Search

• We extend our hierarchical method for food recognition, introducing two additional ways of estimating epistemic uncertainty. • We present a detailed analysis of the epistemic uncertainty provided by each proposed method. • We show that our approach is also effective when different epistemic uncertainty methods are considered. • We show that our method minimizes in all cases the errors propagation from parents to children in the hierarchical approach. • We observe that our method improves the performance with respect to the flat classifier on two public food datasets. Food image recognition has recently attracted the attention of many researchers, due to the challenging problem it poses, the ease collection of food images, and its numerous applications to health and leisure. In real applications, it is necessary to analyze and recognize thousands of different foods. For this purpose, we propose a novel prediction scheme based on a class hierarchy that considers local classifiers, in addition to a flat classifier. In order to make a decision about which approach to use, we define different criteria that take into account both the analysis of the Epistemic Uncertainty estimated from the 'children' classifiers and the prediction from the 'parent' classifier. We evaluate our proposal using three Uncertainty estimation methods, tested on two public food datasets. The results show that the proposed method reduces parent-child error propagation in hierarchical schemes and improves classification results compared to the single flat classifier, meanwhile maintains good performance regardless the Uncertainty estimation method chosen. [ABSTRACT FROM AUTHOR]

Today, we witness the appearance of many lifelogging cameras that are able to capture the life of a person wearing the camera and which produce a large number of images everyday. Automatically characterizing the experience and extracting patterns of behavior of individuals from this huge collection of unlabeled and unstructured egocentric data present major challenges and require novel and efficient algorithmic solutions. The main goal of this work is to propose a new method to automatically assess day similarity from the lifelogging images of a person. We propose a technique to measure the similarity between images based on the Swain's distance and generalize it to detect the similarity between daily visual data. To this purpose, we apply the dynamic time warping (DTW) combined with the Swain's distance for final day similarity estimation. For validation, we apply our technique on the Egocentric Dataset of University of Barcelona (EDUB) of 4912 daily images acquired by four persons with preliminary encouraging results. Methods: The search strategy was designed for high sensitivity over precision, to ensure that no relevant studies were lost. We performed a systematic review of the literature using academic databases (ACM, Scopus, etc.) focusing on themes of day similarity, automatically assess day similarity, assess day similarity on EDUB, and assess day similarity using visual lifelogs. The study included randomized controlled trials, cohort studies, and case-control studies published between 2006 and 2017. [ABSTRACT FROM AUTHOR]

We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity. Experiments on CIFAR-10, STL-10 and UCMerced show that the method achieves the state-of-the-art performance, providing discriminative features that generalize well. [ABSTRACT FROM PUBLISHER]

Abstract: Three-dimensional intravascular ultrasound (IVUS) allows to visualize and obtain volumetric measurements of coronary lesions through an exploration of the cross sections and longitudinal views of arteries. However, the visualization and subsequent morpho-geometric measurements in IVUS longitudinal cuts are subject to distortion caused by periodic image/vessel motion around the IVUS catheter. Usually, to overcome the image motion artifact ECG-gating and image-gated approaches are proposed, leading to slowing the pullback acquisition or disregarding part of IVUS data. In this paper, we argue that the image motion is due to 3-D vessel geometry as well as cardiac dynamics, and propose a dynamic model based on the tracking of an elliptical vessel approximation to recover the rigid transformation and align IVUS images without loosing any IVUS data. We report an extensive validation with synthetic simulated data and in vivo IVUS sequences of 30 patients achieving an average reduction of the image artifact of 97% in synthetic data and 79% in real-data. Our study shows that IVUS alignment improves longitudinal analysis of the IVUS data and is a necessary step towards accurate reconstruction and volumetric measurements of 3-D IVUS. [Copyright &y& Elsevier]

Abstract: Corners and junctions are landmarks characterized by the lack of differentiability in the unit tangent to the image level curve. Detectors based on differential operators are not, by their own definition, the best posed as they require a higher degree of differentiability to yield a reliable response. We argue that a corner detector should be based on the degree of continuity of the tangent vector to the image level sets, work on the image domain and need no assumptions on neither the image local structure nor the particular geometry of the corner/junction. An operator measuring the degree of differentiability of the projection matrix on the image gradient fulfills the above requirements. Because using smoothing kernels leads to corner misplacement, we suggest an alternative fake response remover based on the receptive field inhibition of spurious details. The combination of both orientation discontinuity detection and noise inhibition produce our inhibition orientation energy (IOE) landmark locator. [Copyright &y& Elsevier]

We present a heuristic method for learning error correcting output codes matrices based on a hierarchical partition of the class space that maximizes a discriminative criterion. To achieve this goal, the optimal codeword separation is sacrificed in favor of a maximum class discrimination in the partitions. The creation of the hierarchical partition set is performed using a binary tree. As a result, a compact matrix with high discrimination power is obtained. Our method is validated using the UCI database and applied to a real problem, the classification of traffic sign images. [ABSTRACT FROM AUTHOR]

Among all filtering techniques, those based exclusively on image level sets (geometric flows) have proven to be the less sensitive to the nature of noise and the most contrast preserving. A common feature to existent curvature flows is that they penalize high curvature, regardless of the curve regularity. This constitutes a major drawback since curvature extreme values are standard descriptors of the contour geometry. We argue that an operator designed with shape recovery purposes should include a term penalizing irregularity in the curvature rather than its magnitude. To this purpose, we present a novel geometric flow that includes a function that measures the degree of local irregularity present in the curve. A main advantage is that it achieves non- trivial steady states representing a smooth model of level curves in a noisy image. Performance of our approach is compared to classical filtering techniques in terms of quality in the restored image/shape and asymptotic behavior. We empirically prove that our approach is the technique that achieves the best compromise between image quality and evolution stabilization. [ABSTRACT FROM AUTHOR]

Deformable models have received much popularity due to their ability to include high-level knowledge on the application domain into low-level image processing. Still, most proposed active contour models do not sufficiently profit from the application information and they are too generalized, leading to non-optimal final results of segmentation, tracking or 3D reconstruction processes. In this paper we propose a new deformable model defined in a statistical framework to segment objects of natural scenes. We perform a supervised learning of local appearance of the textured objects and construct a feature space using a set of co-occurrence matrix measures. Linear Discriminant Analysis allows us to obtain an optimal reduced feature space where a mixture model is applied to construct a likelihood map. Instead of using a heuristic potential field, our active model is deformed on a regularized version of the likelihood map in order to segment objects characterized by the same texture pattern. Different tests on synthetic images, natural scene and medical images show the advantages of our statistic deformable model. [ABSTRACT FROM AUTHOR]

The creation of large-scale datasets annotated by humans inevitably introduces noisy labels, leading to reduced generalization in deep-learning models. Sample selection-based learning with noisy labels is a recent approach that exhibits promising upbeat performance improvements. The selection of clean samples amongst the noisy samples is an important criterion in the learning process of these models. In this work, we delve deeper into the clean-noise split decision and highlight the aspect that effective demarcation of samples would lead to better performance. We identify the Global Noise Conundrum in the existing models, where the distribution of samples is treated globally. We propose a per-class-based local distribution of samples and demonstrate the effectiveness of this approach in having a better clean-noise split. We validate our proposal on several benchmarks — both real and synthetic, and show substantial improvements over different state-of-the-art algorithms. We further propose a new metric, classiness to extend our analysis and highlight the effectiveness of the proposed method. Source code and instructions to reproduce this paper are available at https://github.com/aldakata/CCLM/ • Label noise leads to reduced generalization in deep learning models. • Global Noise Conundrum exists in several Learning with Noisy Labels sample-selection methods. • Class-Conditional Local noise Model (CCLM) uses per-class-based local distribution of samples with local thresholds. • Class-aware decision boundary of CCLM leads to a better clean-noise split. • Locally adapted clean-noise split yielded improvements in both real and synthetic noise benchmarks. [ABSTRACT FROM AUTHOR]

Multi‐modal medical image fusion plays an important role in clinical diagnosis and works as an assistance model for clinicians. In this paper, a computed tomography‐magnetic resonance (CT‐MR) image fusion model is proposed using an optimized bio‐inspired spiking feedforward neural network in different decomposition domains. First, source images are decomposed into base (low‐frequency) and detail (high‐frequency) layer components. Low‐frequency subbands are fused using texture energy measures to capture the local energy, contrast, and small edges in the fused image. High‐frequency coefficients are fused using firing maps obtained by pixel‐activated neural model with the optimized parameters using three different optimization techniques such as differential evolution, cuckoo search, and gray wolf optimization, individually. In the optimization model, a fitness function is computed based on the edge index of resultant fused images, which helps to extract and preserve sharp edges available in the source CT and MR images. To validate the fusion performance, a detailed comparative analysis is presented among the proposed and state‐of‐the‐art methods in terms of quantitative and qualitative measures along with computational complexity. Experimental results show that the proposed method produces a significantly better visual quality of fused images meanwhile outperforms the existing methods. [ABSTRACT FROM AUTHOR]

Diagnostic medical imaging plays an imperative role in clinical assessment and treatment of medical abnormalities. The fusion of multimodal medical images merges complementary information present in the multi‐source images and provides a better interpretation with improved diagnostic accuracy. This paper presents a CT–MR neurological image fusion method using an optimised biologically inspired neural network in nonsubsampled shearlet (NSST) domain. NSST decomposed coefficients are utilised to activate the optimised neural model using particle swarm optimisation method and to generate the firing maps. Low and high‐frequency NSST subbands get fused using max‐rule based on firing maps. In the optimisation process, a fitness function is evaluated based on spatial frequency and edge index of the resultant fused image. To analyse the fusion performance, extensive experiments are conducted on the different CT–MR neurological image dataset. Objective performance is evaluated based on different metrics to highlight the clarity, contrast, correlation, visual quality, complementary information, salient information, and edge information present in the fused images. Experimental results show that the proposed method is able to provide better‐fused images and outperforms other existing methods in both visual and quantitative assessments. [ABSTRACT FROM AUTHOR]

Diagnostic medical imaging plays an imperative role in clinical assessment and treatment of medical abnormalities. The fusion of multimodal medical images merges complementary information present in the multi-source images and provides a better interpretation with improved diagnostic accuracy. This paper presents a CT–MR neurological image fusion method using an optimised biologically inspired neural network in nonsubsampled shearlet (NSST) domain. NSST decomposed coefficients are utilised to activate the optimised neural model using particle swarm optimisation method and to generate the firing maps. Low and high-frequency NSST subbands get fused using max-rule based on firing maps. In the optimisation process, a fitness function is evaluated based on spatial frequency and edge index of the resultant fused image. To analyse the fusion performance, extensive experiments are conducted on the different CT–MR neurological image dataset. Objective performance is evaluated based on different metrics to highlight the clarity, contrast, correlation, visual quality, complementary information, salient information, and edge information present in the fused images. Experimental results show that the proposed method is able to provide better-fused images and outperforms other existing methods in both visual and quantitative assessments. [ABSTRACT FROM AUTHOR]

Highlights • MAFood-121 with annotations for SL and ML tasks has been made public here. • MTA has been introduced to assess the coherence of the tasks results. • RUMTL improve the coherence of the outputs between the classes of different tasks. • RUMTL outperform the multi-task food classification in two food images datasets. Abstract Food plays an important role in several aspects of our daily life. Several computer vision approaches have been proposed for tackling food analysis problems, but very little effort has been done in developing methodologies that could take profit of the existent correlation between tasks. In this paper, we propose a new multi-task model that is able to simultaneously predict different food-related tasks, e.g. dish, cuisine and food categories. Here, we extend the homoscedastic uncertainty modeling to allow single-label and multi-label classification and propose a regularization term, which jointly weighs the tasks as well as their correlations. Furthermore, we propose a new Multi-Attribute Food dataset and a new metric, Multi-Task Accuracy. We prove that using both our uncertainty-based loss and the class regularization term, we are able to improve the coherence of outputs between different tasks. Moreover, we outperform the use of task-specific models on classical measures like accuracy or F 1 . [ABSTRACT FROM AUTHOR]

Wearable cameras can gather large amounts of image data that provide rich visual information about the daily activities of the wearer. Motivated by the large number of health applications that could be enabled by the automatic recognition of daily activities, such as lifestyle characterization for habit improvement, context-aware personal assistance and tele-rehabilitation services, we propose a system to classify 21 daily activities from photo-streams acquired by a wearable photo-camera. Our approach combines the advantages of a late fusion ensemble strategy relying on convolutional neural networks at image level with the ability of recurrent neural networks to account for the temporal evolution of high-level features in photo-streams without relying on event boundaries. The proposed batch-based approach achieved an overall accuracy of 89.85%, outperforming state-of-the-art end-to-end methodologies. These results were achieved on a dataset consists of 44,902 egocentric pictures from three persons captured during 26 days in average. [ABSTRACT FROM AUTHOR]

Recent evidence suggests that shorter telomere length (TL) is associated with neuro degenerative diseases and aging related outcomes. The causal association between TL and brain characteristics represented by image derived phenotypes (IDPs) from different magnetic resonance imaging (MRI) modalities remains unclear. Here, we use two-sample Mendelian randomization (MR) to systematically assess the causal relationships between TL and 3,935 brain IDPs. Overall, the MR results suggested that TL was causally associated with 193 IDPs with majority representing diffusion metrics in white matter tracts. 68 IDPs were negatively associated with TL indicating that longer TL causes decreasing in these IDPs, while the other 125 were associated positively (longer TL leads to increased IDPs measures). Among them, ten IDPs have been previously reported as informative biomarkers to estimate brain age. However, the effect direction between TL and IDPs did not reflect the observed direction between aging and IDPs: longer TL was associated with decreases in fractional anisotropy and increases in axial, radial and mean diffusivity. For instance, TL was positively associated with radial diffusivity in the left perihippocampal cingulum tract and with mean diffusivity in right perihippocampal cingulum tract. Our results revealed a causal role of TL on white matter integrity which makes it a valuable factor to be considered when brain age is estimated and investigated. [ABSTRACT FROM AUTHOR]

We developed a novel interpretable biological heart age estimation model using cardiovascular magnetic resonance radiomics measures of ventricular shape and myocardial character. We included 29,996 UK Biobank participants without cardiovascular disease. Images were segmented using an automated analysis pipeline. We extracted 254 radiomics features from the left ventricle, right ventricle, and myocardium of each study. We then used Bayesian ridge regression with tenfold cross-validation to develop a heart age estimation model using the radiomics features as the model input and chronological age as the model output. We examined associations of radiomics features with heart age in men and women, observing sex-differential patterns. We subtracted actual age from model estimated heart age to calculate a "heart age delta", which we considered as a measure of heart aging. We performed a phenome-wide association study of 701 exposures with heart age delta. The strongest correlates of heart aging were measures of obesity, adverse serum lipid markers, hypertension, diabetes, heart rate, income, multimorbidity, musculoskeletal health, and respiratory health. This technique provides a new method for phenotypic assessment relating to cardiovascular aging; further studies are required to assess whether it provides incremental risk information over current approaches. [ABSTRACT FROM AUTHOR]

Abstract: X-ray angiography is widely used in cardiac disease diagnosis during or prior to intravascular interventions. The diaphragm motion and the heart beating induce gray-level changes, which are one of the main obstacles in quantitative analysis of myocardial perfusion. In this paper we focus on detecting the diaphragm border in both single images or whole X-ray angiography sequences. We show that the proposed method outperforms state of the art approaches. We extend a previous publicly available data set, adding new ground truth data. We also compose another set of more challenging images, thus having two separate data sets of increasing difficulty. Finally, we show three applications of our method: (1) a strategy to reduce false positives in vessel enhanced images; (2) a digital diaphragm removal algorithm; (3) an improvement in Myocardial Blush Grade semi-automatic estimation. [Copyright &y& Elsevier]

Abstract: We present ECOC-DRF, a framework where potential functions for Discriminative Random Fields are formulated as an ensemble of classifiers. We introduce the label trick, a technique to express transitions in the pairwise potential as meta-classes. This allows to independently learn any possible transition between labels without assuming any pre-defined model. The Error Correcting Output Codes matrix is used as ensemble framework for the combination of margin classifiers. We apply ECOC-DRF to a large set of classification problems, covering synthetic, natural and medical images for binary and multi-class cases, outperforming state-of-the art in almost all the experiments. [Copyright &y& Elsevier]

Abstract: In this work, a new one-class classification ensemble strategy called approximate polytope ensemble is presented. The main contribution of the paper is threefold. First, the geometrical concept of convex hull is used to define the boundary of the target class defining the problem. Expansions and contractions of this geometrical structure are introduced in order to avoid over-fitting. Second, the decision whether a point belongs to the convex hull model in high dimensional spaces is approximated by means of random projections and an ensemble decision process. Finally, a tiling strategy is proposed in order to model non-convex structures. Experimental results show that the proposed strategy is significantly better than state of the art one-class classification methods on over 200 datasets. [Copyright &y& Elsevier]

In this article, a novel technique for user's authentication and verification using gait as a biometric unobtrusive pattern is proposed. The method is based on a two stages pipeline. First, a general activity recognition classifier is personalized for an specific user using a small sample of her/his walking pattern. As a result, the system is much more selective with respect to the new walking pattern. A second stage verifies whether the user is an authorized one or not. This stage is defined as a one-class classification problem. In order to solve this problem, a four-layer architecture is built around the geometric concept of convex hull. This architecture allows to improve robustness to outliers, modeling non-convex shapes, and to take into account temporal coherence information. Two different scenarios are proposed as validation with two different wearable systems. First, a custom high-performance wearable system is built and used in a free environment. A second dataset is acquired from an Android-based commercial device in a 'wild' scenario with rough terrains, adversarial conditions, crowded places and obstacles. Results on both systems and datasets are very promising, reducing the verification error rates by an order of magnitude with respect to the state-of-the-art technologies. [ABSTRACT FROM AUTHOR]

Abstract: A standard way to deal with multi-class categorization problems is by the combination of binary classifiers in a pairwise voting procedure. Recently, this classical approach has been formalized in the Error-Correcting Output Codes (ECOC) framework. In the ECOC framework, the one-versus-one coding demonstrates to achieve higher performance than the rest of coding designs. The binary problems that we train in the one-versus-one strategy are significantly smaller than in the rest of designs, and usually easier to be learnt, taking into account the smaller overlapping between classes. However, a high percentage of the positions coded by zero of the coding matrix, which implies a high sparseness degree, does not codify meta-class membership information. In this paper, we show that using the training data we can redefine without re-training, in a problem-dependent way, the one-versus-one coding matrix so that the new coded information helps the system to increase its generalization capability. Moreover, the new re-coding strategy is generalized to be applied over any binary code. The results over several UCI Machine Learning repository data sets and two real multi-class problems show that performance improvements can be obtained re-coding the classical one-versus-one and Sparse random designs compared to different state-of-the-art ECOC configurations. [Copyright &y& Elsevier]

Traffic sign classification represents a classical application of multi-object recognition processing in uncontrolled adverse environments. Lack of visibility, illumination changes, and partial occlusions are just a few problems. In this paper, we introduce a novel system for multi-class classification of traffic signs based on error correcting output codes (ECOC). ECOC is based on an ensemble of binary classifiers that are trained on bi-partition of classes. We classify a wide set of traffic signs types using robust error correcting codings. Moreover, we introduce the novel β-correction decoding strategy that outperforms the state-of-the-art decoding techniques, classifying a high number of classes with great success. [ABSTRACT FROM AUTHOR]

In this paper, we present an open source Error-Correcting Output Codes (ECOC) library. The ECOC framework is a powerful tool to deal with multi-class categorization problems. This library contains both state-of-the-art coding (one-versus-one, one-versus-all, dense random, sparse random, DECOC, forest-ECOC, and ECOC-ONE) and decoding designs (hamming, euclidean, inverse hamming, laplacian, β-density, attenuated, loss-based, probabilistic kernel-based, and loss-weighted) with the parameters defined by the authors, as well as the option to include your own coding, decoding, and base classifier. [ABSTRACT FROM AUTHOR]

A common way to model multiclass classification problems is to design a set of binary classifiers and to combine them. Error-Correcting Output Codes (ECOC) represent a successful framework to deal with these type of problems. Recent works in the ECOC framework showed significant performance improvements by means of new problem-dependent designs based on the ternary ECOC framework. The ternary framework contains a larger set of binary problems because of the use of a "do not care" symbol that allows us to ignore some classes by a given classifier. However, there are no proper studies that analyze the effect of the new symbol at the decoding step, In this paper, we present a taxonomy that embeds all binary and ternary ECOC decoding strategies into four groups. We show that the zero symbol introduces two kinds of biases that require redefinition of the decoding design. A new type of decoding measure is proposed, and two novel decoding strategies are defined. We evaluate the state-of-the-art coding and decoding strategies over a set of UCI Machine Learning Repository data sets and into a real traffic sign categorization problem. The experimental results show that, following the new decoding strategies, the performance of the ECOC design is significantly improved. [ABSTRACT FROM AUTHOR]

Abstract: Error-correcting output codes (ECOC) represent a successful framework to deal with multi-class categorization problems based on combining binary classifiers. With the extension of the binary ECOC to the ternary ECOC framework, ECOC designs have been proposed in order to better adapt to distributions of the data. In order to decode ternary matrices, recent works redefined many decoding strategies that were formulated to deal with just two symbols. However, the coding step also is affected, and therefore, it requires to be reconsidered. In this paper, we present a new formulation of the ternary ECOC distance and the error-correcting capabilities in the ternary ECOC framework. Based on the new measure, we stress on how to design coding matrices preventing codification ambiguity and propose a new sparse random coding matrix with ternary distance maximization. The results on a wide set of UCI Machine Learning Repository data sets and in a real speed traffic sign categorization problem show that when the coding design satisfies the new ternary measures, significant performance improvement is obtained independently of the decoding strategy applied. [Copyright &y& Elsevier]

Despite recovering a normal coronary flow after acute myocardial infarction, percutaneous coronary intervention does not guarantee a proper perfusion (irrigation) of the infarcted area. This damage in microcirculation integrity may detrimentally affect the patient survival. Visual assessment of the myocardium opacification in contrast angiography serves to define a subjective score of the microcirculation integrity myocardial blush analysis (MBA). Although MBA correlates with patient prognosis its visual assessment is a very difficult task that requires of a highly expertise training in order to achieve a good intraobserver and interobserver agreement. In this paper, we provide objective descriptors of the myocardium staining pattern by analyzing the spectrum of the image local statistics. The descriptors proposed discriminate among the different phenomena observed in the angiographic sequence and allow defining an objective score of the myocardial perfusion. [ABSTRACT FROM AUTHOR]

Abstract: The error correcting output codes (ECOC) technique is a useful way to extend any binary classifier to the multiclass case. The design of an ECOC matrix usually considers an a priori fixed number of dichotomizers. We argue that the selection and number of dichotomizers must depend on the performance of the ensemble code in relation to the problem domain. In this paper, we present a novel approach that improves the performance of any initial output coding by extending it in a sub-optimal way. The proposed strategy creates the new dichotomizers by minimizing the confusion matrix among classes guided by a validation subset. A weighted methodology is proposed to take into account the different relevance of each dichotomizer. As a result, overfitting is avoided and small codes with good generalization performance are obtained. In the decoding step, we introduce a new strategy that follows the principle that positions coded with the symbol zero should have small influence in the results. We compare our strategy to other well-known ECOC strategies on the UCI database, and the results show it represents a significant improvement. [Copyright &y& Elsevier]

We present a novel approach for retrieval of object categories based on a novel type of image representation: the Generalized Correlogram (GC). In our image representation, the object is described as a constellation of GCs, where each one encodes information about some local part and the spatial relations from this part to others (that is, the part's context). We show how such a representation can be used with fast procedures that learn the object category with weak supervision and efficiently match the model of the object against large collections of images. In the learning stage, we show that, by integrating our representation with Boosting, the system is able to obtain a compact model that is represented by very few features, where each feature conveys key properties about the object's parts and their spatial arrangement. In the matching step, we propose direct procedures that exploit our representation for efficiently considering spatial coherence between the matching of local parts. Combined with an appropriate data organization such as Inverted Files, we show that thousands of images can be evaluated efficiently. The framework has been applied to different standard databases, and we show that our results are favorably compared against state-of-the-art methods in both computational cost and accuracy. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we present a novel methodology to detect and recognize objects in cluttered scenes by proposing boosted contextual descriptors of landmarks in a framework of multi-class object recognition. To detect a sample of the object class, Boosted Landmarks identify landmark candidates in the image and define a constellation of contextual descriptors able to capture the spatial relationship among them. To classify the object, we consider the problem of multi-class classification with a battery of classifiers trained to share their knowledge among classes. For this purpose, we extend the Error Correcting Output Codes technique proposing a methodology based on embedding a forest of optimal tree structures. We validated our approach using public data-sets from the UCI and Caltech databases. Furthermore, we show results of the technique applied to a real computer vision problem: detection and categorization of traffic signs. [Copyright &y& Elsevier]

The article presents engineering research that describes the use of class-conditional independent component analysis in the Bayesian classification, quality rating, and visual inspection of cork stoppers. The best results for comparing and evaluating cork performance was achieved using Bayesian classification through probabilistic modeling in a high-dimensional space.

Abstract: Wireless capsule endoscopy involves inspection of hours of video material by a highly qualified professional. Time episodes corresponding to intestinal contractions, which are of interest to the physician constitute about 1% of the video. The problem is to label automatically time episodes containing contractions so that only a fraction of the video needs inspection. As the classes of contraction and non-contraction images in the video are largely imbalanced, ROC curves are used to optimize the trade-off between false positive and false negative rates. Classifier ensemble methods and simple classifiers were examined. Our results reinforce the claims from recent literature that classifier ensemble methods specifically designed for imbalanced problems have substantial advantages over simple classifiers and standard classifier ensembles. By using ROC curves with the bagging ensemble method the inspection time can be drastically reduced at the expense of a small fraction of missed contractions. [Copyright &y& Elsevier]

Abstract: An efficient snake formulation should conform to the idea of picking the smoothest curve among all the shapes approximating an object of interest. In current geodesic snakes, the regularizing curvature also affects the convergence stage, hindering the latter at concave regions. In the present work, we make use of characteristic functions to define a novel geodesic formulation that decouples regularity and convergence. This term decoupling endows the snake with higher adaptability to non-convex shapes. Convergence is ensured by splitting the definition of the external force into an attractive vector field and a repulsive one. In our paper, we propose to use likelihood maps as approximation of characteristic functions of object appearance. The better efficiency and accuracy of our decoupled scheme are illustrated in the particular case of feature space-based segmentation. [Copyright &y& Elsevier]

Brain age can be estimated using different Magnetic Resonance Imaging (MRI) modalities including diffusion MRI. Recent studies demonstrated that white matter (WM) tracts that share the same function might experience similar alterations. Therefore, in this work, we sought to investigate such issue focusing on five WM bundles holding that feature that is Association, Brainstem, Commissural, Limbic and Projection fibers, respectively. For each tract group, we estimated brain age for 15,335 healthy participants from United Kingdom Biobank relying on diffusion MRI data derived endophenotypes, Bayesian ridge regression modeling and 10 fold-cross validation. Furthermore, we estimated brain age for an Ensemble model that gathers all the considered WM bundles. Association analysis was subsequently performed between the estimated brain age delta as resulting from the six models, that is for each tract group as well as for the Ensemble model, and 38 daily life style measures, 14 cardiac risk factors and cardiovascular magnetic resonance imaging features and genetic variants. The Ensemble model that used all tracts from all fiber groups (FG) performed better than other models to estimate brain age. Limbic tracts based model reached the highest accuracy with a Mean Absolute Error (MAE) of 5.08, followed by the Commissural ( MAE = 5.23 ), Association ( MAE = 5.24 ), and Projection ( MAE = 5.28 ) ones. The Brainstem tracts based model was the less accurate achieving a MAE of 5.86. Accordingly, our study suggests that the Limbic tracts experience less brain aging or allows for more accurate estimates compared to other tract groups. Moreover, the results suggest that Limbic tract leads to the largest number of significant associations with daily lifestyle factors than the other tract groups. Lastly, two SNPs were significantly (p value < 5 E - 8 ) associated with brain age delta in the Projection fibers. Those SNPs are mapped to HIST1H1A and SLC17A3 genes. [ABSTRACT FROM AUTHOR]

• An unsupervised model is proposed for the discovery of social and nutritional traits. • Our proposed modular system allows an individual or joint applicability and analysis. • Social-eating metrics help to quantify the camera wearer's nutritional behaviour. • Deep learning models proved to properly embed the behaviour information over time. • Egocentric visual data exhibits to be a powerful resource for behaviour understanding. Nutrition and social interactions are both key aspects of the daily lives of humans. In this work, we propose a system to evaluate the influence of social interaction in the nutritional habits of a person from a first-person perspective. In order to detect the routine of an individual, we construct a nutritional behaviour pattern discovery model, which outputs routines over a number of days. Our method evaluates similarity of routines with respect to visited food-related scenes over the collected days, making use of Dynamic Time Warping, as well as considering social engagement and its correlation with food-related activities. The nutritional and social descriptors of the collected days are evaluated and encoded using an LSTM Autoencoder. Later, the obtained latent space is clustered to find similar days unaffected by outliers using the Isolation Forest method. Moreover, we introduce a new score metric to evaluate the performance of the proposed algorithm. We validate our method on 104 days and more than 100 k egocentric images gathered by 7 users. Several different visualizations are evaluated for the understanding of the findings. Our results demonstrate good performance and applicability of our proposed model for social-related nutritional behaviour understanding. At the end, relevant applications of the model are discussed by analysing the discovered routine of particular individuals. [ABSTRACT FROM AUTHOR]

Leveraging inexpensive and human intervention-based annotating methodologies, such as crowdsourcing and web crawling, often leads to datasets with noisy labels. Noisy labels can have a detrimental impact on the performance and generalization of deep neural networks. Robust models that are able to handle and mitigate the effect of these noisy labels are thus essential. In this work, we explore the open challenges of neural network memorization and uncertainty in creating robust learning algorithms with noisy labels. To overcome them, we propose a novel framework called "Bayesian DivideMix++" with two critical components: (i) DivideMix++, to enhance the robustness against memorization and (ii) Monte-Carlo MixMatch, which focuses on improving the effectiveness towards label uncertainty. DivideMix++ improves the pipeline by integrating the warm-up and augmentation pipeline with self-supervised pre-training and dedicated different data augmentations for loss analysis and backpropagation. Monte-Carlo MixMatch leverages uncertainty measurements to mitigate the influence of uncertain samples by reducing their weight in the data augmentation MixMatch step. We validate our proposed pipeline using four datasets encompassing various synthetic and real-world noise settings. We demonstrate the effectiveness and merits of our proposed pipeline using extensive experiments. Bayesian DivideMix++ outperforms the state-of-the-art models by considerable differences in all experiments. Our findings underscore the potential of leveraging these modifications to enhance the performance and generalization of deep neural networks in practical scenarios. [ABSTRACT FROM AUTHOR]

• Lung nodule segmentation is essential for determining nodule volume and growth. • Convolutional neural networks outperformed all the other segmentation algorithms. • New soft asymmetric loss function demonstrated high efficiency and stability. • Innovative fit to segmentation mask provides accurate results on object borders. Background and objective: An accurate segmentation of lung nodules in computed tomography images is a crucial step for the physical characterization of the tumour. Being often completely manually accomplished, nodule segmentation turns to be a tedious and time-consuming procedure and this represents a high obstacle in clinical practice. In this paper, we propose a novel Convolutional Neural Network for nodule segmentation that combines a light and efficient architecture with innovative loss function and segmentation strategy. Methods: In contrast to most of the standard end-to-end architectures for nodule segmentation, our network learns the context of the nodules by producing two masks representing all the background and secondary-important elements in the Computed Tomography scan. The nodule is detected by subtracting the context from the original scan image. Additionally, we introduce an asymmetric loss function that automatically compensates for potential errors in the nodule annotations. We trained and tested our Neural Network on the public LIDC-IDRI database, compared it with the state of the art and run a pseudo-Turing test between four radiologists and the network. Results: The results proved that the behaviour of the algorithm is very near to the human performance and its segmentation masks are almost indistinguishable from the ones made by the radiologists. Our method clearly outperforms the state of the art on CT nodule segmentation in terms of F1 score and IoU of 3.3 % and 4.7 % , respectively. Conclusions: The main structure of the network ensures all the properties of the UNet architecture, while the Multi Convolutional Layers give a more accurate pattern recognition. The newly adopted solutions also increase the details on the border of the nodule, even under the noisiest conditions. This method can be applied now for single CT slice nodule segmentation and it represents a starting point for the future development of a fully automatic 3D segmentation software. [ABSTRACT FROM AUTHOR]

Rapid and accurate detection of COVID-19 is a crucial step to control the virus. For this purpose, the authors designed a web-based COVID-19 detector using efficient dual attention networks, called 'EDANet'. The EDANet architecture is based on inverted residual structures to reduce the model complexity and dual attention mechanism with position and channel attention blocks to enhance the discriminant features from the different layers of the network. Although the EDANet has only 4.1 million parameters, the experimental results demonstrate that it achieves the state-of-the-art results on the COVIDx data set in terms of accuracy and sensitivity of 96 and $94\%$94%. The web application is available at the following link: https://covid19detector-cxr.herokuapp.com/. [ABSTRACT FROM AUTHOR]

Purpose: An intraluminal coronary stent is a metal scaffold deployed in a stenotic artery during percutaneous coronary intervention (PCI). In order to have an effective deployment, a stent should be optimally placed with regard to anatomical structures such as bifurcations and stenoses. Intravascular ultrasound (IVUS) is a catheter‐based imaging technique generally used for PCI guiding and assessing the correct placement of the stent. A novel approach that automatically detects the boundaries and the position of the stent along the IVUS pullback is presented. Such a technique aims at optimizing the stent deployment. Methods: The method requires the identification of the stable frames of the sequence and the reliable detection of stent struts. Using these data, a measure of likelihood for a frame to contain a stent is computed. Then, a robust binary representation of the presence of the stent in the pullback is obtained applying an iterative and multiscale quantization of the signal to symbols using the Symbolic Aggregate approXimation algorithm. Results: The technique was extensively validated on a set of 103 IVUS of sequences of in vivo coronary arteries containing metallic and bioabsorbable stents acquired through an international multicentric collaboration across five clinical centers. The method was able to detect the stent position with an overall F‐measure of 86.4%, a Jaccard index score of 75% and a mean distance of 2.5 mm from manually annotated stent boundaries, and in bioabsorbable stents with an overall F‐measure of 88.6%, a Jaccard score of 77.7 and a mean distance of 1.5 mm from manually annotated stent boundaries. Additionally, a map indicating the distance between the lumen and the stent along the pullback is created in order to show the angular sectors of the sequence in which the malapposition is present. Conclusions: Results obtained comparing the automatic results vs the manual annotation of two observers shows that the method approaches the interobserver variability. Similar performances are obtained on both metallic and bioabsorbable stents, showing the flexibility and robustness of the method. [ABSTRACT FROM AUTHOR]

Deep neural networks represent a compelling technique to tackle complex real-world problems, but are over-parameterized and often suffer from over- or under-confident estimates. Deep ensembles have shown better parameter estimations and often provide reliable uncertainty estimates that contribute to the robustness of the results. In this work, we propose a new metric to identify samples that are hard to classify. Our metric is defined as coincidence score for deep ensembles which measures the agreement of its individual models. The main hypothesis we rely on is that deep learning algorithms learn the low-loss samples better compared to large-loss samples. In order to compensate for this, we use controlled over-sampling on the identified "hard" samples using proper data augmentation schemes to enable the models to learn those samples better. We validate the proposed metric using two public food datasets on different backbone architectures and show the improvements compared to the conventional deep neural network training using different performance metrics. • Food images are highly challenging. Hard samples increase the learning complexity. • Not all samples are learned equally — presence of easy and hard samples in training. • Ensemble based metric, called 'Coincidence score', is used to identify hard samples. • Controlled over-sampling on 'hard' samples to ensure better learnability. [ABSTRACT FROM AUTHOR]

Egocentric vision consists in acquiring images along the day from a first person point-of-view using wearable cameras. The automatic analysis of this information allows to discover daily patterns for improving the quality of life of the user. A natural topic that arises in egocentric vision is storytelling, that is, how to understand and tell the story relying behind the pictures. In this paper, we tackle storytelling as an egocentric sequences description problem. We propose a novel methodology that exploits information from temporally neighboring events, matching precisely the nature of egocentric sequences. Furthermore, we present a new method for multimodal data fusion consisting on a multi-input attention recurrent network. We also release the EDUB-SegDesc dataset. This is the first dataset for egocentric image sequences description, consisting of 1339 events with 3991 descriptions, from 55 days acquired by 11 people. Finally, we prove that our proposal outperforms classical attentional encoder-decoder methods for video description. [ABSTRACT FROM AUTHOR]

Saffron is a well-known product in the food industry. It is one of the spices that are sometimes adulterated with the sole motive of gaining more economic profit. Today, machine vision systems are widely used in controlling the quality of food and agricultural products as a new, non-destructive, and inexpensive approach. In this study, a machine vision system based on deep learning was used to detect fraud and saffron quality. A dataset of 1869 images was created and categorized in 6 classes including: dried saffron stigma using a dryer; dried saffron stigma using pressing method; pure stem of saffron; sunflower; saffron stem mixed with food coloring; and corn silk mixed with food coloring. A Learning-to-Augment incorporated Inception-v4 Convolutional Neural Network (LAII-v4 CNN) was developed for grading and fraud detection of saffron in images captured by smartphones. The best policies of data augmentation were selected with the proposed LAII-v4 CNN using images corrupted by Gaussian, speckle, and impulse noise to address overfitting the model. The proposed LAII-v4 CNN compared with regular CNN-based methods and traditional classifiers. Ensemble of Bagged Decision Trees, Ensemble of Boosted Decision Trees, k-Nearest Neighbor, Random Under-sampling Boosted Trees, and Support Vector Machine were used for classification of the features extracted by Histograms of Oriented Gradients and Local Binary Patterns, and selected by the Principal Component Analysis. The results showed that the proposed LAII-v4 CNN with an accuracy of 99.5% has achieved the best performance by employing batch normalization, Dropout, and leaky ReLU. • The learning to augment strategy was used for saffron fraud detection and grading. • Several AI-enhanced techniques were compared to improve classification accuracy. • Corrupted images were used to address the models' overfitting problem. • The LAII-v4 CNN achieved a classification accuracy of 99.5%. [ABSTRACT FROM AUTHOR]

Purpose: An intraluminal coronary stent is a metal mesh tube deployed in a stenotic artery during percutaneous coronary intervention (PCI), in order to prevent acute vessel occlusion. The identification of struts location and the definition of the stent shape is relevant for PCI planning and for patient follow-up. The authors present a fully automatic framework for computer-aided detection (CAD) of intracoronary stents in intravascular ultrasound (IVUS) image sequences. The CAD system is able to detect stent struts and estimate the stent shape. Methods: The proposed CAD uses machine learning to provide a comprehensive interpretation of the local structure of the vessel by means of semantic classification. The output of the classification stage is then used to detect struts and to estimate the stent shape. The proposed approach is validated using a multicentric data-set of 1,015 images from 107 IVUS sequences containing both metallic and bioabsorbable stents. Results: The method was able to detect struts in both metallic stents with an overall F-measure of 77.7% and a mean distance of 0.15 mm from manually annotated struts, and in bioabsorbable stents with an overall F-measure of 77.4% and a mean distance of 0.09 mm from manually annotated struts. Conclusions: The results are close to the interobserver variability and suggest that the system has the potential of being used as a method for aiding percutaneous interventions. [ABSTRACT FROM AUTHOR]

Background and objective Fast intravascular ultrasound (IVUS) video processing is required for calcium volume computation during the planning phase of percutaneous coronary interventional (PCI) procedures. Nonlinear multiresolution techniques are generally applied to improve the processing time by down-sampling the video frames. Methods This paper presents four different segmentation methods for calcium volume measurement, namely Threshold-based, Fuzzy c-Means (FCM), K-means, and Hidden Markov Random Field (HMRF) embedded with five different kinds of multiresolution techniques (bilinear, bicubic, wavelet, Lanczos, and Gaussian pyramid). This leads to 20 different kinds of combinations. IVUS image data sets consisting of 38,760 IVUS frames taken from 19 patients were collected using 40 MHz IVUS catheter (Atlantis® SR Pro, Boston Scientific®, pullback speed of 0.5 mm/sec.). The performance of these 20 systems is compared with and without multiresolution using the following metrics: (a) computational time; (b) calcium volume; (c) image quality degradation ratio; and (d) quality assessment ratio. Results Among the four segmentation methods embedded with five kinds of multiresolution techniques, FCM segmentation combined with wavelet-based multiresolution gave the best performance. FCM and wavelet experienced the highest percentage mean improvement in computational time of 77.15% and 74.07%, respectively. Wavelet interpolation experiences the highest mean precision-of-merit (PoM) of 94.06 ± 3.64% and 81.34 ± 16.29% as compared to other multiresolution techniques for volume level and frame level respectively. Wavelet multiresolution technique also experiences the highest Jaccard Index and Dice Similarity of 0.7 and 0.8, respectively. Multiresolution is a nonlinear operation which introduces bias and thus degrades the image. The proposed system also provides a bias correction approach to enrich the system, giving a better mean calcium volume similarity for all the multiresolution-based segmentation methods. After including the bias correction, bicubic interpolation gives the largest increase in mean calcium volume similarity of 4.13% compared to the rest of the multiresolution techniques. The system is automated and can be adapted in clinical settings. Conclusions We demonstrated the time improvement in calcium volume computation without compromising the quality of IVUS image. Among the 20 different combinations of multiresolution with calcium volume segmentation methods, the FCM embedded with wavelet-based multiresolution gave the best performance. [ABSTRACT FROM AUTHOR]

Quantitative assessment of calcified atherosclerotic volume within the coronary artery wall is vital for cardiac interventional procedures. The goal of this study is to automatically measure the calcium volume, given the borders of coronary vessel wall for all the frames of the intravascular ultrasound (IVUS) video. Three soft computing fuzzy classification techniques were adapted namely Fuzzy c-Means (FCM), K-means, and Hidden Markov Random Field (HMRF) for automated segmentation of calcium regions and volume computation. These methods were benchmarked against previously developed threshold-based method. IVUS image data sets (around 30, 600 IVUS frames) from 15 patients were collected using 40 MHz IVUS catheter (Atlantis® SR Pro, Boston Scientific®, pullback speed of 0.5 mm/s). Calcium mean volume for FCM, K-means, HMRF and threshold-based method were 37.84 ± 17.38 mm, 27.79 ± 10.94 mm, 46.44 ± 19.13 mm and 35.92 ± 16.44 mm respectively. Cross-correlation, Jaccard Index and Dice Similarity were highest between FCM and threshold-based method: 0.99, 0.92 ± 0.02 and 0.95 + 0.02 respectively. Student's t-test, z-test and Wilcoxon-test are also performed to demonstrate consistency, reliability and accuracy of the results. Given the vessel wall region, the system reliably and automatically measures the calcium volume in IVUS videos. Further, we validated our system against a trained expert using scoring: K-means showed the best performance with an accuracy of 92.80 %. Out procedure and protocol is along the line with method previously published clinically. [ABSTRACT FROM AUTHOR]