A great deal of attention has been devoted to the analysis of particulate matter (PM) concentrati... more A great deal of attention has been devoted to the analysis of particulate matter (PM) concentrations in various scenarios because of their negative effects on human health. Here, we investigate how meteorological conditions can affect PM concentrations in the peculiar case of the district of the city of Lecce in the Apulia region (Southern Italy), which is characterized by the highest tumor rate of the whole region despite the absence of nearby heavy industries. We present a unified machine learning framework which combines air quality and meteorological data, either measured on ground or forecast. Our findings show that the concentrations of PM10, PM2.5, NO2 and CO are significantly associated with the meteorological conditions and suggest that it is possible to predict air quality using either ground weather observations or weather forecasts.
Computational and Mathematical Methods in Medicine, 2015
Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnet... more Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnetic resonance imaging (MRI) scans can show these variations and therefore can be used as a supportive feature for a number of neurodegenerative diseases. The hippocampus has been known to be a biomarker for Alzheimer disease and other neurological and psychiatric diseases. However, it requires accurate, robust, and reproducible delineation of hippocampal structures. Fully automatic methods are usually the voxel based approach; for each voxel a number of local features were calculated. In this paper, we compared four different techniques for feature selection from a set of 315 features extracted for each voxel: (i) filter method based on the Kolmogorov-Smirnov test; two wrapper methods, respectively, (ii) sequential forward selection and (iii) sequential backward elimination; and (iv) embedded method based on the Random Forest Classifier on a set of 10 T1-weighted brain MRIs and tested on ...
Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB), 2014
The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a p... more The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a primary role in the pathogenesis of other neurological and psychiatric diseases. This study presents a fully automated pattern recognition system for an accurate and reproducible segmentation of the hippocampus in structural Magnetic Resonance Imaging (MRI). The method was validated on a mixed cohort of 56 T1-weighted structural brain images, and consists of three processing levels: (a) Linear registration: all brain images were registered to a standard template and an automated method was applied to capture the global shape of the hippocampus. (b) Feature extraction: all voxels included in the previously selected volume were characterized by 315 features computed from local information. (c) Voxel classification: a Random Forest algorithm was used to classify voxels as belonging or not belonging to the hippocampus. In order to improve the classification performance, an adaptive learning m...
We developed a multiplex network approach for the description and recognition of structural brain... more We developed a multiplex network approach for the description and recognition of structural brain changes in the context of the early diagnosis of Alzheimer disease (AD). Our techniques can supply a convenient mathematical framework to model structural inter- and intra-subject brain similarities in magnetic resonance images (MRI) within Alzheimer disease studies. We used a set of 100 structural T1 brain scans, from subjects of the Alzheimer’s Disease Neuroimaging Initiative, including AD patients, normal controls (NC) and mild cognitive impairment (MCI) subjects. We evaluated the classification performances including the comparison of two state-of-the-art techniques, Random Forests (RF) and Support Vector Machines (SVM) . Our results show that multiplex networks can significantly improve the classification performance obtained only with the use of structural features. They can also effectively distinguish NC, MCI and AD patterns with an area under the receiver-operating-characterist...
Cognitive impairment has mainly two, non mutually exclusive, etiologies: structural or connectivi... more Cognitive impairment has mainly two, non mutually exclusive, etiologies: structural or connectivity lesions. Analogously, we present here a methodology aimed at investigating magnetic resonance imaging (MRI) scans of subject after a traumatic brain injury (TBI) to detect the presence of these heterogeneous lesions and access the information content within. In particular, we use (i) complex network topological features to capture the effect of disease on connectivity and (ii) morphological brain measurements to describe anomalous patterns from a structural perspective. This integrated base of knowledge is then used to emphasize differences arising within a cohort including normal controls and patients labeled as category-I and category-II according to their outcome after TBI. Results suggest that topological measurements provide a suitable measurement to detect category-I subjects, while structural features are effective to distinguish controls from category-II subjects.
Remote sensing images find application in several different domains, such as land cover or land u... more Remote sensing images find application in several different domains, such as land cover or land usage observation, environmental monitoring, and urbanization. This latter field has recently witnessed an interesting development with the use of remote sensing for infrastructural monitoring. In this work, we present an analysis of Sentinel-1 images, which were used to monitor the Italian provinces of Bologna and Modena located at the Emilia Region Apennines foothill. The goal of this study was the development of a machine learning-based detection system to monitor the deterioration of public aqueduct infrastructures based on Persistent Scatterer Interferometry (PSI). We evaluated the land deformation over a temporal range of five years; these series feed a k-means clustering algorithm to separate the pixels of the region according to different deformation patterns. Furthermore, we defined the critical areas as those areas where different patterns collided or overlapped. The proposed ap...
The Weather Research and Forecasting mesoscale model (WRF) has been used to simulate hourly 10m w... more The Weather Research and Forecasting mesoscale model (WRF) has been used to simulate hourly 10m wind speed. This model is able to solve atmospheric equations with a resolution up to tens of meters. However, since processes as turbulence, radiation exchange, cumulus and microphysics are represented by means of physical parameterizations, WRF surface outputs are affected by systematic errors also due to uncertainties of the initial and boundary conditions provided by global models. In this study a preliminary approach to develop bias correction and reduction is presented, based on post-processing WRF output by Artificial Neural Networks (ANN). Post-processed WRF output at a single location in the city of Taranto, in the southern part of Apulia region, has been validated against ground data from a weather monitoring station. In particular, the ANN algorithm has a feed-forward multilayer perceptron architecture. In order to achieve better correction of the bias, a feature selection h...
ABSTRACT This paper presents a fully automated algorithm for the segmentation of the Hippocampus,... more ABSTRACT This paper presents a fully automated algorithm for the segmentation of the Hippocampus, applied to 56 3D T1-weighted structural brain MRI scans. The tools system consists in three processing levels: (a) Image segmentation for the localization of volumes of interest (VOIs). All brains were linearly registered to a standard template to obtain a basic shape prior to capture the VOIs containing the Hippocampus and the peri-hippocampal region. (b) Characterization of voxels included in the selected VOIs by means of 315 features computed from the local information (image intensity, positions, local Haralik features, Haar-like filters). (c) Features classification by means of Neural Network and Random Forest classifiers, followed by comparison of the respective performances. The novelty of proposed method is the application field and the “active learning”, a procedure of training dataset selection used during learning of classification based on Pearson’s coefficient between the image to be segmented and the training dataset. The Dice coefficients of 0.81 ± 0.03 for the analyzed dataset are nevertheless comparable with the current literature for mixed- cohorts. This study suggests the value of the proposed classification approach for large-scale research studies or to assist the neuroradiologist in clinical diagnosis of brain disorders such as schizophrenia or the Alzheimer’s disease.
Parkinson’s disease (PD) is a chronic, progressive neurodegenerative disease and represents the m... more Parkinson’s disease (PD) is a chronic, progressive neurodegenerative disease and represents the most common disease of this type, after Alzheimer’s dementia. It is characterized by motor and nonmotor features and by a long prodromal stage that lasts many years. Genetic research has shown that PD is a complex and multisystem disorder. To capture the molecular complexity of this disease we used a complex network approach. We maximized the information entropy of the gene co-expression matrix betweenness to obtain a gene adjacency matrix; then we used a fast greedy algorithm to detect communities. Finally we applied principal component analysis on the detected gene communities, with the ultimate purpose of discriminating between PD patients and healthy controls by means of a random forests classifier. We used a publicly available substantia nigra microarray dataset, GSE20163, from NCBI GEO database, containing gene expression profiles for 10 PD patients and 18 normal controls. With this...
In recent years, a number of different procedures have been proposed for segmentation of remote s... more In recent years, a number of different procedures have been proposed for segmentation of remote sensing images, basing on spectral information. Model-based and machine learning strategies have been investigated in several studies. This work presents a comprehensive overview and an unbiased comparison of the most adopted segmentation strategies: Support Vector Machines (SVM), Random Forests, Neural networks, Sen2Cor, FMask and MAJA. We used a training set for learning and two different independent sets for testing. The comparison accounted for 135 images acquired from 54 different worldwide sites. We observed that machine learning segmentations are extremely reliable when the training and test are homogeneous. SVM performed slightly better than other methods. In particular, when using heterogeneous test data, SVM remained the most accurate segmentation method while state-of-the-art model-based methods such as MAJA and FMask obtained better sensitivity and precision, respectively. The...
Abstract Air pollution can increase the risk of respiratory diseases, enhancing the susceptibilit... more Abstract Air pollution can increase the risk of respiratory diseases, enhancing the susceptibility to viral and bacterial infections. Some studies suggest that small air particles facilitate the spread of viruses and also of the new coronavirus, besides the direct person-to-person contagion. However, the effects of the exposure to particulate matter and other contaminants on SARS-CoV-2 has been poorly explored. Here we examined the possible reasons why the new coronavirus differently impacted on Italian regional and provincial populations. With the help of artificial intelligence, we studied the importance of air pollution for mortality and positivity rates of the SARS-CoV-2 outbreak in Italy. We discovered that among several environmental, health, and socio-economic factors, air pollution and fine particulate matter (PM2.5), as its main component, resulted as the most important predictors of SARS-CoV-2 effects. We also found that the emissions from industries, farms, and road traffic - in order of importance - might be responsible for more than 70% of the deaths associated with SARS-CoV-2 nationwide. Given the major contribution played by air pollution (much more important than other health and socio-economic factors, as we discovered), we projected that, with an increase of 5-10% in air pollution, similar future pathogens may inflate the epidemic toll of Italy by 21-32% additional cases, whose 19-28% more positives and 4-14% more deaths. Our findings, demonstrating that fine-particulate (PM2.5) pollutant level is the most important factor to predict SARS-CoV-2 effects that would worsen even with a slight decrease of air quality, highlight that the imperative of productivity before health and environmental protection is, indeed, a short-term/small-minded resolution.
In this work we propose a novel application of Partial Differential Equations (PDEs) inpainting t... more In this work we propose a novel application of Partial Differential Equations (PDEs) inpainting techniques to two medical contexts. The first one concerning recovering of concentration maps for superparamagnetic nanoparticles, used as tracers in the framework of Magnetic Particle Imaging. The analysis is carried out by two set of simulations, with and without adding a source of noise, to show that the inpainted images preserve the main properties of the original ones. The second medical application is related to recovering data of corneal elevation maps in ophthalmology. A new procedure consisting in applying the PDEs inpainting techniques to the radial curvature image is proposed. The images of the anterior corneal surface are properly recovered to obtain an approximation error of the required precision. We compare inpainting methods based on second, third and fourth-order PDEs with standard approximation and interpolation techniques.
A great deal of attention has been devoted to the analysis of particulate matter (PM) concentrati... more A great deal of attention has been devoted to the analysis of particulate matter (PM) concentrations in various scenarios because of their negative effects on human health. Here, we investigate how meteorological conditions can affect PM concentrations in the peculiar case of the district of the city of Lecce in the Apulia region (Southern Italy), which is characterized by the highest tumor rate of the whole region despite the absence of nearby heavy industries. We present a unified machine learning framework which combines air quality and meteorological data, either measured on ground or forecast. Our findings show that the concentrations of PM10, PM2.5, NO2 and CO are significantly associated with the meteorological conditions and suggest that it is possible to predict air quality using either ground weather observations or weather forecasts.
Computational and Mathematical Methods in Medicine, 2015
Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnet... more Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnetic resonance imaging (MRI) scans can show these variations and therefore can be used as a supportive feature for a number of neurodegenerative diseases. The hippocampus has been known to be a biomarker for Alzheimer disease and other neurological and psychiatric diseases. However, it requires accurate, robust, and reproducible delineation of hippocampal structures. Fully automatic methods are usually the voxel based approach; for each voxel a number of local features were calculated. In this paper, we compared four different techniques for feature selection from a set of 315 features extracted for each voxel: (i) filter method based on the Kolmogorov-Smirnov test; two wrapper methods, respectively, (ii) sequential forward selection and (iii) sequential backward elimination; and (iv) embedded method based on the Random Forest Classifier on a set of 10 T1-weighted brain MRIs and tested on ...
Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB), 2014
The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a p... more The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a primary role in the pathogenesis of other neurological and psychiatric diseases. This study presents a fully automated pattern recognition system for an accurate and reproducible segmentation of the hippocampus in structural Magnetic Resonance Imaging (MRI). The method was validated on a mixed cohort of 56 T1-weighted structural brain images, and consists of three processing levels: (a) Linear registration: all brain images were registered to a standard template and an automated method was applied to capture the global shape of the hippocampus. (b) Feature extraction: all voxels included in the previously selected volume were characterized by 315 features computed from local information. (c) Voxel classification: a Random Forest algorithm was used to classify voxels as belonging or not belonging to the hippocampus. In order to improve the classification performance, an adaptive learning m...
We developed a multiplex network approach for the description and recognition of structural brain... more We developed a multiplex network approach for the description and recognition of structural brain changes in the context of the early diagnosis of Alzheimer disease (AD). Our techniques can supply a convenient mathematical framework to model structural inter- and intra-subject brain similarities in magnetic resonance images (MRI) within Alzheimer disease studies. We used a set of 100 structural T1 brain scans, from subjects of the Alzheimer’s Disease Neuroimaging Initiative, including AD patients, normal controls (NC) and mild cognitive impairment (MCI) subjects. We evaluated the classification performances including the comparison of two state-of-the-art techniques, Random Forests (RF) and Support Vector Machines (SVM) . Our results show that multiplex networks can significantly improve the classification performance obtained only with the use of structural features. They can also effectively distinguish NC, MCI and AD patterns with an area under the receiver-operating-characterist...
Cognitive impairment has mainly two, non mutually exclusive, etiologies: structural or connectivi... more Cognitive impairment has mainly two, non mutually exclusive, etiologies: structural or connectivity lesions. Analogously, we present here a methodology aimed at investigating magnetic resonance imaging (MRI) scans of subject after a traumatic brain injury (TBI) to detect the presence of these heterogeneous lesions and access the information content within. In particular, we use (i) complex network topological features to capture the effect of disease on connectivity and (ii) morphological brain measurements to describe anomalous patterns from a structural perspective. This integrated base of knowledge is then used to emphasize differences arising within a cohort including normal controls and patients labeled as category-I and category-II according to their outcome after TBI. Results suggest that topological measurements provide a suitable measurement to detect category-I subjects, while structural features are effective to distinguish controls from category-II subjects.
Remote sensing images find application in several different domains, such as land cover or land u... more Remote sensing images find application in several different domains, such as land cover or land usage observation, environmental monitoring, and urbanization. This latter field has recently witnessed an interesting development with the use of remote sensing for infrastructural monitoring. In this work, we present an analysis of Sentinel-1 images, which were used to monitor the Italian provinces of Bologna and Modena located at the Emilia Region Apennines foothill. The goal of this study was the development of a machine learning-based detection system to monitor the deterioration of public aqueduct infrastructures based on Persistent Scatterer Interferometry (PSI). We evaluated the land deformation over a temporal range of five years; these series feed a k-means clustering algorithm to separate the pixels of the region according to different deformation patterns. Furthermore, we defined the critical areas as those areas where different patterns collided or overlapped. The proposed ap...
The Weather Research and Forecasting mesoscale model (WRF) has been used to simulate hourly 10m w... more The Weather Research and Forecasting mesoscale model (WRF) has been used to simulate hourly 10m wind speed. This model is able to solve atmospheric equations with a resolution up to tens of meters. However, since processes as turbulence, radiation exchange, cumulus and microphysics are represented by means of physical parameterizations, WRF surface outputs are affected by systematic errors also due to uncertainties of the initial and boundary conditions provided by global models. In this study a preliminary approach to develop bias correction and reduction is presented, based on post-processing WRF output by Artificial Neural Networks (ANN). Post-processed WRF output at a single location in the city of Taranto, in the southern part of Apulia region, has been validated against ground data from a weather monitoring station. In particular, the ANN algorithm has a feed-forward multilayer perceptron architecture. In order to achieve better correction of the bias, a feature selection h...
ABSTRACT This paper presents a fully automated algorithm for the segmentation of the Hippocampus,... more ABSTRACT This paper presents a fully automated algorithm for the segmentation of the Hippocampus, applied to 56 3D T1-weighted structural brain MRI scans. The tools system consists in three processing levels: (a) Image segmentation for the localization of volumes of interest (VOIs). All brains were linearly registered to a standard template to obtain a basic shape prior to capture the VOIs containing the Hippocampus and the peri-hippocampal region. (b) Characterization of voxels included in the selected VOIs by means of 315 features computed from the local information (image intensity, positions, local Haralik features, Haar-like filters). (c) Features classification by means of Neural Network and Random Forest classifiers, followed by comparison of the respective performances. The novelty of proposed method is the application field and the “active learning”, a procedure of training dataset selection used during learning of classification based on Pearson’s coefficient between the image to be segmented and the training dataset. The Dice coefficients of 0.81 ± 0.03 for the analyzed dataset are nevertheless comparable with the current literature for mixed- cohorts. This study suggests the value of the proposed classification approach for large-scale research studies or to assist the neuroradiologist in clinical diagnosis of brain disorders such as schizophrenia or the Alzheimer’s disease.
Parkinson’s disease (PD) is a chronic, progressive neurodegenerative disease and represents the m... more Parkinson’s disease (PD) is a chronic, progressive neurodegenerative disease and represents the most common disease of this type, after Alzheimer’s dementia. It is characterized by motor and nonmotor features and by a long prodromal stage that lasts many years. Genetic research has shown that PD is a complex and multisystem disorder. To capture the molecular complexity of this disease we used a complex network approach. We maximized the information entropy of the gene co-expression matrix betweenness to obtain a gene adjacency matrix; then we used a fast greedy algorithm to detect communities. Finally we applied principal component analysis on the detected gene communities, with the ultimate purpose of discriminating between PD patients and healthy controls by means of a random forests classifier. We used a publicly available substantia nigra microarray dataset, GSE20163, from NCBI GEO database, containing gene expression profiles for 10 PD patients and 18 normal controls. With this...
In recent years, a number of different procedures have been proposed for segmentation of remote s... more In recent years, a number of different procedures have been proposed for segmentation of remote sensing images, basing on spectral information. Model-based and machine learning strategies have been investigated in several studies. This work presents a comprehensive overview and an unbiased comparison of the most adopted segmentation strategies: Support Vector Machines (SVM), Random Forests, Neural networks, Sen2Cor, FMask and MAJA. We used a training set for learning and two different independent sets for testing. The comparison accounted for 135 images acquired from 54 different worldwide sites. We observed that machine learning segmentations are extremely reliable when the training and test are homogeneous. SVM performed slightly better than other methods. In particular, when using heterogeneous test data, SVM remained the most accurate segmentation method while state-of-the-art model-based methods such as MAJA and FMask obtained better sensitivity and precision, respectively. The...
Abstract Air pollution can increase the risk of respiratory diseases, enhancing the susceptibilit... more Abstract Air pollution can increase the risk of respiratory diseases, enhancing the susceptibility to viral and bacterial infections. Some studies suggest that small air particles facilitate the spread of viruses and also of the new coronavirus, besides the direct person-to-person contagion. However, the effects of the exposure to particulate matter and other contaminants on SARS-CoV-2 has been poorly explored. Here we examined the possible reasons why the new coronavirus differently impacted on Italian regional and provincial populations. With the help of artificial intelligence, we studied the importance of air pollution for mortality and positivity rates of the SARS-CoV-2 outbreak in Italy. We discovered that among several environmental, health, and socio-economic factors, air pollution and fine particulate matter (PM2.5), as its main component, resulted as the most important predictors of SARS-CoV-2 effects. We also found that the emissions from industries, farms, and road traffic - in order of importance - might be responsible for more than 70% of the deaths associated with SARS-CoV-2 nationwide. Given the major contribution played by air pollution (much more important than other health and socio-economic factors, as we discovered), we projected that, with an increase of 5-10% in air pollution, similar future pathogens may inflate the epidemic toll of Italy by 21-32% additional cases, whose 19-28% more positives and 4-14% more deaths. Our findings, demonstrating that fine-particulate (PM2.5) pollutant level is the most important factor to predict SARS-CoV-2 effects that would worsen even with a slight decrease of air quality, highlight that the imperative of productivity before health and environmental protection is, indeed, a short-term/small-minded resolution.
In this work we propose a novel application of Partial Differential Equations (PDEs) inpainting t... more In this work we propose a novel application of Partial Differential Equations (PDEs) inpainting techniques to two medical contexts. The first one concerning recovering of concentration maps for superparamagnetic nanoparticles, used as tracers in the framework of Magnetic Particle Imaging. The analysis is carried out by two set of simulations, with and without adding a source of noise, to show that the inpainted images preserve the main properties of the original ones. The second medical application is related to recovering data of corneal elevation maps in ophthalmology. A new procedure consisting in applying the PDEs inpainting techniques to the radial curvature image is proposed. The images of the anterior corneal surface are properly recovered to obtain an approximation error of the required precision. We compare inpainting methods based on second, third and fourth-order PDEs with standard approximation and interpolation techniques.
Uploads