Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network

Automated tissue characterization is one of the most crucial components of a computer aided diagnosis (CAD) system for interstitial lung diseases (ILDs). Although much research has been conducted in this field, the problem remains challenging. Deep learning techniques have recently achieved impressive results in a variety of computer vision problems, raising expectations that they might be applied in other domains, such as medical image analysis. In this paper, we propose and evaluate a convolutional neural network (CNN), designed for the classification of ILD patterns. The proposed network consists of 5 convolutional layers with 2×2 kernels and LeakyReLU activations, followed by average pooling with size equal to the size of the final feature maps and three dense layers. The last dense layer has 7 outputs, equivalent to the classes considered: healthy, ground glass opacity (GGO), micronodules, consolidation, reticulation, honeycombing and a combination of GGO/reticulation. To train and evaluate the CNN, we used a dataset of 14696 image patches, derived by 120 CT scans from different scanners and hospitals. To the best of our knowledge, this is the first deep CNN designed for the specific problem. A comparative analysis proved the effectiveness of the proposed CNN against previous methods in a challenging dataset. The classification performance (~85.5%) demonstrated the potential of CNNs in analyzing lung patterns. Future work includes, extending the CNN to three-dimensional data provided by CT volume scans and integrating the proposed method into a CAD system that aims to provide differential diagnosis for ILDs as a supportive tool for radiologists.

Aplicación de técnicas de inteligencia artificial a la predicción de contaminantes atmosféricos

Abstract Air pollution is a big threat and a phenomenon that has a specific impact on human health, in addition, changes that occur in the chemical composition of the atmosphere can change the weather and cause acid rain or ozone destruction. Those are phenomena of global importance. The World Health Organization (WHO) considerates air pollution as one of the most important global priorities. Salamanca, Gto., Mexico has been ranked as one of the most polluted cities in this country. The industry of the area led to a major economic development and rapid population growth in the second half of the twentieth century. The impact in the air quality is important and significant efforts have been made to measure the concentrations of pollutants. The main pollution sources are locally based plants in the chemical and power generation sectors. The registered concerning pollutants are Sulphur Dioxide (SO2) and particles on the order of ∼10 micrometers or less (PM10). The prediction in the concentration of those pollutants can be a powerful tool in order to take preventive measures such as the reduction of emissions and alerting the affected population. In this PhD thesis we propose a model to predict concentrations of pollutants SO2 and PM10 for each monitoring booth in the Atmospheric Monitoring Network Salamanca (REDMAS - for its spanish acronym). The proposed models consider the use of meteorological variables as factors influencing the concentration of pollutants. The information used along this work is the current real data from REDMAS. In the proposed model, Artificial Neural Networks (ANN) combined with clustering algorithms are used. The type of ANN used is the Multilayer Perceptron with a hidden layer, using separate structures for the prediction of each pollutant. The meteorological variables used for prediction were: Wind Direction (WD), wind speed (WS), Temperature (T) and relative humidity (RH). Clustering algorithms, K-means and Fuzzy C-means, are used to find relationships between air pollutants and weather variables under consideration, which are added as input of the RNA. Those relationships provide information to the ANN in order to obtain the prediction of the pollutants. The results of the model proposed in this work are compared with the results of a multivariate linear regression and multilayer perceptron neural network. The evaluation of the prediction is calculated with the mean absolute error, the root mean square error, the correlation coefficient and the index of agreement. The results show the importance of meteorological variables in the prediction of the concentration of the pollutants SO2 and PM10 in the city of Salamanca, Gto., Mexico. The results show that the proposed model perform better than multivariate linear regression and multilayer perceptron neural network. The models implemented for each monitoring booth have the ability to make predictions of air quality that can be used in a system of real-time forecasting and human health impact analysis. Among the main results of the development of this thesis we can cite: A model based on artificial neural network combined with clustering algorithms for prediction with a hour ahead of the concentration of each pollutant (SO2 and PM10) is proposed. A different model was designed for each pollutant and for each of the three monitoring booths of the REDMAS. A model to predict the average of pollutant concentration in the next 24 hours of pollutants SO2 and PM10 is proposed, based on artificial neural network combined with clustering algorithms. Model was designed for each booth of the REDMAS and each pollutant separately. Resumen La contaminación atmosférica es una amenaza aguda, constituye un fenómeno que tiene particular incidencia sobre la salud del hombre. Los cambios que se producen en la composición química de la atmósfera pueden cambiar el clima, producir lluvia ácida o destruir el ozono, fenómenos todos ellos de una gran importancia global. La Organización Mundial de la Salud (OMS) considera la contaminación atmosférica como una de las más importantes prioridades mundiales. Salamanca, Gto., México; ha sido catalogada como una de las ciudades más contaminadas en este país. La industria de la zona propició un importante desarrollo económico y un crecimiento acelerado de la población en la segunda mitad del siglo XX. Las afectaciones en el aire son graves y se han hecho importantes esfuerzos por medir las concentraciones de los contaminantes. Las principales fuentes de contaminación son fuentes fijas como industrias químicas y de generación eléctrica. Los contaminantes que se han registrado como preocupantes son el Bióxido de Azufre (SO2) y las Partículas Menores a 10 micrómetros (PM10). La predicción de las concentraciones de estos contaminantes puede ser una potente herramienta que permita tomar medidas preventivas como reducción de emisiones a la atmósfera y alertar a la población afectada. En la presente tesis doctoral se propone un modelo de predicción de concentraci ón de los contaminantes más críticos SO2 y PM10 para cada caseta de monitorización de la Red de Monitorización Atmosférica de Salamanca (REDMAS). Los modelos propuestos plantean el uso de las variables meteorol ógicas como factores que influyen en la concentración de los contaminantes. La información utilizada durante el desarrollo de este trabajo corresponde a datos reales obtenidos de la REDMAS. En el Modelo Propuesto (MP) se aplican Redes Neuronales Artificiales (RNA) combinadas con algoritmos de agrupamiento. La RNA utilizada es el Perceptrón Multicapa con una capa oculta, utilizando estructuras independientes para la predicción de cada contaminante. Las variables meteorológicas disponibles para realizar la predicción fueron: Dirección de Viento (DV), Velocidad de Viento (VV), Temperatura (T) y Humedad Relativa (HR). Los algoritmos de agrupamiento K-means y Fuzzy C-means son utilizados para encontrar relaciones existentes entre los contaminantes atmosféricos en estudio y las variables meteorológicas. Dichas relaciones aportan información a las RNA para obtener la predicción de los contaminantes, la cual es agregada como entrada de las RNA. Los resultados del modelo propuesto en este trabajo son comparados con los resultados de una Regresión Lineal Multivariable (RLM) y un Perceptrón Multicapa (MLP). La evaluación de la predicción se realiza con el Error Medio Absoluto, la Raíz del Error Cuadrático Medio, el coeficiente de correlación y el índice de acuerdo. Los resultados obtenidos muestran la importancia de las variables meteorológicas en la predicción de la concentración de los contaminantes SO2 y PM10 en la ciudad de Salamanca, Gto., México. Los resultados muestran que el MP predice mejor la concentración de los contaminantes SO2 y PM10 que los modelos RLM y MLP. Los modelos implementados para cada caseta de monitorizaci ón tienen la capacidad para realizar predicciones de calidad del aire, estos modelos pueden ser implementados en un sistema que permita realizar la predicción en tiempo real y analizar el impacto en la salud de la población. Entre los principales resultados obtenidos del desarrollo de esta tesis podemos citar: Se propone un modelo basado en una red neuronal artificial combinado con algoritmos de agrupamiento para la predicción con una hora de anticipaci ón de la concentración de cada contaminante (SO2 y PM10). Se diseñó un modelo diferente para cada contaminante y para cada una de las tres casetas de monitorización de la REDMAS. Se propone un modelo de predicción del promedio de la concentración de las próximas 24 horas de los contaminantes SO2 y PM10, basado en una red neuronal artificial combinado con algoritmos de agrupamiento. Se diseñó un modelo para cada caseta de monitorización de la REDMAS y para cada contaminante por separado.

Artificial Neural Nets with Interaction of Afferents

The aim is to obtain computationally more powerful, neuro physiologically founded, artificial neurons and neural nets. Artificial Neural Nets (ANN) of the Perceptron type evolved from the original proposal by McCulloch an Pitts classical paper [1]. Essentially, they keep the computing structure of a linear machine followed by a non linear operation. The McCulloch-Pitts formal neuron (which was never considered by the author’s to be models of real neurons) consists of the simplest case of a linear computation of the inputs followed by a threshold. Networks of one layer cannot compute anylogical function of the inputs, but only those which are linearly separable. Thus, the simple exclusive OR (contrast detector) function of two inputs requires two layers of formal neurons

On the Biological Plausibility of Artificial Metaplasticity

The training algorithm studied in this paper is inspired by the biological metaplasticity property of neurons. Tested on different multidisciplinary applications, it achieves a more efficient training and improves Artificial Neural Network Performance. The algorithm has been recently proposed for Artificial Neural Networks in general, although for the purpose of discussing its biological plausibility, a Multilayer Perceptron has been used. During the training phase, the artificial metaplasticity multilayer perceptron could be considered a new probabilistic version of the presynaptic rule, as during the training phase the algorithm assigns higher values for updating the weights in the less probable activations than in the ones with higher probability

Neutron spectrometry using artificial neural networks for a bonner sphere spectrometer with 3He detector

Neutron spectra unfolding and dose equivalent calculation are complicated tasks in radiation protection, are highly dependent of the neutron energy, and a precise knowledge on neutron spectrometry is essential for all dosimetry-related studies as well as many nuclear physics experiments. In previous works have been reported neutron spectrometry and dosimetry results, by using the ANN technology as alternative solution, starting from the count rates of a Bonner spheres system with a LiI(Eu) thermal neutrons detector, 7 polyethylene spheres and the UTA4 response matrix with 31 energy bins. In this work, an ANN was designed and optimized by using the RDANN methodology for the Bonner spheres system used at CIEMAT Spain, which is composed of a He neutron detector, 12 moderator spheres and a response matrix for 72 energy bins. For the ANN design process a neutrons spectra catalogue compiled by the IAEA was used. From this compilation, the neutrons spectra were converted from lethargy to energy spectra. Then, the resulting energy ?uence spectra were re-binned by using the MCNP code to the corresponding energy bins of the He response matrix before mentioned. With the response matrix and the re-binned spectra the counts rate of the Bonner spheres system were calculated and the resulting re-binned neutrons spectra and calculated counts rate were used as the ANN training data set.

Improving Wishart Classification of Polarimetric SAR Data Using the Hopfield Neural Network Optimization Approach.

This paper proposes the optimization relaxation approach based on the analogue Hopfield Neural Network (HNN) for cluster refinement of pre-classified Polarimetric Synthetic Aperture Radar (PolSAR) image data. We consider the initial classification provided by the maximum-likelihood classifier based on the complex Wishart distribution, which is then supplied to the HNN optimization approach. The goal is to improve the classification results obtained by the Wishart approach. The classification improvement is verified by computing a cluster separability coefficient and a measure of homogeneity within the clusters. During the HNN optimization process, for each iteration and for each pixel, two consistency coefficients are computed, taking into account two types of relations between the pixel under consideration and its corresponding neighbors. Based on these coefficients and on the information coming from the pixel itself, the pixel under study is re-classified. Different experiments are carried out to verify that the proposed approach outperforms other strategies, achieving the best results in terms of separability and a trade-off with the homogeneity preserving relevant structures in the image. The performance is also measured in terms of computational central processing unit (CPU) times.

Neural network controller for active demand side management with PV energy in the residential sector

In this paper, we describe the development of a control system for Demand-Side Management in the residential sector with Distributed Generation. The electrical system under study incorporates local PV energy generation, an electricity storage system, connection to the grid and a home automation system. The distributed control system is composed of two modules: a scheduler and a coordinator, both implemented with neural networks. The control system enhances the local energy performance, scheduling the tasks demanded by the user and maximizing the use of local generation.

Air pollution data classification by SOM Neural Network

Over the last ten years, Salamanca has been considered among the most polluted cities in México. This paper presents a Self-Organizing Maps (SOM) Neural Network application to classify pollution data and automatize the air pollution level determination for Sulphur Dioxide (SO2) in Salamanca. Meteorological parameters are well known to be important factors contributing to air quality estimation and prediction. In order to observe the behavior and clarify the influence of wind parameters on the SO2 concentrations a SOM Neural Network have been implemented along a year. The main advantages of the SOM is that it allows to integrate data from different sensors and provide readily interpretation results. Especially, it is powerful mapping and classification tool, which others information in an easier way and facilitates the task of establishing an order of priority between the distinguished groups of concentrations depending on their need for further research or remediation actions in subsequent management steps. The results show a significative correlation between pollutant concentrations and some environmental variables.

Using a causal smoothing to improve the performance of an on-line neural network glucose prediction algorithm

This work evaluates a spline-based smoothing method applied to the output of a glucose predictor. Methods:Our on-line prediction algorithm is based on a neural network model (NNM). We trained/validated the NNM with a prediction horizon of 30 minutes using 39/54 profiles of patients monitored with the Guardian® Real-Time continuous glucose monitoring system The NNM output is smoothed by fitting a causal cubic spline. The assessment parameters are the error (RMSE), mean delay (MD) and the high-frequency noise (HFCrms). The HFCrms is the root-mean-square values of the high-frequency components isolated with a zero-delay non-causal filter. HFCrms is 2.90±1.37 (mg/dl) for the original profiles.

Data Mining with Enhanced Neural Networks-CMMSE

Abstract This paper presents a new method to extract knowledge from existing data sets, that is, to extract symbolic rules using the weights of an Artificial Neural Network. The method has been applied to a neural network with special architecture named Enhanced Neural Network (ENN). This architecture improves the results that have been obtained with multilayer perceptron (MLP). The relationship among the knowledge stored in the weights, the performance of the network and the new implemented algorithm to acquire rules from the weights is explained. The method itself gives a model to follow in the knowledge acquisition with ENN.

Aplicación de técnicas de inteligencia artificial para contribuir en la detección de microcalcificaciones en mamografía digitalizada

A nivel mundial, el cáncer de mama es el tipo de cáncer más frecuente además de una de las principales causas de muerte entre la población femenina. Actualmente, el método más eficaz para detectar lesiones mamarias en una etapa temprana es la mamografía. Ésta contribuye decisivamente al diagnóstico precoz de esta enfermedad que, si se detecta a tiempo, tiene una probabilidad de curación muy alta. Uno de los principales y más frecuentes hallazgos en una mamografía, son las microcalcificaciones, las cuales son consideradas como un indicador importante de cáncer de mama. En el momento de analizar las mamografías, factores como la capacidad de visualización, la fatiga o la experiencia profesional del especialista radiólogo hacen que el riesgo de omitir ciertas lesiones presentes se vea incrementado. Para disminuir dicho riesgo es importante contar con diferentes alternativas como por ejemplo, una segunda opinión por otro especialista o un doble análisis por el mismo. En la primera opción se eleva el coste y en ambas se prolonga el tiempo del diagnóstico. Esto supone una gran motivación para el desarrollo de sistemas de apoyo o asistencia en la toma de decisiones. En este trabajo de tesis se propone, se desarrolla y se justifica un sistema capaz de detectar microcalcificaciones en regiones de interés extraídas de mamografías digitalizadas, para contribuir a la detección temprana del cáncer demama. Dicho sistema estará basado en técnicas de procesamiento de imagen digital, de reconocimiento de patrones y de inteligencia artificial. Para su desarrollo, se tienen en cuenta las siguientes consideraciones: 1. Con el objetivo de entrenar y probar el sistema propuesto, se creará una base de datos de imágenes, las cuales pertenecen a regiones de interés extraídas de mamografías digitalizadas. 2. Se propone la aplicación de la transformada Top-Hat, una técnica de procesamiento digital de imagen basada en operaciones de morfología matemática. La finalidad de aplicar esta técnica es la de mejorar el contraste entre las microcalcificaciones y el tejido presente en la imagen. 3. Se propone un algoritmo novel llamado sub-segmentación, el cual está basado en técnicas de reconocimiento de patrones aplicando un algoritmo de agrupamiento no supervisado, el PFCM (Possibilistic Fuzzy c-Means). El objetivo es encontrar las regiones correspondientes a las microcalcificaciones y diferenciarlas del tejido sano. Además, con la finalidad de mostrar las ventajas y desventajas del algoritmo propuesto, éste es comparado con dos algoritmos del mismo tipo: el k-means y el FCM (Fuzzy c-Means). Por otro lado, es importante destacar que en este trabajo por primera vez la sub-segmentación es utilizada para detectar regiones pertenecientes a microcalcificaciones en imágenes de mamografía. 4. Finalmente, se propone el uso de un clasificador basado en una red neuronal artificial, específicamente un MLP (Multi-layer Perceptron). El propósito del clasificador es discriminar de manera binaria los patrones creados a partir de la intensidad de niveles de gris de la imagen original. Dicha clasificación distingue entre microcalcificación y tejido sano. ABSTRACT Breast cancer is one of the leading causes of women mortality in the world and its early detection continues being a key piece to improve the prognosis and survival. Currently, the most reliable and practical method for early detection of breast cancer is mammography.The presence of microcalcifications has been considered as a very important indicator ofmalignant types of breast cancer and its detection and classification are important to prevent and treat the disease. However, the detection and classification of microcalcifications continue being a hard work due to that, in mammograms there is a poor contrast between microcalcifications and the tissue around them. Factors such as visualization, tiredness or insufficient experience of the specialist increase the risk of omit some present lesions. To reduce this risk, is important to have alternatives such as a second opinion or a double analysis for the same specialist. In the first option, the cost increases and diagnosis time also increases for both of them. This is the reason why there is a great motivation for development of help systems or assistance in the decision making process. This work presents, develops and justifies a system for the detection of microcalcifications in regions of interest extracted fromdigitizedmammographies to contribute to the early detection of breast cancer. This systemis based on image processing techniques, pattern recognition and artificial intelligence. For system development the following features are considered: With the aim of training and testing the system, an images database is created, belonging to a region of interest extracted from digitized mammograms. The application of the top-hat transformis proposed. This image processing technique is based on mathematical morphology operations. The aim of this technique is to improve the contrast betweenmicrocalcifications and tissue present in the image. A novel algorithm called sub-segmentation is proposed. The sub-segmentation is based on pattern recognition techniques applying a non-supervised clustering algorithm known as Possibilistic Fuzzy c-Means (PFCM). The aim is to find regions corresponding to the microcalcifications and distinguish them from the healthy tissue. Furthermore,with the aim of showing themain advantages and disadvantages this is compared with two algorithms of same type: the k-means and the fuzzy c-means (FCM). On the other hand, it is important to highlight in this work for the first time the sub-segmentation is used for microcalcifications detection. Finally, a classifier based on an artificial neural network such as Multi-layer Perceptron is used. The purpose of this classifier is to discriminate froma binary perspective the patterns built from gray level intensity of the original image. This classification distinguishes between microcalcifications and healthy tissue.

Accurate characterization of multi-resonant reflectarray cells by artificial neural networks

This paper describes the accurate characterization of the reflection coefficients of a multilayered reflectarray element by means of artificial neural networks. The procedure has been tested with different RA elements related to actual specifications. Up to 9 parameters were considered and the complete reflection coefficient matrix was accurately obtained, including cross polar reflection coefficients. Results show a good agreement between simulations carried out by the Method of Moments and the ANN model outputs at RA element level, as well as with performances of the complete RA antenna designed.

Monitorización de estructuras aeronáuticas mediante técnicas de inteligencia artificial

Una de las barreras para la aplicación de las técnicas de monitorización de la integridad estructural (SHM) basadas en ondas elásticas guiadas (GLW) en aeronaves es la influencia perniciosa de las condiciones ambientales y de operación (EOC). En esta tesis se ha estudiado dicha influencia y la compensación de la misma, particularizando en variaciones del estado de carga y temperatura. La compensación de dichos efectos se fundamenta en Redes Neuronales Artificiales (ANN) empleando datos experimentales procesados con la Transformada Chirplet. Los cambios en la geometría y en las propiedades del material respecto al estado inicial de la estructura (lo daños) provocan cambios en la forma de onda de las GLW (lo que denominamos característica sensible al daño o DSF). Mediante técnicas de tratamiento de señal se puede buscar una relación entre dichas variaciones y los daños, esto se conoce como SHM. Sin embargo, las variaciones en las EOC producen también cambios en los datos adquiridos relativos a las GLW (DSF) que provocan errores en los algoritmos de diagnóstico de daño (SHM). Esto sucede porque las firmas de daño y de las EOC en la DSF son del mismo orden. Por lo tanto, es necesario cuantificar y compensar el efecto de las EOC sobre la GLW. Si bien existen diversas metodologías para compensar los efectos de las EOC como por ejemplo “Optimal Baseline Selection” (OBS) o “Baseline Signal Stretching” (BSS), estas, se emplean exclusivamente en la compensación de los efectos térmicos. El método propuesto en esta tesis mezcla análisis de datos experimentales, como en el método OBS, y modelos basados en Redes Neuronales Artificiales (ANN) que reemplazan el modelado físico requerido por el método BSS. El análisis de datos experimentales consiste en aplicar la Transformada Chirplet (CT) para extraer la firma de las EOC sobre la DSF. Con esta información, obtenida bajo diversas EOC, se entrena una ANN. A continuación, la ANN actuará como un interpolador de referencias de la estructura sin daño, generando información de referencia para cualquier EOC. La comparación de las mediciones reales de la DSF con los valores simulados por la ANN, dará como resultado la firma daño en la DSF, lo que permite el diagnóstico de daño. Este esquema se ha aplicado y verificado, en diversas EOC, para una estructura unidimensional con un único camino de daño, y para una estructura representativa de un fuselaje de una aeronave, con curvatura y múltiples elementos rigidizadores, sometida a un estado de cargas complejo, con múltiples caminos de daños. Los efectos de las EOC se han estudiado en detalle en la estructura unidimensional y se han generalizado para el fuselaje, demostrando la independencia del método respecto a la configuración de la estructura y el tipo de sensores utilizados para la adquisición de datos GLW. Por otra parte, esta metodología se puede utilizar para la compensación simultánea de una variedad medible de EOC, que afecten a la adquisición de datos de la onda elástica guiada. El principal resultado entre otros, de esta tesis, es la metodología CT-ANN para la compensación de EOC en técnicas SHM basadas en ondas elásticas guiadas para el diagnóstico de daño. ABSTRACT One of the open problems to implement Structural Health Monitoring techniques based on elastic guided waves in real aircraft structures at operation is the influence of the environmental and operational conditions (EOC) on the damage diagnosis problem. This thesis deals with the compensation of these environmental and operational effects, specifically, the temperature and the external loading, by the use of the Chirplet Transform working with Artificial Neural Networks. It is well known that the guided elastic wave form is affected by the damage appearance (what is known as the damage sensitive feature or DSF). The DSF is modified by the temperature and by the load applied to the structure. The EOC promotes variations in the acquired data (DSF) and cause mistakes in damage diagnosis algorithms. This effect promotes changes on the waveform due to the EOC variations of the same order than the damage occurrence. It is difficult to separate both effects in order to avoid damage diagnosis mistakes. Therefore it is necessary to quantify and compensate the effect of EOC over the GLW forms. There are several approaches to compensate the EOC effects such as Optimal Baseline Selection (OBS) or Baseline Signal Stretching (BSS). Usually, they are used for temperature compensation. The new method proposed here mixes experimental data analysis, as in the OBS method, and Artificial Neural Network (ANN) models to replace the physical modelling which involves the BSS method. The experimental data analysis studied is based on apply the Chirplet Transform (CT) to extract the EOC signature on the DSF. The information obtained varying EOC is employed to train an ANN. Then, the ANN will act as a baselines interpolator of the undamaged structure. The ANN generates reference information at any EOC. By comparing real measurements of the DSF against the ANN simulated values, the damage signature appears clearly in the DSF, enabling an accurate damage diagnosis. This schema has been applied in a range of EOC for a one-dimensional structure containing single damage path and two dimensional real fuselage structure with stiffener elements and multiple damage paths. The EOC effects tested in the one-dimensional structure have been generalized to the fuselage showing its independence from structural arrangement and the type of sensors used for GLW data acquisition. Moreover, it can be used for the simultaneous compensation of a variety of measurable EOC, which affects the guided wave data acquisition. The main result, among others, of this thesis is the CT-ANN methodology for the compensation of EOC in GLW based SHM technique for damage diagnosis.