information that would assist in providing improved diagnosis. The review suggests that there is room for improvement of existing artificial intelligence-based models using retinal imaging modalities before they are incorporated into clinical practice. [ABSTRACT FROM AUTHOR]

Background: Manually measured anthropometric quantities are used in many applications including human malnutrition assessment. Training is required to collect anthropometric measurements manually, which is not ideal in resource-constrained environments. Photogrammetric methods have been gaining attention in recent years, due to the availability and affordability of digital cameras. Objective: The primary goal is to demonstrate that height and mid-upper arm circumference (MUAC)–indicators of malnutrition–can be accurately estimated by applying linear regression to distance measurements from photographs of participants taken from five views, and determine the optimal view combinations. A secondary goal is to observe the effect on estimate error of two approaches which reduce complexity of the setup, computational requirements and the expertise required of the observer. Methods: Thirty-one participants (11 female, 20 male; 18–37 years) were photographed from five views. Distances were computed using both camera calibration and reference object techniques from manually annotated photos. To estimate height, linear regression was applied to the distances between the top of the participants head and the floor, as well as the height of a bounding box enclosing the participant’s silhouette which eliminates the need to identify the floor. To estimate MUAC, linear regression was applied to the mid-upper arm width. Estimates were computed for all view combinations and performance was compared to other photogrammetric methods from the literature—linear distance method for height, and shape models for MUAC. Results: The mean absolute difference (MAD) between the linear regression estimates and manual measurements were smaller compared to other methods. For the optimal view combinations (smallest MAD), the technical error of measurement and coefficient of reliability also indicate the linear regression methods are more reliable. The optimal view combination was the front and side views. When estimating height by linear regression of the distance from the head to the floor, the mean MAD was 10.51 mm ± 6.52 mm SD, and when estimating height from the bounding box using the reference object, the mean MAD per participant was 11.53 mm ± 6.43 mm SD. When estimating MUAC from the mid-upper arm radius using the reference object, the mean MAD was 7.24 mm ± 4.79 mm SD. The mean MAD for all methods when using camera calibration was 2–3 mm smaller. Conclusions: Applying linear regression to distance measurements from photos of adults taken from multiple view angles has been shown to accurately estimate height and MUAC to within the accuracy required for nutrition assessment. Future work will focus on automating the landmark detection, and validating the methods on populations that include undernourished adults and children of all nutrition statuses. These future works will improve the practicality of this method as a potential tool for nutrition assessment by novice users. [ABSTRACT FROM AUTHOR]

• Wall Shear Stress (WSS) is associated with coronary artery disease risk. • Computational Fluid Dynamics is computationally expensive. • Deep learning models provide a fast and accurate method of calculating WSS. Haemodynamic metrics, such as blood flow induced shear stresses at the inner vessel lumen, are associated with the development and progression of coronary artery disease. Understanding these metrics may therefore improve the assessment of an individual's coronary disease risk. However, the calculation of such luminal Wall Shear Stress (WSS) using traditional Computational Fluid Dynamics (CFD) methods is relatively slow and computationally expensive. As a result, CFD based haemodynamic computation is not suitable for integrated and large-scale use in clinical settings. In this work, deep learning techniques are proposed as an alternative method to CFD, whereby luminal WSS magnitude can be predicted in coronary bifurcations throughout the cardiac cycle based on the steady state solution (which takes <120 seconds to calculate including preprocessing), vessel geometry and additional global features. The deep learning model is trained on a dataset of 101 patient-specific and 2626 synthetic left main bifurcation models with 26 separate patient-specific cases used as the test set. The model showed high fidelity predictions with <5% (normalised against mean WSS magnitude) deviation to CFD derived values as the gold-standard method, while being orders of magnitude faster with on average <2 minutes versus 3 hours computation for transient CFD. This method therefore offers a new approach to substantially reduce the computational cost involved in, for example, large-scale population studies of coronary haemodynamic metrics, and may therefore open the pathway for future clinical integration. [ABSTRACT FROM AUTHOR]

Vision-based human motion tracking has gained significant interest in recent years, as the need for more intuitive human-computer interaction paradigms are sought after. Immersive environments, such as large-scale displays and virtual reality systems are particularly suitable for such interaction mechanisms, as they provide a controlled basis for experimentation and evaluation. However, despite the growing interest, human-motion tracking within immersive environments is still in its infancy. The lack of visible light and the presence of multiple people within such environments pose several challenges to the problem. In this research a robust framework for real-time, multi-camera human-motion tracking within an immersive environment is presented. The static nature of the environment is exploited to utilise a novel 2-cohort camera layout. This layout proves to be highly useful for tracking, providing several benefits over existing techniques, which treat all cameras as the same. [ABSTRACT FROM AUTHOR]

Isolating relevant information and reducing the dimensionality of the original data set are key areas of interest in pattern recognition and machine learning. In this paper, a novel approach to reducing dimensionality of the feature space by employing independent component analysis (ICA) is introduced. While ICA is primarily a feature extraction technique, it is used here as a feature selection/construction technique in a generic way. The new technique, called feature selection based on independent component analysis (FS_ICA), efficiently builds a reduced set of features without loss in accuracy and also has a fast incremental version. When used as a first step in supervised learning, FS_ICA outperforms comparable methods in efficiency without loss of classification accuracy. For large data sets as in medical image segmentation of high-resolution computer tomography images, FS_ICA reduces dimensionality of the data set substantially and results in efficient and accurate classification. [ABSTRACT FROM AUTHOR]

An automated method is presented for segmentation of two-dimensional HRCT images of the lung into regions of four lung patterns: normal, emphysema, honeycombing, and ground-glass opacity (GGO). Segmentation was implemented in two stages. At the first stage, pixel-wise classification of the lung area was performed using local textural features extracted by the wavelet transform. At the second stage, classification results were refined by application of knowledge-based rules. Performance of the method was compared on two sets of HRCT images: one included HRCT images with characteristic examples of lung patterns and the other consisted of unselected HRCT images that represented a model of routine operations at a general radiology practice. On the first set of images, sensitivity of the method ranged from 0.92 to 0.99, and specificity ranged from 0.96 to 0.99. On the second set of images, sensitivity and specificity were, respectively, 0.49 and 0.95 for emphysema, 0.87 and 0.55 for normal, 0.34 and 0.99 for honeycombing, and 0.57 and 0.94 for GGO. The two-stage approach allowed for simple and effective application of high-level knowledge about appearance of lung patterns on HRCT images and did not require feature and region of interest size selection for the first stage of pixel-wise lung pattern classification. [ABSTRACT FROM AUTHOR]

Liquid biopsy has shown promise for cancer diagnosis due to its minimally invasive nature and the potential for novel biomarker discovery. However, the low concentration of relevant blood-based biosources and the heterogeneity of samples (i.e. the variability of relative abundance of molecules identified), pose major challenges to biomarker discovery. Moreover, the number of molecular measurements or features (e.g. transcript read counts) per sample could be in the order of several thousand, whereas the number of samples is often substantially lower, leading to the curse of dimensionality. These challenges, among others, elucidate the importance of a robust biomarker panel identification or feature extraction step wherein relevant molecular measurements are identified prior to classification for cancer detection. In this work, we performed a benchmarking study on 12 feature extraction methods using transcriptomic profiles derived from different blood-based biosources. The methods were assessed both in terms of their predictive performance and the robustness of the biomarker panels in diagnosing cancer or stratifying cancer subtypes. While performing the comparison, the feature extraction methods are categorized into feature subset selection methods and transformation methods. A transformation feature extraction method, namely partial least square discriminant analysis, was found to perform consistently superior in terms of classification performance. As part of the benchmarking study, a generic pipeline has been created and made available as an R package to ensure reproducibility of the results and allow for easy extension of this study to other datasets (https://github.com/VafaeeLab/bloodbased-pancancer-diagnosis). [ABSTRACT FROM AUTHOR]

The task of designing large real-time reactive systems, which interact continuously with their environment and exhibit concurrency properties, is a challenging one. In this paper, we explore the utility of a combination of behavior and function specification languages in specifying such systems and verifying their properties. An existing specification language, statecharts, is used to specify the behavior of real-time reactive systems, while a new logic-based language called FNLOG (based on first-order predicate calculus and temporal logic, is designed to express the system functions over real time. Two types of system properties, intrinsic and structural, are proposed. It is shown that both types of system properties are expressible in FNLOG and may be verified by logical deduction, and also hold for the corresponding behavior specification. [ABSTRACT FROM AUTHOR]

Atypical visual attention in individuals with autism spectrum disorders (ASD) has been utilised as a unique diagnosis criterion in previous research. This paper presents a novel approach to the automatic and quantitative screening of ASD as well as symptom severity prediction in preschool children. We develop a novel computational pipeline that extracts learned features from a dynamic visual stimulus to classify ASD children and predict the level of ASD-related symptoms. Experimental results demonstrate promising performance that is superior to using handcrafted features and machine learning algorithms, in terms of evaluation metrics used in diagnostic tests. Using a leave-one-out cross-validation approach, we obtained an accuracy of 94.59%, a sensitivity of 100%, a specificity of 76.47% and an area under the receiver operating characteristic curve (AUC) of 96% for ASD classification. In addition, we obtained an accuracy of 94.74%, a sensitivity of 87.50%, a specificity of 100% and an AUC of 99% for ASD symptom severity prediction. [ABSTRACT FROM AUTHOR]

Despite the fact that great progress has been made on single image deraining tasks, it is still challenging for existing models to produce satisfactory results directly, and it often requires a single or multiple refinement stages to gradually improve the quality. However, in this paper, we demonstrate that existing image-level refinement with a stage-independent learning design is problematic with the side effect of over/under-deraining. To resolve this issue, we for the first time propose the mechanism of learning to carry out refinement on the unsatisfactory features, and propose a novel attentive feature refinement (AFR) module. Specifically, AFR is designed as a two-branched network for simultaneous rain-distribution-aware attention map learning and attention guided hierarchy-preserving feature refinement. Guided by task-specific attention, coarse features are progressively refined to better model the diversified rainy effects. By using a separable convolution as the basic component, our AFR module introduces little computation overhead and can be readily integrated into most rainy-to-clean image translation networks for achieving better deraining results. By incorporating a series of AFR modules into a general encoder-decoder network, AFR-Net is constructed for deraining and it achieves new state-of-the-art results on both synthetic and real images. Furthermore, by using AFR-Net as a teacher model, we explore the use of knowledge distillation to successfully learn a student model that is also able to achieve state-of-the-art results but with a much faster inference speed (i.e., it only takes 0.08 second to process a $512\times 512$ rainy image). Code and pre-trained models are available at $\langle $ https://github.com/RobinCSIRO/AFR-Net $\rangle $. [ABSTRACT FROM AUTHOR]

Perception of content and structure in images with rainstreaks or raindrops is challenging, and it often calls for robust deraining algorithms to remove the diversified rainy effects. Much progress has been made on the design of advanced encoder–decoder single image deraining networks. However, most of the existing networks are built in a blind manner and often produce over/under-deraining artefacts. In this paper, we point out, for the first time, that the unsatisfactory results are caused by the highly imbalanced distribution between rainy effects and varied background scenes. Ignoring this phenomenon results in the representation learned by the encoder being biased towards rainy regions, while paying less attention to the valuable contextual regions. To resolve this, a context-enhanced representation learning and deraining network is proposed with a novel two-branch encoder design. Specifically, one branch takes the rainy image directly as input for learning a mixed representation depicting the variation of both rainy regions and contextual regions, and another branch is guided by a carefully learned soft attention mask to learn an embedding only depicting the contextual regions. By combining the embeddings from these two branches with a carefully designed co-occurrence modelling module, and then improving the semantic property of the co-occurrence features via a bi-directional attention layer, the underlying imbalanced learning problem is resolved. Extensive experiments are carried out for removing rainstreaks and raindrops from both synthetic and real rainy images, and the proposed model is demonstrated to produce significantly better results than state-of-the-art models. In addition, comprehensive ablation studies are also performed to analyze the contributions of different designs. Code and pre-trained models will be publicly available at https://github.com/RobinCSIRO/CERLD-Net.git. [ABSTRACT FROM AUTHOR]

Restoring a rainy image with raindrops or rainstreaks of varying scales, directions, and densities is an extremely challenging task. Recent approaches attempt to leverage the rain distribution (e.g., location) as prior to generate satisfactory results. However, concatenation of a single distribution map with the rainy image or with intermediate feature maps is too simplistic to fully exploit the advantages of such priors. To further explore this valuable information, an advanced cascaded attention guidance network, dubbed as CAG-Net, is formulated and designed as a three-stage model. In the first stage, a multi-task learning network is constructed for producing the attention map and coarse de-raining results simultaneously. Subsequently, the coarse results and the rain distribution map are concatenated and fed to the second stage for results refinement. In this stage, the attention map generation network from the first stage is used to formulate a novel semantic consistency loss for better detail recovery. In the third stage, a novel pyramidal “where-and-how” learning mechanism is formulated. At each pyramid level, a two-branch network is designed to take the features from previous stages as inputs to generate better attention-guidance features and de-raining features, which are then combined via a gating scheme to produce the final de-raining results. Moreover, the uncertainty maps are also generated in this stage for more accurate pixel-wise loss calculation. Extensive experiments are carried out for removing raindrops or rainstreaks from both synthetic and real rainy images, and CAG-Net is demonstrated to produce significantly better results than state-of-the-art models. Codes are available at < https://github.com/RobinCSIRO/CAGNet >. [ABSTRACT FROM AUTHOR]

Medical image analysis plays a pivotal role in the evaluation of diseases, including screening, surveillance, diagnosis, and prognosis. Liver is one of the major organs responsible for key functions of metabolism, protein and hormone synthesis, detoxification, and waste excretion. Patients with advanced liver disease and Hepatocellular Carcinoma (HCC) are often asymptomatic in the early stages; however delays in diagnosis and treatment can lead to increased rates of decompensated liver diseases, late-stage HCC, morbidity and mortality. Ultrasound (US) is commonly used imaging modality for diagnosis of chronic liver diseases that includes fibrosis, cirrhosis and portal hypertension. In this paper, we first provide an overview of various diagnostic methods for stages of liver diseases and discuss the role of Computer-Aided Diagnosis (CAD) systems in diagnosing liver diseases. Second, we review the utility of machine learning and deep learning approaches as diagnostic tools. Finally, we present the limitations of existing studies and outline future directions to further improve diagnostic accuracy, as well as reduce cost and subjectivity, while also improving workflow for the clinicians. [ABSTRACT FROM AUTHOR]

Objective: Prior research suggests there are observable behaviours preceding suicide attempts in public places. However, there are currently no ways to continually monitor such sites, limiting the potential to intervene. In this mixed-methods study, we examined the acceptability and feasibility of using an automated computer system to identify crisis behaviours. Methods: First, we conducted a large-scale acceptability survey to assess public perceptions on research using closed-circuit television and artificial intelligence for suicide prevention. Second, we identified crisis behaviours at a frequently used cliff location by manual structured analysis of closed-circuit television footage. Third, we configured a computer vision algorithm to identify crisis behaviours and evaluated its sensitivity and specificity using test footage. Results: Overall, attitudes were positive towards research using closed-circuit television and artificial intelligence for suicide prevention, including among those with lived experience. The second study revealed that there are identifiable behaviours, including repetitive pacing and an extended stay. Finally, the automated behaviour recognition algorithm was able to correctly identify 80% of acted crisis clips and correctly reject 90% of acted non-crisis clips. Conclusion: The results suggest that using computer vision to detect behaviours preceding suicide is feasible and well accepted by the community and may be a feasible method of initiating human contact during a crisis. [ABSTRACT FROM AUTHOR]

Introduction: The purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age‐related changes by using drusen masks for spatial feature supervision. Methods: A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre‐processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver‐operating characteristic (AUC). Fivefold cross‐validation was performed, and the results compared with four other methods. Results: Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01). Conclusion: The proposed drusen‐aware model outperformed baseline and other vessel feature‐based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five‐category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real‐life clinical setting. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer diagnosis and treatment can be improved by understanding the specific genetic makeup of a patient's tumour. Currently, this genetic information is obtained through expensive and time-consuming molecular tests, which are not widely reimbursed by healthcare systems. To address this issue, we propose a new, computationally efficient deep learning based method called hist2RNA to predict the expression of genes using digital images of stained tissue samples. Our approach successfully predicts gene expression and identifies breast cancer subtypes, enabling personalized treatments, thereby improving patient survival and overall breast cancer management. Gene expression can be used to subtype breast cancer with improved prediction of risk of recurrence and treatment responsiveness over that obtained using routine immunohistochemistry (IHC). However, in the clinic, molecular profiling is primarily used for ER+ breast cancer, which is costly, tissue destructive, requires specialised platforms, and takes several weeks to obtain a result. Deep learning algorithms can effectively extract morphological patterns in digital histopathology images to predict molecular phenotypes quickly and cost-effectively. We propose a new, computationally efficient approach called hist2RNA inspired by bulk RNA sequencing techniques to predict the expression of 138 genes (incorporated from 6 commercially available molecular profiling tests), including luminal PAM50 subtype, from hematoxylin and eosin (H&E)-stained whole slide images (WSIs). The training phase involves the aggregation of extracted features for each patient from a pretrained model to predict gene expression at the patient level using annotated H&E images from The Cancer Genome Atlas (TCGA, n = 335). We demonstrate successful gene prediction on a held-out test set (n = 160, corr = 0.82 across patients, corr = 0.29 across genes) and perform exploratory analysis on an external tissue microarray (TMA) dataset (n = 498) with known IHC and survival information. Our model is able to predict gene expression and luminal PAM50 subtype (Luminal A versus Luminal B) on the TMA dataset with prognostic significance for overall survival in univariate analysis (c-index = 0.56, hazard ratio = 2.16 (95% CI 1.12–3.06), p < 5 × 10−3), and independent significance in multivariate analysis incorporating standard clinicopathological variables (c-index = 0.65, hazard ratio = 1.87 (95% CI 1.30–2.68), p < 5 × 10−3). The proposed strategy achieves superior performance while requiring less training time, resulting in less energy consumption and computational cost compared to patch-based models. Additionally, hist2RNA predicts gene expression that has potential to determine luminal molecular subtypes which correlates with overall survival, without the need for expensive molecular testing. [ABSTRACT FROM AUTHOR]

Background: A number of differences in joint attention behaviour between children with autism spectrum disorder (ASD) and typically developing (TD) individuals have previously been documented. Method: We use eye-tracking technology to assess response to joint attention (RJA) behaviours in 77 children aged 31 to 73 months. We conducted a repeated-measures analysis of variance to identify differences between groups. In addition, we analysed correlations between eye-tracking and clinical measures using Spearman's correlation. Results: The children diagnosed with ASD were less likely to follow gaze compared to TD children. Children with ASD were less accurate at gaze following when only eye gaze information was available, compared to when eye gaze with head movement was observed. Higher accuracy gaze-following profiles were associated with better early cognition and more adaptive behaviours in children with ASD. Less accurate gaze-following profiles were associated with more severe ASD symptomatology. Conclusion: There are differences in RJA behaviours between ASD and TD preschool children. Several eye-tracking measures of RJA behaviours in preschool children were found to be associated with clinical measures for ASD diagnosis. This study also highlights the construct validity of using eye-tracking measures as potential biomarkers in the assessment and diagnosis of ASD in preschool children. [ABSTRACT FROM AUTHOR]

Classical supervised object detection methods learn object models from labelled training data. This is tedious to create especially when the training dataset is large. Detection methods such as background subtraction and headlight detection can detect potential positive blobs that may contain the object without labelled training data. However, such blobs are not always accurate. They may include noise such as part of an object, multiple objects and other types of objects. Therefore, soft labels that indicate their probability of being positive may be more useful. A modified soft label estimation method based on Maximum Mean Discrepancy is introduced in this work. Based on it, a Generalized Hough Transform based object detection method from soft-labelled training data is proposed to utilize potential detections and their estimated soft labels. Experimental results show that the method can achieve comparable performance to supervised methods. It outperforms both Generalized Hough Transform based object detection with hard-labelled training blobs, and a state-of-the-art weakly supervised method. [ABSTRACT FROM AUTHOR]

Background: Feature selection is often used to identify the important features in a dataset but can produce unstable results when applied to high-dimensional data. The stability of feature selection can be improved with the use of feature selection ensembles, which aggregate the results of multiple base feature selectors. However, a threshold must be applied to the final aggregated feature set to separate the relevant features from the redundant ones. A fixed threshold, which is typically used, offers no guarantee that the final set of selected features contains only relevant features. This work examines a selection of data-driven thresholds to automatically identify the relevant features in an ensemble feature selector and evaluates their predictive accuracy and stability. Ensemble feature selection with data-driven thresholding is applied to two real-world studies of Alzheimer's disease. Alzheimer's disease is a progressive neurodegenerative disease with no known cure, that begins at least 2–3 decades before overt symptoms appear, presenting an opportunity for researchers to identify early biomarkers that might identify patients at risk of developing Alzheimer's disease. Results: The ensemble feature selectors, combined with data-driven thresholds, produced more stable results, on the whole, than the equivalent individual feature selectors, showing an improvement in stability of up to 34%. The most successful data-driven thresholds were the robust rank aggregation threshold and the threshold algorithm threshold from the field of information retrieval. The features identified by applying these methods to datasets from Alzheimer's disease studies reflect current findings in the AD literature. Conclusions: Data-driven thresholds applied to ensemble feature selectors provide more stable, and therefore more reproducible, selections of features than individual feature selectors, without loss of performance. The use of a data-driven threshold eliminates the need to choose a fixed threshold a-priori and can select a more meaningful set of features. A reliable and compact set of features can produce more interpretable models by identifying the factors that are important in understanding a disease. [ABSTRACT FROM AUTHOR]

• Methods for segmenting coronary arteries are systematically reviewed. • Segmentation of the arteries are vital in both research and clinical applications. • Current trends and state of the art segmentation algorithms are explored. Background and Objective: Vessel segmentation is the first processing stage of 3D medical images for both clinical and research use. Current segmentation methods are tedious and time consuming, requiring significant manual correction and hence are infeasible to use in large data sets. Methods: Here, we review and analyse available coronary artery segmentation methods, focusing on fully automated methods capable of handling the rapidly growing medical images available. All manuscripts published since 2010 are systematically reviewed, categorised into different groups based on the approach taken, and characteristics of the different approaches as well as trends over the past decade are explored. Results: The manuscripts were divided intro three broad categories, consisting of region growing, voxelwise prediction and partitioning approaches. The most common approach overall was region growing, particularly using active contour models, however these have had a sharp fall in popularity in recent years with convolutional neural networks becoming significantly more popular. Conclusions: The systematic review of current coronary artery segmentation methods shows interesting trends, with rising popularity of machine learning methods, a focus on efficient methods, and falling popularity of computationally expensive processing steps such as vesselness and multiplanar reformation. [ABSTRACT FROM AUTHOR]

• Proposed complex shearlets can overcome the weakness of the current shearlets. • Idea fully using both amplitude and phase information to detect corners is novel. • A new phase congruence model with high localization ability and noise tolerance. • A new rotation-normalized tensor using all amplitudes and phases to detect corners. • The work yields improvements on the current state-of-the-art in corner detection. Corner detection algorithms based on multi-scale analysis attract more attention due to their promising performance. However, they only consider amplitude information, neglect phase information and partially utilize multi-scale decomposition coefficients to detect corners. This limits their detection accuracy, repeatability and localization ability. This paper describes a new multi-scale analysis based corner detector. To overcome the problems of bilateral margin responses, edge extension and lack of phase information in traditional shearlets, a novel complex shearlet transform is proposed to better localize distributed discontinuities and especially to extract phase information from geometrical features. Moreover, a new rotary phase congruence tensor is proposed to utilize all amplitude and phase information for corner detection. Its tolerances to noise and ability for corner localization are improved further by screening and normalizing the amplitude information. Experimental results demonstrate that the localization ability and detection accuracy of the proposed method are superior to current detectors, and its repeatability is generally higher than current detectors and recent machine learning based interest point detectors. [ABSTRACT FROM AUTHOR]

Understanding human behaviours through video analysis has seen significant research progress in recent years with the advancement of deep learning. This topic is of great importance to the next generation of intelligent visual surveillance systems which are capable of real-time detection and analysis of human behaviours. One important application is to automatically monitor and detect individuals who are in crisis at suicide hotspots to facilitate early intervention and prevention. However, there is still a significant gap between research in human action recognition and visual video processing in general, and their application to monitor hotspots for suicide prevention. While complex backgrounds, non-rigid movements of pedestrians and limitations of surveillance cameras and multi-task requirements for a surveillance system all pose challenges to the development of such systems, a further challenge is the detection of crisis behaviours before a suicide attempt is made, and there is a paucity of datasets in this area due to privacy and confidentiality issues. Most relevant research only applies to detecting suicides such as hangings or jumps from bridges, providing no potential for early prevention. In this research, these problems are addressed by proposing a new modular design for an intelligent visual processing pipeline that is capable of pedestrian detection, tracking, pose estimation and recognition of both normal actions and high risk behavioural cues that are important indicators of a suicide attempt. Specifically, based on the key finding that human body gestures can be used for the detection of social signals that potentially precede a suicide attempt, a new 2D skeleton-based action recognition algorithm is proposed. By using a two-branch network that takes advantage of three types of skeleton-based features extracted from a sequence of frames and a stacked LSTM structure, the model predicts the action label at each time step. It achieved good performance on both the public dataset JHMDB and a smaller private CCTV footage collection on action recognition. Moreover, a logical layer, which uses knowledge from a human coding study to recognise pre-suicide behaviour indicators, has been built on top of the action recognition module to compensate for the small dataset size. It enables complex behaviour patterns to be recognised even from smaller datasets. The whole pipeline has been tested in a real-world application of suicide prevention using simulated footage from a surveillance system installed at a suicide hotspot, and preliminary results confirm its effectiveness at capturing crisis behaviour indicators for early detection and prevention of suicide. [ABSTRACT FROM AUTHOR]

Automated brain tumour segmentation from post-operative images is a clinically relevant yet challenging problem. In this study, an automated method for segmenting brain tumour into its subregions has been developed. The dataset consists of multimodal post-operative brain scans (T1 MRI, post-Gadolinium T1 MRI, and T2-FLAIR images) of 15 patients who were treated with post-operative radiation therapy, along with manual annotations of their tumour subregions. A 3D densely-connected U-net was developed for segmentation of brain tumour regions and extensive experiments were conducted to enhance model accuracy. A model was initially developed using the publicly available BraTS dataset consisting of pre-operative brain scans. This model achieved Dice Scores of 0.90, 0.83 and 0.78 for predicting whole tumour, tumour core, and enhancing tumour subregions when tested on BraTS20 blind validation dataset. The acquired knowledge from BraTS was then transferred to the local dataset. For augmentation purpose, the local dataset was registered to a dataset of MRI brain scans of healthy subjects. To improve the robustness of the model and enhance its accuracy, ensemble learning was used to combine the outputs of all the trained models. Even though the size of the dataset is very small, the final model can segment brain tumours with a high Dice Score of 0.83, 0.77 and 0.60 for whole tumour, tumour core and enhancing core respectively. [ABSTRACT FROM AUTHOR]

Deformable image registration plays a critical role in various clinical applications (e.g., image fusion, atlas creation, and tumors targeting). In radiation therapy, especially in the context of fast registration of computed tomography (CT) lung image modalities, it is used to determine the geometric transformation by relating the anatomic points in two images. The main challenge lies in effectively addressing the nonlinear large and small deformation between the inspiration and expiration phases. In this work, we propose an unsupervised hybrid paradigm-based registration network (HPRN) for the registration of 4D CT lung images without relying on ground truth data. The proposed HPRN exhibits effective learning of multi-scale and multi-resolution features, leading to the computation of a more accurate Deformation Vector Field (DVF). Furthermore, we incorporate the regularization, image similarity and Jacobian determinant loss functions, which results in improving capability in dealing with complex large and small deformations. We evaluate the effectiveness of the proposed model on the publicly accessible DIRLab 4DCT lung image dataset, which shows the effectiveness of the proposed framework by achieving better Target Registration Error (2. 04 ± 1. 42 mm) compared to other state-of-the-art unsupervised image registration algorithms. • Present hybrid multi-resolution pyramid to effectively handle both large and small deformations. • HPRN can accurately capture complex deformation patterns in medical image registration tasks. • Present joint loss function, that exhibits superior robustness against variations in image grayscale distribution and contrast. [ABSTRACT FROM AUTHOR]

Accurate and automated lung segmentation in high-resolution computed tomography (HRCT) is highly challenged by the presence of pathologies affecting lung parenchyma appearance and borders. The algorithm presented employs an anatomical model-driven approach and systematic incremental knowledge acquisition to produce coarse lung delineation, used as initialization for the graph-cut algorithm. The proposed method is evaluated on a 49 HRCT cases dataset including various lung disease patterns. The accuracy of the method is assessed using dice similarity coefficient (DSC) and shape differentiation metrics (dmean, drms), by comparing the outputs of automatic lung segmentations and manual ones. The proposed automatic method demonstrates high segmentation accuracy (DSC = 96.64%, dmean = 1.75 mm, drms = 3.27 mm) with low variation that depends on the lung disease pattern. It also presents good improvement over the initial lung segmentation (ΔDSC = 4.74%, Δdmean = -3.67 mm, Δdrms = -6.25 mm), including impressive amelioration (maximum values of ΔDSC = 58.22% and Δdmean = -78.66 mm) when the anatomy-driven algorithm reaches its limit. Segmentation evaluation shows that the method can accurately segment lungs even in the presence of disease patterns, with some limitations in the apices and bases of lungs. Therefore, the developed automatic segmentation method is a good candidate for the first stage of a computer-aided diagnosis system for diffuse lung diseases. [ABSTRACT FROM AUTHOR]

Segmentation of organs and structures, as either targets or organs-at-risk, has a significant influence on the success of radiation therapy. Manual segmentation is a tedious and time-consuming task for clinicians, and inter-observer variability can affect the outcomes of radiation therapy. The recent hype over deep neural networks has added many powerful auto-segmentation methods as variations of convolutional neural networks (CNN). This paper presents a descriptive review of the literature on deep learning techniques for segmentation in radiation therapy planning. The most common CNN architecture across the four clinical sub sites considered was U-net, with the majority of deep learning segmentation articles focussed on head and neck normal tissue structures. The most common data sets were CT images from an inhouse source, along with some public data sets. N-fold cross-validation was commonly employed; however, not all work separated training, test and validation data sets. This area of research is expanding rapidly. To facilitate comparisons of proposed methods and benchmarking, consistent use of appropriate metrics and independent validation should be carefully considered. [ABSTRACT FROM AUTHOR]

Data collected from clinical trials and cohort studies, such as dementia studies, are often high-dimensional, censored, heterogeneous and contain missing information, presenting challenges to traditional statistical analysis. There is an urgent need for methods that can overcome these challenges to model this complex data. At present there is no cure for dementia and no treatment that can successfully change the course of the disease. Machine learning models that can predict the time until a patient develops dementia are important tools in helping understand dementia risks and can give more accurate results than traditional statistical methods when modelling high-dimensional, heterogeneous, clinical data. This work compares the performance and stability of ten machine learning algorithms, combined with eight feature selection methods, capable of performing survival analysis of high-dimensional, heterogeneous, clinical data. We developed models that predict survival to dementia using baseline data from two different studies. The Sydney Memory and Ageing Study (MAS) is a longitudinal cohort study of 1037 participants, aged 70–90 years, that aims to determine the effects of ageing on cognition. The Alzheimer's Disease Neuroimaging Initiative (ADNI) is a longitudinal study aimed at identifying biomarkers for the early detection and tracking of Alzheimer's disease. Using the concordance index as a measure of performance, our models achieve maximum performance values of 0.82 for MAS and 0.93 For ADNI. [ABSTRACT FROM AUTHOR]

The expressive ability of classic Hawkes processes is limited due to the parametric assumption on the baseline intensity and triggering kernel. Therefore, it is desirable to perform inference in a data-driven, nonparametric approach. Many recent works have proposed nonparametric Hawkes process models based on Gaussian processes (GP). However, the likelihood is non-conjugate to the prior resulting in a complicated and time-consuming inference procedure. To address the problem, we present the sigmoid Gaussian Hawkes process model in this paper: the baseline intensity and triggering kernel are both modeled as the sigmoid transformation of random trajectories drawn from a GP. By introducing auxiliary latent random variables (branching structure, P´olya-Gamma random variables and latent marked Poisson processes), the likelihood is converted to two decoupled components with a Gaussian form which allows for an efficient conjugate analytical inference. Using the augmented likelihood, we derive an efficient Gibbs sampling algorithm to sample from the posterior; an efficient expectation-maximization (EM) algorithm to obtain the maximum a posteriori (MAP) estimate and furthermore an efficient mean-field variational inference algorithm to approximate the posterior. To further accelerate the inference, a sparse GP approximation is introduced to reduce complexity. We demonstrate the performance of our three algorithms on both simulated and real data. The experiments show that our proposed inference algorithms can recover well the underlying prompting characteristics efficiently. [ABSTRACT FROM AUTHOR]

This article describes a new data set for the study of genocide, politicide, and similar atrocities. Existing data sets have facilitated advances in understanding and policy-relevant applications such as forecasting but have been criticized for insufficient transparency, replicability, and for omitting failed or prevented attempts at genocide/politicide. More general data sets of mass civilian killing do not typically enable users to isolate situations in which specific groups are deliberately targeted. The Targeted Mass Killing (TMK) data set identifies 201 TMK episodes, 1946 to 2017, with annualized information on perpetrator intent, severity, targeted groups, and new ordinal and binary indicators of genocide/politicide that can serve as alternatives to existing measures. Users are also able to construct their own indicators based on their research questions or preferred definitions. The article discusses the concept and operationalization of TMK, provides comparisons with other data sets, and highlights some of the strengths and new capabilities of the TMK data. [ABSTRACT FROM AUTHOR]

Advances in the manufacturing of miniaturized low-power embedded systems are paving the way for ultra-lightweight wearable cameras that can visually log the minute details of people's daily lives. This survey highlights the possible applications of wearable cameras, from industrial to personal, and outlines the main challenges in realizing their full potential. [ABSTRACT FROM AUTHOR]

Cardiovascular disease is a major cause of death worldwide. Computed Tomography Coronary Angiography (CTCA) is a non-invasive method used to evaluate coronary artery disease, as well as evaluating and reconstructing heart and coronary vessel structures. Reconstructed models have a wide array of for educational, training and research applications such as the study of diseased and non-diseased coronary anatomy, machine learning based disease risk prediction and in-silico and in-vitro testing of medical devices. However, coronary arteries are difficult to image due to their small size, location, and movement, causing poor resolution and artefacts. Segmentation of coronary arteries has traditionally focused on semi-automatic methods where a human expert guides the algorithm and corrects errors, which severely limits large-scale applications and integration within clinical systems. International challenges aiming to overcome this barrier have focussed on specific tasks such as centreline extraction, stenosis quantification, and segmentation of specific artery segments only. Here we present the results of the first challenge to develop fully automatic segmentation methods of full coronary artery trees and establish the first large standardized dataset of normal and diseased arteries. This forms a new automated segmentation benchmark allowing the automated processing of CTCAs directly relevant for large-scale and personalized clinical applications. [Display omitted] • Virtual coronary artery models of have been increasingly used in research and clinical settings. • Standardized dataset of coronary artery ground truth allows objective comparison of new methods. • ASOCA challenge provides automated testing and evaluation framework. [ABSTRACT FROM AUTHOR]

Radiological images play a central role in radiotherapy, especially in target volume delineation. Radiomic feature extraction has demonstrated its potential for predicting patient outcome and cancer risk assessment prior to treatment. However, inherent methodological challenges such as severe class imbalance, small training sample size, multi-centre data and weak correlation of image representations to outcomes are yet to be addressed adequately. Current radiomic analysis relies on segmented images (e.g., of tumours) for feature extraction, leading to loss of important context information in surrounding tissue. In this work, we examine the correlation between radiomics and clinical outcomes by combining two data modalities: pre-treatment computerized tomography (CT) imaging data and contours of segmented gross tumour volumes (GTVs). We focus on a clinical head & neck cancer dataset and design an efficient convolutional neural network (CNN) architecture together with appropriate machine learning strategies to cope with the challenges. During the training process on two cohorts, our algorithm learns to produce clinical outcome predictions by automatically extracting radiomic features. Test results on two other cohorts show state-of-the-art performance in predicting different clinical endpoints (i.e., distant metastasis: AUC = 0.91; loco-regional failure: AUC = 0.78; overall survival: AUC = 0.70 on segmented CT data) compared to prior studies. Furthermore, we also conduct extensive experiments both on the whole CT dataset and a combination of CT and GTV contours to investigate different learning strategies for this task. For example, further experiments indicate that overall survival prediction significantly improves to 0.83 AUC by combining CT and GTV contours as inputs, and the combination provides more intuitive visual explanations for patient outcome predictions. [ABSTRACT FROM AUTHOR]

We present what is, to the best of our knowledge, the first published set of annual out-of-sample forecasts of genocide and politicide based on a global dataset. Our goal is to produce a prototype for a real-time model capable of forecasting one year into the future. Building on the current literature, we take several important steps forward. We implement an unconditional two-stage model encompassing both instability and genocide, allowing our sample to be the available global data, rather than using conditional case selection or a case-control approach. We explore factors exhibiting considerable variance over time to improve yearly forecasting performance. And we produce annual lists of at-risk states in a format that should be of use to policymakers seeking to prevent such mass atrocities. Our out-of-sample forecasts for 1988–2003 predict 90.9% of genocide onsets correctly while also predicting 79.2% of non-onset years correctly, an improvement over a previous study using a case-control in-sample approach. We produce 16 annual forecasts based only on previous years’ data, which identify six of 11 cases of genocide/politicide onset within the top 5% of at-risk countries per year. We believe this represents substantial progress towards useful real-time forecasting of such rare events. We conclude by suggesting ways to further enhance predictive performance. [ABSTRACT FROM PUBLISHER]

• It took full advantages of shearlet to obtain structural information. • Improved shearlets to overcome the weakness of the current shearlets for corner detection. • A novel multi-directional structure tensor for making full use of structural information. • A new multi-scale corner measurement function for exactly refining candidate corners. • It yields some improvements on the current state-of-the-art in corner detection. Image corners have been widely used in various computer vision tasks. Current multi-scale analysis based corner detectors do not make full use of the multi-scale and multi-directional structural information. This degrades their detection accuracy and capability of refining corners. In this work, an improved shearlet transform with a flexible number of directions and a reasonable support is proposed to extract accurate multi-scale and multi-directional structural information from images. To make full use of the structural information from the improved shearlets, a novel multi-directional structure tensor is constructed for corner detection, and a multi-scale corner measurement function is proposed to remove false candidate corners. Experimental results demonstrate that the proposed corner detector performs better than existing corner and interest point detectors in terms of detection accuracy, localization accuracy, and robustness to affine transformations, illumination changes, noise, viewpoint changes, etc. It has a great potential for extension as a descriptor and for applications in computer vision tasks. [ABSTRACT FROM AUTHOR]