RESUMEN
We present an automatic road incident detector characterised by a low computational complexity for easy implementation in affordable devices, automatic adaptability to changes in scenery and road conditions, and automatic detection of the most common incidents (vehicles with abnormal speed, pedestrians or objects falling on the road, vehicles stopped on the shoulder, and detection of kamikaze vehicles). To achieve these goals, different tasks have been addressed: lane segmentation, identification of traffic directions, and elimination of unnecessary objects in the foreground. The proposed system has been tested on a collection of videos recorded in real scenarios with real traffic, including areas with different lighting. Self-adaptability (plug and play) to different scenarios has been tested using videos with significant scene changes. The achieved system can process a minimum of 80 video frames within the camera's field of view, covering a distance of 400 m, all within a span of 12 s. This capability ensures that vehicles travelling at speeds of 120 km/h are seamlessly detected with more than enough margin. Additionally, our analysis has revealed a substantial improvement in incident detection with respect to previous approaches. Specifically, an increase in accuracy of 2-5% in automatic mode and 2-7% in semi-automatic mode. The proposed classifier module only needs 2.3 MBytes of GPU to carry out the inference, thus allowing implementation in low-cost devices.
RESUMEN
Attention Deficit/Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder in childhood that often persists into adulthood. Objectively diagnosing ADHD can be challenging due to the reliance on subjective questionnaires in clinical assessment. Fortunately, recent advancements in artificial intelligence (AI) have shown promise in providing objective diagnoses through the analysis of medical images or activity recordings. These AI-based techniques have demonstrated accurate ADHD diagnosis; however, the growing complexity of deep learning models has introduced a lack of interpretability. These models often function as black boxes, unable to offer meaningful insights into the data patterns that characterize ADHD. OBJECTIVE: This paper proposes a methodology to interpret the output of an AI-based diagnosis system for combined ADHD in age and gender-stratified populations. METHODS: Our system is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks (CNNs) to classify spectrograms of activity windows. These windows are interpreted using occlusion maps to highlight the time-frequency patterns explaining ADHD activity. RESULTS: Significant differences in the frequency patterns between ADHD and controls both in diurnal and nocturnal activity were found for all the populations. Temporal dispersion also presented differences in the male population. CONCLUSION: The proposed interpretation techniques for CNNs highlighted gender- and age-related differences between ADHD patients and controls. Leveraging these differences could potentially lead to improved diagnostic accuracy, especially if a larger and more balanced dataset is utilized. SIGNIFICANCE: Our findings pave the way for the development of an AI-based diagnosis system for ADHD that offers interpretability, thereby providing valuable insights into the underlying etiology of the disease.
Asunto(s)
Trastorno por Déficit de Atención con Hiperactividad , Aprendizaje Profundo , Humanos , Masculino , Trastorno por Déficit de Atención con Hiperactividad/diagnóstico , Inteligencia Artificial , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND AND OBJECTIVE: This paper proposes a new and highly efficient implementation of 3D+t groupwise registration based on the free-form deformation paradigm. METHODS: Deformation is posed as a cascade of 1D convolutions, achieving great reduction in execution time for evaluation of transformations and gradients. RESULTS: The proposed method has been applied to 4D cardiac MRI and 4D thoracic CT monomodal datasets. Results show an average runtime reduction above 90%, both in CPU and GPU executions, compared with the classical tensor product formulation. CONCLUSIONS: Our implementation, although fully developed for the metric sum of squared differences, can be extended to other metrics and its adaptation to multiresolution strategies is straightforward. Therefore, it can be extremely useful to speed up image registration procedures in different applications where high dimensional data are involved.
Asunto(s)
Algoritmos , Tomografía Computarizada Cuatridimensional , Imagen por Resonancia MagnéticaRESUMEN
Groupwise image (GW) registration is customarily used for subsequent processing in medical imaging. However, it is computationally expensive due to repeated calculation of transformations and gradients. In this paper, we propose a deep learning (DL) architecture that achieves GW elastic registration of a 2D dynamic sequence on an affordable average GPU. Our solution, referred to as dGW, is a simplified version of the well-known U-net. In our GW solution, the image that the other images are registered to, referred to in the paper as template image, is iteratively obtained together with the registered images. Design and evaluation have been carried out using 2D cine cardiac MR slices from 2 databases respectively consisting of 89 and 41 subjects. The first database was used for training and validation with 66.6-33.3% split. The second one was used for validation (50%) and testing (50%). Additional network hyperparameters, which are-in essence-those that control the transformation smoothness degree, are obtained by means of a forward selection procedure. Our results show a 9-fold runtime reduction with respect to an optimization-based implementation; in addition, making use of the well-known structural similarity (SSIM) index we have obtained significative differences with dGW with respect to an alternative DL solution based on Voxelmorph.
RESUMEN
Attention Deficit/Hyperactivity Disorder (ADHD) is the most common neurobehavioral disorder in children and adolescents. However, its etiology is still unknown, and this hinders the existence of reliable, fast and inexpensive standard diagnostic methods. OBJECTIVE: This paper proposes an end-to-end methodology for automatic diagnosis of the combined type of ADHD. METHODS: Diagnosis is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks to classify spectrograms of activity windows. RESULTS: We achieve up to [Formula: see text] average sensitivity, [Formula: see text] specificity and AUC values over [Formula: see text]. Overall, our figures overcome those obtained by actigraphy-based methods reported in the literature as well as others based on more expensive (and not so convenient) acquisition methods. CONCLUSION: These results reinforce the idea that combining deep learning techniques together with actimetry can lead to a robust and efficient system for objective ADHD diagnosis. SIGNIFICANCE: Reliance on simple activity measurements leads to an inexpensive and non-invasive objective diagn-ostic method, which can be easily implemented with daily devices.
Asunto(s)
Trastorno por Déficit de Atención con Hiperactividad , Actigrafía , Actividades Cotidianas , Adolescente , Trastorno por Déficit de Atención con Hiperactividad/diagnóstico , Niño , Humanos , Redes Neurales de la ComputaciónRESUMEN
The present survey describes the state-of-the-art techniques for dynamic cardiac magnetic resonance image reconstruction. Additionally, clinical relevance, main challenges, and future trends of this image modality are outlined. Thus, this paper aims to provide a general vision about cine MRI as the standard procedure in functional evaluation of the heart, focusing on technical methodologies.
RESUMEN
Cough is a protective reflex conveying information on the state of the respiratory system. Cough assessment has been limited so far to subjective measurement tools or uncomfortable (i.e., non-wearable) cough monitors. This limits the potential of real-time cough monitoring to improve respiratory care. OBJECTIVE: This paper presents a machine hearing system for audio-based robust cough segmentation that can be easily deployed in mobile scenarios. METHODS: Cough detection is performed in two steps. First, a short-term spectral feature set is separately computed in five predefined frequency bands: [0, 0.5), [0.5, 1), [1, 1.5), [1.5, 2), and [2, 5.5125] kHz. Feature selection and combination are then applied to make the short-term feature set robust enough in different noisy scenarios. Second, high-level data representation is achieved by computing the mean and standard deviation of short-term descriptors in 300 ms long-term frames. Finally, cough detection is carried out using a support vector machine trained with data from different noisy scenarios. The system is evaluated using a patient signal database which emulates three real-life scenarios in terms of noise content. RESULTS: The system achieves 92.71% sensitivity, 88.58% specificity, and 90.69% Area Under Receiver Operating Charcteristic (ROC) curve (AUC), outperforming state-of-the-art methods. CONCLUSION: Our research outcome paves the way to create a device for cough monitoring in real-life situations. SIGNIFICANCE: Our proposal is aligned with a more comfortable and less disruptive patient monitoring, with benefits for patients (allows self-monitoring of cough symptoms), practitioners (e.g., assessment of treatments or better clinical understanding of cough patterns), and national health systems (by reducing hospitalizations).
Asunto(s)
Tos , Procesamiento de Señales Asistido por Computador , Máquina de Vectores de Soporte , Anciano , Tos/clasificación , Tos/diagnóstico , Femenino , Humanos , Masculino , Persona de Mediana Edad , Monitoreo Fisiológico/métodos , Sensibilidad y Especificidad , Relación Señal-Ruido , Espectrografía del Sonido/métodosRESUMEN
Telehealth has shown potential to improve access to healthcare cost-effectively in respiratory illness. However, it has failed to live up to expectation, in part because of poor objective measures of symptoms such as cough events, which could lead to early diagnosis or prevention. Considering the burden that these conditions constitute for national health systems, an effort is needed to foster telehealth potential by developing low-cost technology for efficient monitoring and analysis of cough events. This paper proposes the use of local Hu moments as a robust feature set for automatic cough detection in smartphone-acquired audio signals. The final system feeds a k-nearest-neighbor classifier with the extracted features. To properly evaluate the system in a diversity of noisy backgrounds, we contaminated real cough audio data with a variety of sounds including noise from both indoor and outdoor environments and noncough events (sneeze, laugh, speech, etc.). The created database allows flexible settings of signal-to-noise ratio levels between background sounds and events (cough and noncough). This evaluation was complemented using real patient data from an outpatient clinic. The system is able to detect cough events with high sensitivity (up to 88.51%) and specificity (up to 99.77%) in a variety of noisy environments, overcoming other state-of-the-art audio features. Our proposal paves the way for ubiquitous cough monitoring with minimal disruption in daily activities.
Asunto(s)
Tos/diagnóstico , Procesamiento de Señales Asistido por Computador , Espectrografía del Sonido/métodos , Anciano , Algoritmos , Femenino , Humanos , Masculino , Persona de Mediana Edad , Redes Neurales de la Computación , Enfermedades Respiratorias , Teléfono Inteligente , Máquina de Vectores de Soporte , TelemedicinaRESUMEN
The Fast Marching method is widely employed in several fields of image processing. Some years ago a Multi-Stencil version (MSFM) was introduced to improve its accuracy by solving the equation for a set of stencils and choosing the best solution at each considered node. The following work proposes a modified numerical scheme for MSFM to take into account the variation of the local cost, which has proven to be second order. The influence of the stencil set choice on the algorithm outcome with respect to stencil orthogonality and axis swapping is also explored, where stencils are taken from neighborhoods of varying radius. The experimental results show that the proposed schemes improve the accuracy of their original counterparts, and that the use of permutation-invariant stencil sets provides robustness against shifted vector coordinates in the stencil set.
RESUMEN
The potential of telemedicine in respiratory health care has not been completely unveiled in part due to the inexistence of reliable objective measurements of symptoms such as cough. Currently available cough detectors are uncomfortable and expensive at a time when generic smartphones can perform this task. However, two major challenges preclude smartphone-based cough detectors from effective deployment namely, the need to deal with noisy environments and computational cost. This paper focuses on the latter, since complex machine learning algorithms are too slow for real-time use and kill the battery in a few hours unless specific actions are taken. In this paper, we present a robust and efficient implementation of a smartphone-based cough detector. The audio signal acquired from the device's microphone is processed by computing local Hu moments as a robust feature set in the presence of background noise. We previously demonstrated that pairing Hu moments and a standard k-NN classifier achieved accurate cough detection at the expense of computation time. To speed-up k-NN search, many tree structures have been proposed. Our cough detector uses an improved vantage point (vp)-tree with optimized construction methods and a distance function that results in faster searches. We achieve 18× speed-up over classic vp-trees, and 560× over standard implementations of k-NN in state-of-the-art machine learning libraries, with classification accuracies over 93%, enabling real-time performance on low-end smartphones.
Asunto(s)
Tos/clasificación , Tos/diagnóstico , Procesamiento de Señales Asistido por Computador/instrumentación , Teléfono Inteligente , Telemedicina/instrumentación , Algoritmos , Humanos , Redes Neurales de la ComputaciónRESUMEN
Health Monitoring apps for smartphones have the potential to improve quality of life and decrease the cost of health services. However, they have failed to live up to expectation in the context of respiratory disease. This is in part due to poor objective measurements of symptoms such as cough. Real-time cough detection using smartphones faces two main challenges namely, the necessity of dealing with noisy input signals, and the need of the algorithms to be computationally efficient, since a high battery consumption would prevent patients from using them. This paper proposes a robust and efficient smartphone-based cough detection system able to keep the phone battery consumption below 25% (16% if only the detector is considered) during 24â¯h use. The proposed system efficiently calculates local image moments over audio spectrograms to feed an optimized classifier for final cough detection. Our system achieves 88.94% sensitivity and 98.64% specificity in noisy environments with a 5500× speed-up and 4× battery saving compared to the baseline implementation. Power consumption is also reduced by a minimum factor of 6 compared to existing optimized systems in the literature.
Asunto(s)
Algoritmos , Tos , Aplicaciones Móviles , Teléfono Inteligente , Adulto , Anciano , Tos/diagnóstico , Tos/fisiopatología , Femenino , Humanos , Masculino , Persona de Mediana Edad , Monitoreo Fisiológico/instrumentación , Monitoreo Fisiológico/métodosRESUMEN
This paper proposes a new cough detection system based on audio signals acquired from conventional smartphones. The system relies on local Hu moments to characterize cough events and a Λ-NN classifier to distinguish cough events from non-cough ones (speech, laugh, sneeze, etc.) and noisy sounds. To deal with the unbalance between classes, we employ Distinct-Borderline2 Synthetic Minority Oversampling Technique and a bespoke cost matrix. The system additionally features a post-processing module to avoid isolated false negatives and, this way, increases sensitivity. Evaluation has been carried out using a database comprising a variety of cough and non-cough events and different types of background noise. In this study, we specifically focused on noise likely to appear when the user is carrying the smartphone in daily activities. Different Signal to Noise Ratio values were tested ranging between -15 and 0 dB. Our experiments confirm that local Hu moments are suitable not only for characterizing cough events but also for coping with noisy environments. Results show a sensitivity of 94.17% and a specificity of 92.16% at -15 dB. Thus, our system shows potential as a reliable and place-ubiquitous monitoring device that helps patients self-manage their own respiratory diseases and avoids unreported or fabricated symptoms.
Asunto(s)
Tos/diagnóstico , Procesamiento de Señales Asistido por Computador , Teléfono Inteligente , Área Bajo la Curva , Bases de Datos Factuales , Humanos , Ruido , Sensibilidad y Especificidad , Relación Señal-Ruido , EstornudoRESUMEN
This paper presents an efficient cough detection system based on simple decision-tree classification of spectral features from a smartphone audio signal. Preliminary evaluation on voluntary coughs shows that the system can achieve 98% sensitivity and 97.13% specificity when the audio signal is sampled at full rate. With this baseline system, we study possible efficiency optimisations by evaluating the effect of downsampling below the Nyquist rate and how the system performance at low sampling frequencies can be improved by incorporating compressive sensing reconstruction schemes. Our results show that undersampling down to 400 Hz can still keep sensitivity and specificity values above 90% despite of aliasing. Furthermore, the sparsity of cough signals in the time domain allows keeping performance figures close to 90% when sampling at 100 Hz using compressive sensing schemes.
Asunto(s)
Tos/diagnóstico , Algoritmos , Fuerza Compresiva , Femenino , Humanos , Masculino , Sensibilidad y EspecificidadRESUMEN
This paper presents a common stochastic modelling framework for physiological signals which allows patient simulation following a synthesis-by-analysis approach. Within this framework, we propose a general model-based methodology able to reconstruct missing or artifacted signal intervals in cardiovascular monitoring applications. The proposed model consists of independent stages which provide high flexibility to incorporate signals of different nature in terms of shape, cross-correlation and variability. The reconstruction methodology is based on model sampling and selection based on a wide range of boundary conditions, which include prior information. Results on real data show how the proposed methodology fits the particular approaches presented so far for electrocardiogram (ECG) reconstruction and how a simple extension within the framework can significantly improve their performance.
Asunto(s)
Enfermedades Cardiovasculares/fisiopatología , Modelos Teóricos , Electrocardiografía , Humanos , Procesamiento de Señales Asistido por ComputadorRESUMEN
In this paper, we propose a stochastic model of photoplethysmographic signals that is able to synthesize an arbitrary number of other statistically equivalent signals to the one under analysis. To that end, we first preprocess the pulse signal to normalize and time-align pulses. In a second stage, we design a single-pulse model, which consists of ten parameters. In the third stage, the time evolution of this ten-parameter vector is approximated by means of two autoregressive moving average models, one for the trend and one for the residue; this model is applied after a decorrelation step which let us to process each vector component in parallel. The experiments carried out show that the model we here propose is able to maintain the main features of the original signal; this is accomplished by means of both a linear spectral analysis and also by comparing two measures obtained from a nonlinear analysis. Finally, we explore the capability of the model to: 1) track physical activity; 2) obtain statistics of clinical parameters by model sampling; and 3) recover corrupted or missing signal epochs by synthesis.
Asunto(s)
Fotopletismografía/métodos , Procesamiento de Señales Asistido por Computador , Adulto , Simulación por Computador , Humanos , Masculino , Modelos Teóricos , Dinámicas no Lineales , Análisis de Componente Principal , Reproducibilidad de los Resultados , Procesos EstocásticosRESUMEN
This paper proposes a methodology to design a physiologically realistic computer simulator of images of the left ventricle myocardium based on a patient-specific biomechanical model. The simulator takes a magnetic resonance image of a given patient at end diastole, uses a manual segmentation of that image to model the geometry of the myocardium and sets the parameters of the constitutive model used for biomechanical simulation according to a regional labeling of the contractility of the myocardium for that patient. The simulated deformations are used to warp the magnetic resonance dataset throughout the cardiac cycle to generate different image modalities. The simulator is validated by quantifying its ability to model actual deformations in a set of patients affected by an acute myocardial infarction. Specifically a high correlation has been encountered between the ejection fraction derived from the simulated end systolic deformation of the myocardium and the myocardium segmented from actual data. Additionally, most of the parameters that describe the simulated deformation compare well with reported values. Overall, the simulator is intended as a testbed for extensive comparisons of myocardial motion tracking methods due to its ability to relate the impaired myocardial function with the associated ventricular remodeling, a novel contribution in the literature of cardiac image simulators.
Asunto(s)
Simulación por Computador , Imagen por Resonancia Magnética , Miocardio/citología , Programas Informáticos , Algoritmos , Fenómenos Biomecánicos , Corazón/fisiología , Corazón/fisiopatología , Humanos , Procesamiento de Imagen Asistido por Computador , Infarto del Miocardio/diagnóstico , Infarto del Miocardio/patología , Infarto del Miocardio/fisiopatología , Miocardio/patologíaRESUMEN
Diffusion tensor imaging (DTI) constitutes the most used paradigm among the diffusion-weighted magnetic resonance imaging (DW-MRI) techniques due to its simplicity and application potential. Recently, real-time estimation in DW-MRI has deserved special attention, with several proposals aiming at the estimation of meaningful diffusion parameters during the repetition time of the acquisition sequence. Specifically focusing on DTI, the underlying model of the noise present in the acquired data is not taken into account, leading to a suboptimal estimation of the diffusion tensor. In this paper, we propose an optimal real-time estimation framework for DTI reconstruction in single-coil acquisitions. By including an online estimation of the time-changing noise variance associated to the acquisition process, the proposed method achieves the sequential best linear unbiased estimator. Results on both synthetic and real data show that our method outperforms those so far proposed, reaching the best performance of the existing proposals by processing a substantially lower number of diffusion images.
Asunto(s)
Algoritmos , Mapeo Encefálico/métodos , Imagen de Difusión Tensora/métodos , Procesamiento de Imagen Asistido por Computador/métodos , Anisotropía , HumanosRESUMEN
Attention-Deficit Hyperactivity Disorder (ADHD) is the most common mental health problem in childhood and adolescence. It is commonly diagnosed by means of subjective methods which tend to overestimate the severity of the pathology. A number of objective methods also exist, but they are either expensive or time-consuming. Some recent proposals based on nonlinear processing of activity registries have deserved special attention. Since they rely on actigraphy measurements, they are both inexpensive and non-invasive. Among these methods, those shown to have higher reliability are based on single-channel complexity assessment of the activity patterns. This way, potentially useful information related to the interaction between the different channels is discarded. In this paper we propose a new methodology for ADHD diagnosis based on joint complexity assessment of multichannel activity registries. Results on real data show that the proposed method constitute a useful diagnostic aid tool reaching 87:10% sensitivity and 84.38% specificity. The combination of ADHD indicators extracted with the proposed method with single-channel complexity-based indices previously proposed lead to sensitivity and specifity values above 90%.
Asunto(s)
Actigrafía/métodos , Actigrafía/estadística & datos numéricos , Trastorno por Déficit de Atención con Hiperactividad/diagnóstico , Trastorno por Déficit de Atención con Hiperactividad/epidemiología , Diagnóstico por Computador/métodos , Reconocimiento de Normas Patrones Automatizadas/métodos , Sistema de Registros , Adulto , Algoritmos , Femenino , Humanos , Masculino , Persona de Mediana Edad , Dinámicas no Lineales , Prevalencia , Reproducibilidad de los Resultados , Sensibilidad y Especificidad , España/epidemiologíaRESUMEN
This paper proposes a topology-preserving multiresolution elastic registration method based on a discrete Markov random field of deformations and a block-matching procedure. The method is applied to the object-based interpolation of tomographic slices. For that purpose, the fidelity of a given deformation to the data is established by a block-matching strategy based on intensity- and gradient-related features, the smoothness of the transformation is favored by an appropriate prior on the field, and the deformation is guaranteed to maintain the topology by imposing some hard constraints on the local configurations of the field. The resulting deformation is defined as the maximum a posteriori configuration. Additionally, the relative influence of the fidelity and smoothness terms is weighted by the unsupervised estimation of the field parameters. In order to obtain an unbiased interpolation result, the registration is performed both in the forward and backward directions, and the resulting transformations are combined by using the local information content of the deformation. The method is applied to magnetic resonance and computed tomography acquisitions of the brain and the torso. Quantitative comparisons offer an overall improvement in performance with respect to related works in the literature. Additionally, the application of the interpolation method to cardiac magnetic resonance images has shown that the removal of any of the main components of the algorithm results in a decrease in performance which has proven to be statistically significant.
Asunto(s)
Algoritmos , Reconocimiento de Normas Patrones Automatizadas/métodos , Intensificación de Imagen Radiográfica/métodos , Interpretación de Imagen Radiográfica Asistida por Computador/métodos , Técnica de Sustracción , Tomografía Computarizada por Rayos X/métodos , Humanos , Cadenas de Markov , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
The diagnosis and therapy planning of high prevalence pathologies such as infantile colic can be substantially improved by statistical signal processing of activity/rest registries. Assuming that colic episodes are associated to activity episodes, diagnosis aid systems should be based on preprocessing techniques able to separate real activity from rest epochs, and feature extraction methods to identify meaningful indices with diagnostic capabilities. In this paper, we propose a two step diagnosis aid methodology for infantile colic in children below 3 months old. Identification of activity periods is performed by means of a wavelet based activity filter which does not depend on the acquisition device (as so far proposed methods do). In addition, symbolic dynamic analysis is used for extraction of discriminative indices from the activity time series. Results on real data yielded 100% sensitivity and 80% specificity in a study group composed of 46 cases and 10 control subjects.