List of publications

@article{Gargano2019,
abstract = {God the Father with Angels (about 1330, tempera on panel) by Giotto is the Gable of the altarpiece of Baroncelli Chapel in the church of Santa Croce in Florence. Very little is known about its history since the separation from the so-called Baroncelli Polyptych. Now at the San Diego Museum of Art, the Gable had never been studied by means of scientific methods before our team took the opportunity to during the exhibition “Giotto, l’Italia”, held in Milan. Exploiting the integration of different knowledge, technologies and resources of our team, we were able to provide data for understanding the organizational model of Giotto's workshop performing non-invasive analyses with portable instruments during closing hours of exhibition (four diagnostic campaigns, six hours of work/campaign, no interruption of the exhibition). The achieved results confirm the painting technique based on different layers of pigments, a technique already used by Giotto. Combining the effectiveness of scanning MA-XRF with the responsive of IR reflectography and IR false colour, we moved step by step toward the discovery of Giotto's palette for the flesh tones in God the Father with Angels. FORS and XRF single point analyses were performed on some selected areas too. The IR reflectography results support the hypothesis of a detailed underdrawing with both thin and flat brushstrokes. By applying image-processing algorithms to the collected reflectograms, we obtained quantitative objective measures supporting the hypothesis that a guide could have been used in the realization of human figures; this means the use of sketches for the face of “God the Father” and for the faces of angels.},
author = {Gargano, M. and Galli, A. and Bonizzoni, L. and Alberti, R. and Aresi, N. and Caccia, M. and Castiglioni, I. and Interlenghi, M. and Salvatore, C. and Ludwig, N. and Martini, M.},
doi = {10.1016/j.culher.2018.09.016},
journal = {Journal of Cultural Heritage},
pages = {255-263},
title = {{The Giotto's workshop in the XXI century: looking inside the “God the Father with Angels” gable}},
url = {https://www.sciencedirect.com/science/article/pii/S1296207418302231},
volume = {36},
year = {2019},
note = {[Role: coauthor]}
}

God the Father with Angels (about 1330, tempera on panel) by Giotto is the Gable of the altarpiece of Baroncelli Chapel in the church of Santa Croce in Florence. Very little is known about its history since the separation from the so-called Baroncelli Polyptych. Now at the San Diego Museum of Art, the Gable had never been studied by means of scientific methods before our team took the opportunity to during the exhibition “Giotto, l’Italia”, held in Milan. Exploiting the integration of different knowledge, technologies and resources of our team, we were able to provide data for understanding the organizational model of Giotto's workshop performing non-invasive analyses with portable instruments during closing hours of exhibition (four diagnostic campaigns, six hours of work/campaign, no interruption of the exhibition). The achieved results confirm the painting technique based on different layers of pigments, a technique already used by Giotto. Combining the effectiveness of scanning MA-XRF with the responsive of IR reflectography and IR false colour, we moved step by step toward the discovery of Giotto's palette for the flesh tones in God the Father with Angels. FORS and XRF single point analyses were performed on some selected areas too. The IR reflectography results support the hypothesis of a detailed underdrawing with both thin and flat brushstrokes. By applying image-processing algorithms to the collected reflectograms, we obtained quantitative objective measures supporting the hypothesis that a guide could have been used in the realization of human figures; this means the use of sketches for the face of “God the Father” and for the faces of angels.

@article{Salvatore2018b,
abstract = {There is no disease-modifying treatment currently available for AD, one of the more impacting neurodegenerative diseases affecting more than 47.5 million people worldwide. The definition of new approaches for the design of proper clinical trials is highly demanded in order to achieve non-confounding results and assess more effective treatment. In this study, a cohort of 200 subjects was obtained from the Alzheimer’s Disease Neuroimaging Initiative. Subjects were followed-up for 24 months, and classified as AD (50), progressive-MCI to AD (50), stable-MCI (50), and cognitively normal (50). Structural T1-weighted MRI brain studies and neuropsychological measures of these subjects were used to train and optimize an artificial-intelligence classifier to distinguish mild-AD patients who need treatment (AD + pMCI) from subjects who do not need treatment (sMCI + CN). The classifier was able to distinguish between the two groups 24 months before AD definite diagnosis using a combination of MRI brain studies and specific neuropsychological measures, with 85% accuracy, 83% sensitivity, and 87% specificity. The combined-approach model outperformed the classification using MRI data alone (72% classification accuracy, 69% sensitivity, and 75% specificity). The patterns of morphological abnormalities localized in the temporal pole and medial-temporal cortex might be considered as biomarkers of clinical progression and evolution. These regions can be already observed 24 months before AD definite diagnosis. The best neuropsychological predictors mainly included measures of functional abilities, memory and learning, working memory, language, visuoconstructional reasoning, and complex attention, with a particular focus on some of the sub-scores of the FAQ and AVLT tests.},
author = {Salvatore, C. and Cerasa, A. and Castiglioni, I.},
doi = {10.3389/fnagi.2018.00135},
journal = {Frontiers in Aging Neuroscience},
pages = {135},
title = {{MRI characterizes the progressive course of AD and predicts conversion to Alzheimer’s dementia twenty-four months before probable diagnosis}},
url = {https://www.frontiersin.org/articles/10.3389/fnagi.2018.00135/full},
volume = {10},
year = {2018},
note = {[Role: first author]}
}

There is no disease-modifying treatment currently available for AD, one of the more impacting neurodegenerative diseases affecting more than 47.5 million people worldwide. The definition of new approaches for the design of proper clinical trials is highly demanded in order to achieve non-confounding results and assess more effective treatment. In this study, a cohort of 200 subjects was obtained from the Alzheimer’s Disease Neuroimaging Initiative. Subjects were followed-up for 24 months, and classified as AD (50), progressive-MCI to AD (50), stable-MCI (50), and cognitively normal (50). Structural T1-weighted MRI brain studies and neuropsychological measures of these subjects were used to train and optimize an artificial-intelligence classifier to distinguish mild-AD patients who need treatment (AD + pMCI) from subjects who do not need treatment (sMCI + CN). The classifier was able to distinguish between the two groups 24 months before AD definite diagnosis using a combination of MRI brain studies and specific neuropsychological measures, with 85% accuracy, 83% sensitivity, and 87% specificity. The combined-approach model outperformed the classification using MRI data alone (72% classification accuracy, 69% sensitivity, and 75% specificity). The patterns of morphological abnormalities localized in the temporal pole and medial-temporal cortex might be considered as biomarkers of clinical progression and evolution. These regions can be already observed 24 months before AD definite diagnosis. The best neuropsychological predictors mainly included measures of functional abilities, memory and learning, working memory, language, visuoconstructional reasoning, and complex attention, with a particular focus on some of the sub-scores of the FAQ and AVLT tests.

@article{Castiglioni2018,
abstract = {An increasing number of web-supported competitions is organized within the area of medical-image analysis involving worlwide participants. They allow computer scientists competing in a specific challenge to directly access standardized image data collected by large multicenter studies. Participating in such challenges is an effective way to facilitate better comparisons between new and existing computer-based image-analysis solutions. Grand Challenges in Biomedical-Image Analysis (http://grand-challenge. org) is one of...},
author = {Castiglioni, I. and Salvatore, C. and Ramirez, J. and Górriz, J.M.},
doi = {10.1016/j.jneumeth.2017.12.019},
journal = {Journal of Neuroscience Methods},
pages = {10-13},
title = {{Machine-learning neuroimaging challenge for automated diagnosis of mild cognitive impairment: lessons learnt}},
url = {https://www.sciencedirect.com/science/article/pii/S0165027017304375},
volume = {302},
year = {2018},
note = {[Role: first author | Castiglioni and Salvatore equally contributed to the paper]}
}

An increasing number of web-supported competitions is organized within the area of medical-image analysis involving worlwide participants. They allow computer scientists competing in a specific challenge to directly access standardized image data collected by large multicenter studies. Participating in such challenges is an effective way to facilitate better comparisons between new and existing computer-based image-analysis solutions. Grand Challenges in Biomedical-Image Analysis (http://grand-challenge. org) is one of...

@article{Salvatore2018a,
abstract = {Background AD is the most frequent neurodegenerative disease, severely impacting our society. Early diagnosis and prognosis are challenging tasks in the management of AD patients. New Method We implemented a machine-learning classifier for the automatic early diagnosis and prognosis of AD by means of features extracted, selected and optimized from structural MRI brain images. The classifier was designed to perform multi-label automatic classification into the following four classes: HC, ncMCI, cMCI, and AD. Results From our analyses, it emerged that MMSE and hippocampus-related measures must be included as primary measures in automatic-classification systems for both the early diagnosis and the prognosis of AD. The voting scheme mainly based on the binary-classification performances on the different four groups is the best choice to model the multi-label decision function for AD, when compared with a simple majority-vote scheme or with a scheme aimed at discriminating patients with high vs low risk of conversion to AD and therapy addressing. Comparison with Existing Method(s) The accuracies of our binary classifications were higher than or comparable to previously published methods. An improvement is needed on the approach we used to combine binary-classification outputs to obtain the final multi-label classification. Conclusions The performance of multi-label automatic-classification systems strongly depends on the choice of the voting scheme used for combining binary-classification labels.},
author = {Salvatore, C. and Castiglioni, I.},
doi = {10.1016/j.jneumeth.2017.12.016},
journal = {Journal of Neuroscience Methods},
pages = {58-65},
title = {{A Wrapped Multi-label Classifier for the Automatic Diagnosis and Prognosis of Alzheimer’s Disease}},
url = {https://www.sciencedirect.com/science/article/pii/S016502701730434X},
volume = {302},
year = {2018},
note = {[Role: first author, corresponding author]}
}

Background AD is the most frequent neurodegenerative disease, severely impacting our society. Early diagnosis and prognosis are challenging tasks in the management of AD patients. New Method We implemented a machine-learning classifier for the automatic early diagnosis and prognosis of AD by means of features extracted, selected and optimized from structural MRI brain images. The classifier was designed to perform multi-label automatic classification into the following four classes: HC, ncMCI, cMCI, and AD. Results From our analyses, it emerged that MMSE and hippocampus-related measures must be included as primary measures in automatic-classification systems for both the early diagnosis and the prognosis of AD. The voting scheme mainly based on the binary-classification performances on the different four groups is the best choice to model the multi-label decision function for AD, when compared with a simple majority-vote scheme or with a scheme aimed at discriminating patients with high vs low risk of conversion to AD and therapy addressing. Comparison with Existing Method(s) The accuracies of our binary classifications were higher than or comparable to previously published methods. An improvement is needed on the approach we used to combine binary-classification outputs to obtain the final multi-label classification. Conclusions The performance of multi-label automatic-classification systems strongly depends on the choice of the voting scheme used for combining binary-classification labels.

@inproceedings{Ludwig2018,
abstract = {The Giotto’s masterpiece God the Father with Angels, never investigated till now, was studied by our team of local researchers, involved in application of scientific methods for cultural heritage since many years. Exploiting the integration of different knowledges, technologies and resources of our team, we were able to provide data to understand the painting technique, the pigment used and the underdrawing of this Giotto’s painting. We performed the following non-invasive analyses: Macro-XRF scanning (MA-XRF), Fiber optic reflectance spectroscopy (FORS), high resolution IR scanning reflectography, infrared false color (IRFC). Only portable instrumentations were used, with operating times compatible with the opening hours of exhibition. In particular, the analytical campaign was the opportunity to test the portable IR scanning prototype based on a peculiar spherical scanning system characterized by light weight and low cost motorized head. The analytical results revealed a painting technique already used by Giotto and based on different superimposed pigment layers. By combining the effectiveness of scanning portable-XRF (pXRF) with the responsive of image spectroscopic analysis, we move step by step toward the discovery of Giotto’s palette, with particular attention to the flesh tones in God the Father with Angels. The imaging data support the hypothesis of a detailed underlying sketch that includes also a drawing characterized by larger brush signs; the use of patrones for the face of “God” was supposed thanks to comparison with other Giotto masterpieces.},
author = {Ludwig, N. and Bonizzoni, L. and Caccia, M. and Cavaliere, F. and Gargano, M. and Viganò, D. and Salvatore, C. and Interlenghi, M. and Martini, M. and Galli, A.},
doi = {10.1007/978-3-030-01629-6_6},
journal = {In: Bortignon P., Lodato G., Meroni E., Paris M., Perini L., Vicini A. (eds) Toward a Science Campus in Milan. CDIP 2017. Springer, Cham},
pages = {},
title = {{Giotto Unveiled: New Developments in Imaging and Elemental Analysis Techniques for Cultural Heritage}},
url = {https://link.springer.com/chapter/10.1007/978-3-030-01629-6_6},
volume = {},
year = {2018},
note = {[Role: coauthor]}
}

The Giotto’s masterpiece God the Father with Angels, never investigated till now, was studied by our team of local researchers, involved in application of scientific methods for cultural heritage since many years. Exploiting the integration of different knowledges, technologies and resources of our team, we were able to provide data to understand the painting technique, the pigment used and the underdrawing of this Giotto’s painting. We performed the following non-invasive analyses: Macro-XRF scanning (MA-XRF), Fiber optic reflectance spectroscopy (FORS), high resolution IR scanning reflectography, infrared false color (IRFC). Only portable instrumentations were used, with operating times compatible with the opening hours of exhibition. In particular, the analytical campaign was the opportunity to test the portable IR scanning prototype based on a peculiar spherical scanning system characterized by light weight and low cost motorized head. The analytical results revealed a painting technique already used by Giotto and based on different superimposed pigment layers. By combining the effectiveness of scanning portable-XRF (pXRF) with the responsive of image spectroscopic analysis, we move step by step toward the discovery of Giotto’s palette, with particular attention to the flesh tones in God the Father with Angels. The imaging data support the hypothesis of a detailed underlying sketch that includes also a drawing characterized by larger brush signs; the use of patrones for the face of “God” was supposed thanks to comparison with other Giotto masterpieces.

@article{Crippa2017,
abstract = {The current gold standard for diagnosis of attention deficit/hyperactivity disorder (ADHD) includes subjective measures, such as clinical interview, observation, and rating scales. The significant heterogeneity of ADHD symptoms represents a challenge for this assessment, and could prevent an accurate diagnosis. The aim of the present work was to investigate the ability of a multi-domain profile of measures, including blood fatty acid profiles, neuropsychological measures, and functional measures from near-infrared spectroscopy (fNIRS), to correctly recognize school-aged children with ADHD. To answer this question, we elaborated a supervised machine learning method to accurately discriminate 22 children with ADHD from 22 children with typical development by means of the proposed profile of measures. To assess the performance of our classifier, we adopted a nested 10-fold cross validation, where the original dataset was split into 10 subsets of equal size, which were used repeatedly for training and testing. Each subset was used once for performance validation. Our method reached a maximum diagnostic accuracy of 81% through the combining of the predictive models trained on neuropsychological, fatty acid profiles, and deoxygenated hemoglobin features. With respect to the analysis of a single-domain dataset per time, the most discriminant neuropsychological features were measures of vigilance, focused and sustained attention, and cognitive flexibility; the most discriminating blood fatty acids were linoleic acid and the total amount of polyunsaturated fatty acids (PUFA). Lastly, with respect to the fNIRS data, we found a significant advantage of the deoxygenated hemoglobin over the oxygenated hemoglobin data in terms of predictive accuracy. These preliminary findings show the feasibility and applicability of our machine learning method in correctly identifying children with ADHD based on multi-domain data. The present machine learning classification approach might be helpful for supporting the clinical practice of diagnosing ADHD, even fostering a computer-aided diagnosis perspective.},
author = {Crippa, A. and Salvatore, C. and Molteni, E. and Mauri, M. and Salandi, A. and Trabattoni, S. and Agostoni, C. and Molteni, M. and Nobile, M. and Castiglioni, I.},
doi = {10.3389/fpsyt.2017.00189},
journal = {Frontiers in Psychiatry},
pages = {189},
title = {{The utility of a computerized algorithm based on a multi-domain profile of measures for the diagnosis of ADHD}},
url = {https://www.frontiersin.org/articles/10.3389/fpsyt.2017.00189/full},
volume = {8},
year = {2017},
note = {[Role: first author | Crippa and Salvatore equally contributed to the paper]}
}

The current gold standard for diagnosis of attention deficit/hyperactivity disorder (ADHD) includes subjective measures, such as clinical interview, observation, and rating scales. The significant heterogeneity of ADHD symptoms represents a challenge for this assessment, and could prevent an accurate diagnosis. The aim of the present work was to investigate the ability of a multi-domain profile of measures, including blood fatty acid profiles, neuropsychological measures, and functional measures from near-infrared spectroscopy (fNIRS), to correctly recognize school-aged children with ADHD. To answer this question, we elaborated a supervised machine learning method to accurately discriminate 22 children with ADHD from 22 children with typical development by means of the proposed profile of measures. To assess the performance of our classifier, we adopted a nested 10-fold cross validation, where the original dataset was split into 10 subsets of equal size, which were used repeatedly for training and testing. Each subset was used once for performance validation. Our method reached a maximum diagnostic accuracy of 81% through the combining of the predictive models trained on neuropsychological, fatty acid profiles, and deoxygenated hemoglobin features. With respect to the analysis of a single-domain dataset per time, the most discriminant neuropsychological features were measures of vigilance, focused and sustained attention, and cognitive flexibility; the most discriminating blood fatty acids were linoleic acid and the total amount of polyunsaturated fatty acids (PUFA). Lastly, with respect to the fNIRS data, we found a significant advantage of the deoxygenated hemoglobin over the oxygenated hemoglobin data in terms of predictive accuracy. These preliminary findings show the feasibility and applicability of our machine learning method in correctly identifying children with ADHD based on multi-domain data. The present machine learning classification approach might be helpful for supporting the clinical practice of diagnosing ADHD, even fostering a computer-aided diagnosis perspective.

@inbook{Nanni2017,
abstract = {},
author = {Nanni, L. and Zaffonato, C. and Salvatore, C. and Castiglioni, I.},
doi = {},
booktitle = {Machine Learning: Advances in Research and Applications},
publisher = {Editor Nova Science Publishers, Inc.},
pages = {},
title = {{An Ensemble of Classifiers for the Early Diagnosis of Alzheimer's Disease}},
url = {to appear},
volume = {},
year = {2017},
note = {[Role: first author | Nanni, Zaffonato and Salvatore equally contributed to the paper]}
}

@article{Battista2017,
abstract = {Subjects with Alzheimer's disease (AD) show loss of cognitive functions and change in behavioral and functional state affecting the quality of their daily life and that of their families and caregivers. A neuropsychological assessment plays a crucial role in detecting such changes from normal conditions. However, despite the existence of clinical measures that are used to classify and diagnose AD, a large amount of subjectivity continues to exist. Our aim was to assess the potential of machine learning in quantifying this process and optimizing or even reducing the amount of neuropsychological tests used to classify AD patients, also at an early stage of impairment. We investigated the role of twelve state-of-the-art neuropsychological tests in the automatic classification of subjects with none, mild, or severe impairment as measured by the clinical dementia rating (CDR). Data were obtained from the ADNI database. In the groups of measures used as features, we included measures of both cognitive domains and subdomains. Our findings show that some tests are more frequently best predictors for the automatic classification, namely, LM, ADAS-Cog, AVLT, and FAQ, with amajor role of the ADAS-Cogmeasures of delayed and immediate memory and the FAQmeasure of financial competency.},
author = {Battista, P. and Salvatore, C. and Castiglioni, I.},
doi = {10.1155/2017/1850909},
journal = {Behavioural Neurology},
pages = {19},
title = {{Optimizing neuropsychological assessments for cognitive, behavioral, and functional impairment classification: A machine learning study}},
url = {https://www.hindawi.com/journals/bn/2017/1850909/},
volume = {2017},
year = {2017},
note = {[Role: first author | Battista and Salvatore equally contributed to the paper]}
}

Subjects with Alzheimer's disease (AD) show loss of cognitive functions and change in behavioral and functional state affecting the quality of their daily life and that of their families and caregivers. A neuropsychological assessment plays a crucial role in detecting such changes from normal conditions. However, despite the existence of clinical measures that are used to classify and diagnose AD, a large amount of subjectivity continues to exist. Our aim was to assess the potential of machine learning in quantifying this process and optimizing or even reducing the amount of neuropsychological tests used to classify AD patients, also at an early stage of impairment. We investigated the role of twelve state-of-the-art neuropsychological tests in the automatic classification of subjects with none, mild, or severe impairment as measured by the clinical dementia rating (CDR). Data were obtained from the ADNI database. In the groups of measures used as features, we included measures of both cognitive domains and subdomains. Our findings show that some tests are more frequently best predictors for the automatic classification, namely, LM, ADAS-Cog, AVLT, and FAQ, with amajor role of the ADAS-Cogmeasures of delayed and immediate memory and the FAQmeasure of financial competency.

@article{Nanni2016,
abstract = {One of the current challenges in Alzheimer's Disease (AD)-related research is to achieve an early and definite diagnosis. Automatic classification of AD is typically based on the use of feature vectors of high dimensionality, containing few training patterns, which leads to the curse-of-dimensionality problem. It is indispensable to find good approaches for selecting a subset of the original set of features. In this work, a method to perform early diagnosis of AD is proposed, combining different feature reduction approaches on both brain MRI studies and expression values of blood plasma proteins. Each selected set of features is used to train a Support Vector Machine (SVM), then the set of SVM is combined by weighted sum rule. Moreover, a novel approach for considering the feature vector as an image is proposed, different texture descriptors are extracted from the image and used to train a SVM. The superior performance of the proposed system is obtained without any ad hoc parameter optimization (i.e., the same ensemble of classifiers and the same parameter settings are used in all datasets). The MATLAB code for the ensemble of classifiers will be publicly available.},
author = {Nanni, L. and Salvatore, C. and Cerasa, A. and Castiglioni, I.},
doi = {10.1016/j.patrec.2016.10.010},
journal = {Pattern Recognition Letters},
pages = {259-266},
title = {{Combining multiple approaches for the early diagnosis of Alzheimer's Disease}},
url = {http://www.sciencedirect.com/science/article/pii/S016786551630277X},
volume = {84},
year = {2016},
note = {[Role: first author | Nanni and Salvatore equally contributed to the paper]}
}

One of the current challenges in Alzheimer's Disease (AD)-related research is to achieve an early and definite diagnosis. Automatic classification of AD is typically based on the use of feature vectors of high dimensionality, containing few training patterns, which leads to the curse-of-dimensionality problem. It is indispensable to find good approaches for selecting a subset of the original set of features. In this work, a method to perform early diagnosis of AD is proposed, combining different feature reduction approaches on both brain MRI studies and expression values of blood plasma proteins. Each selected set of features is used to train a Support Vector Machine (SVM), then the set of SVM is combined by weighted sum rule. Moreover, a novel approach for considering the feature vector as an image is proposed, different texture descriptors are extracted from the image and used to train a SVM. The superior performance of the proposed system is obtained without any ad hoc parameter optimization (i.e., the same ensemble of classifiers and the same parameter settings are used in all datasets). The MATLAB code for the ensemble of classifiers will be publicly available.

@article{Salvatore2016,
abstract = {The emergence of Alzheimer's Disease (AD) as a consequence of increasing aging population makes urgent the availability of methods for the early and accurate diagnosis. Magnetic Resonance Imaging (MRI) could be used as in vivo, non invasive tool to identify sensitive and specific markers of very early AD progression. In recent years, multivariate pattern analysis (MVPA) and machine- learning algorithms have attracted strong interest within the neuroimaging community, as they allow automatic classification of imaging data with higher performance than univariate statistical analysis. An exhaustive search of PubMed, Web of Science and Medline records was performed in this work, in order to retrieve studies focused on the potential role of MRI in aiding the clinician in early diagnosis of AD by using Support Vector Machines (SVMs) as MVPA automated classification method. A total of 30 studies emerged, published from 2008 to date. This review aims to give a state-of-the-art overview about SVM for the early and differential diagnosis of AD-related pathologies by means of MRI data, starting from preliminary steps such as image pre-processing, feature extraction and feature selection, and ending with classification, validation strategies and extraction of MRI-related biomarkers. The main advantages and drawbacks of the different techniques were explored. Results obtained by the reviewed studies were reported in terms of classification performance and biomarker outcomes, in order to shed light on the parameters that accompany normal and pathological aging. Unresolved issues and possible future directions were finally pointed out.},
author = {Salvatore, C. and Battista, P. and Castiglioni, I.},
doi = {10.3389/fnins.2015.00307},
journal = {Current Alzheimer Research},
number = {5},
pages = {509-533},
title = {{Frontiers for the early diagnosis of AD by means of MRI brain imaging and support vector machines}},
url = {http://www.eurekaselect.com/136991},
volume = {13},
year = {2016},
note = {[Role: first author, corresponding author]}
}

The emergence of Alzheimer's Disease (AD) as a consequence of increasing aging population makes urgent the availability of methods for the early and accurate diagnosis. Magnetic Resonance Imaging (MRI) could be used as in vivo, non invasive tool to identify sensitive and specific markers of very early AD progression. In recent years, multivariate pattern analysis (MVPA) and machine- learning algorithms have attracted strong interest within the neuroimaging community, as they allow automatic classification of imaging data with higher performance than univariate statistical analysis. An exhaustive search of PubMed, Web of Science and Medline records was performed in this work, in order to retrieve studies focused on the potential role of MRI in aiding the clinician in early diagnosis of AD by using Support Vector Machines (SVMs) as MVPA automated classification method. A total of 30 studies emerged, published from 2008 to date. This review aims to give a state-of-the-art overview about SVM for the early and differential diagnosis of AD-related pathologies by means of MRI data, starting from preliminary steps such as image pre-processing, feature extraction and feature selection, and ending with classification, validation strategies and extraction of MRI-related biomarkers. The main advantages and drawbacks of the different techniques were explored. Results obtained by the reviewed studies were reported in terms of classification performance and biomarker outcomes, in order to shed light on the parameters that accompany normal and pathological aging. Unresolved issues and possible future directions were finally pointed out.

@phdthesis{Salvatore2015b,
  title = {Development and validation of a Decision Support System for the automatic diagnosis of medical images from brain MRI studies},
  school = {Universit{\`{a}} degli Studi di Milano-Bicocca},
  author = {Salvatore, C.},
  year = {2015},
  url = {https://www.google.it/url?sa=t&rct=j&q=&esrc=s&source=web&cd=5&cad=rja&uact=8&ved=0ahUKEwiMz-DY2LXSAhVGVRQKHXloCfoQFgg7MAQ&url=https%3A%2F%2Fboa.unimib.it%2Fretrieve%2Fhandle%2F10281%2F94834%2F139075%2Fphd_unimib_703037.pdf&usg=AFQjCNFo_cSSWZRnlwsz0_O2XOBMqtCNYA&sig2=opTLNxwW82kxk0Q1UN3iQA}
}

@article{Cerasa2015,
  abstract = {Presently, there are no valid biomarkers to identify individuals with eating disorders (ED). The aim of this work was to assess the feasibility of a machine learning method for extracting reliable neuroimaging features allowing individual categorization of patients with ED. Support Vector Machine (SVM) technique, combined with a pattern recognition method, was employed utilizing structural magnetic resonance images. Seventeen females with ED (six with diagnosis of anorexia nervosa and 11 with bulimia nervosa) were compared against 17 body mass index-matched healthy controls (HC). Machine learning allowed individual diagnosis of ED versus HC with an Accuracy ≥ 0.80. Voxel-based pattern recognition analysis demonstrated that voxels influencing the classification Accuracy involved the occipital cortex, the posterior cerebellar lobule, precuneus, sensorimotor/premotor cortices, and the medial prefrontal cortex, all critical regions known to be strongly involved in the pathophysiological mechanisms of ED. Although these findings should be considered preliminary given the small size investigated, SVM analysis highlights the role of well-known brain regions as possible biomarkers to distinguish ED from HC at an individual level, thus encouraging the translational implementation of this new multivariate approach in the clinical practice.},
  author = {Cerasa, A. and Castiglioni, I. and Salvatore, C. and Funaro, A. and Martino, I. and Alfano, S. and Donzuso, G. and Perrotta, P. and Gioia, M.C. and Gilardi, M.C. and Quattrone, A.},
  doi = {10.1155/2015/924814},
  journal = {Behavioural Neurology},
  title = {{Biomarkers of Eating Disorders Using Support Vector Machine Analysis of Structural Neuroimaging Data: Preliminary Results}},
  volume = {2015},
  pages = {10},
  year = {2015},
  url = {https://www.hindawi.com/journals/bn/2015/924814/},
  note = {[Role: coauthor]}
}

Presently, there are no valid biomarkers to identify individuals with eating disorders (ED). The aim of this work was to assess the feasibility of a machine learning method for extracting reliable neuroimaging features allowing individual categorization of patients with ED. Support Vector Machine (SVM) technique, combined with a pattern recognition method, was employed utilizing structural magnetic resonance images. Seventeen females with ED (six with diagnosis of anorexia nervosa and 11 with bulimia nervosa) were compared against 17 body mass index-matched healthy controls (HC). Machine learning allowed individual diagnosis of ED versus HC with an Accuracy ≥ 0.80. Voxel-based pattern recognition analysis demonstrated that voxels influencing the classification Accuracy involved the occipital cortex, the posterior cerebellar lobule, precuneus, sensorimotor/premotor cortices, and the medial prefrontal cortex, all critical regions known to be strongly involved in the pathophysiological mechanisms of ED. Although these findings should be considered preliminary given the small size investigated, SVM analysis highlights the role of well-known brain regions as possible biomarkers to distinguish ED from HC at an individual level, thus encouraging the translational implementation of this new multivariate approach in the clinical practice.

@article{Crippa2015,
abstract = {In the present work, we have undertaken a proof-of-concept study to determine whether a simple upper-limb movement could be useful to accurately classify low-functioning children with autism spectrum disorder (ASD) aged 2–4. To answer this question, we developed a supervised machine-learning method to correctly discriminate 15 preschool children with ASD from 15 typically developing children by means of kinematic analysis of a simple reach-to-drop task. Our method reached a maximum classification accuracy of 96.7 {\%} with seven features related to the goal-oriented part of the movement. These preliminary findings offer insight into a possible motor signature of ASD that may be potentially useful in identifying a well-defined subset of patients, reducing the clinical heterogeneity within the broad behavioral phenotype.},
author = {Crippa, Alessandro and Salvatore, Christian and Perego, Paolo and Forti, Sara and Nobile, Maria and Molteni, Massimo and Castiglioni, Isabella},
doi = {10.1007/s10803-015-2379-8},
journal = {Journal of Autism and Developmental Disorders},
number = {7},
title = {{Use of Machine Learning to Identify Children with Autism and Their Motor Abnormalities}},
volume = {45},
pages = {2146-2156},
year = {2015},
url = {https://link.springer.com/article/10.1007/s10803-015-2379-8},
note = {[Role: coauthor]}
}

In the present work, we have undertaken a proof-of-concept study to determine whether a simple upper-limb movement could be useful to accurately classify low-functioning children with autism spectrum disorder (ASD) aged 2–4. To answer this question, we developed a supervised machine-learning method to correctly discriminate 15 preschool children with ASD from 15 typically developing children by means of kinematic analysis of a simple reach-to-drop task. Our method reached a maximum classification accuracy of 96.7 % with seven features related to the goal-oriented part of the movement. These preliminary findings offer insight into a possible motor signature of ASD that may be potentially useful in identifying a well-defined subset of patients, reducing the clinical heterogeneity within the broad behavioral phenotype.

@article{Salvatore2015a,
abstract = {Determination of sensitive and specific markers of very early AD progression is intended to aid researchers and clinicians to develop new treatments and monitor their effectiveness, as well as to lessen the time and cost of clinical trials. Magnetic Resonance (MR)-related biomarkers have been recently identified by the use of machine learning methods for the in vivo differential diagnosis of AD. However, the vast majority of neuroimaging papers investigating this topic are focused on the difference between AD and patients with mild cognitive impairment (MCI), not considering the impact of MCI patients who will (MCIc) or not convert (MCInc) to AD. Morphological T1-weighted MRIs of 137 AD, 76 MCIc, 134 MCInc, and 162 healthy controls (CN) selected from the Alzheimer's disease neuroimaging initiative (ADNI) cohort, were used by an optimized machine learning algorithm. Voxels influencing the classification between these AD-related pre-clinical phases involved hippocampus, entorhinal cortex, basal ganglia, gyrus rectus, precuneus, and cerebellum, all critical regions known to be strongly involved in the pathophysiological mechanisms of AD. Classification accuracy was 76{\%} AD vs. CN, 72{\%} MCIc vs. CN, 66{\%} MCIc vs. MCInc (nested 20-fold cross validation). Our data encourage the application of computer-based diagnosis in clinical practice of AD opening new prospective in the early management of AD patients.},
author = {Salvatore, C. and Cerasa, A. and Battista, P. and Gilardi, M.C. and Quattrone, A. and Castiglioni, I.},
doi = {10.3389/fnins.2015.00307},
journal = {Frontiers in Neuroscience},
number = {SEP},
pages = {307},
title = {{Magnetic resonance imaging biomarkers for the early diagnosis of Alzheimer's disease: A machine learning approach}},
url = {http://journal.frontiersin.org/article/10.3389/fnins.2015.00307/full},
volume = {9},
year = {2015},
note = {[Role: first author]}
}

Determination of sensitive and specific markers of very early AD progression is intended to aid researchers and clinicians to develop new treatments and monitor their effectiveness, as well as to lessen the time and cost of clinical trials. Magnetic Resonance (MR)-related biomarkers have been recently identified by the use of machine learning methods for the in vivo differential diagnosis of AD. However, the vast majority of neuroimaging papers investigating this topic are focused on the difference between AD and patients with mild cognitive impairment (MCI), not considering the impact of MCI patients who will (MCIc) or not convert (MCInc) to AD. Morphological T1-weighted MRIs of 137 AD, 76 MCIc, 134 MCInc, and 162 healthy controls (CN) selected from the Alzheimer's disease neuroimaging initiative (ADNI) cohort, were used by an optimized machine learning algorithm. Voxels influencing the classification between these AD-related pre-clinical phases involved hippocampus, entorhinal cortex, basal ganglia, gyrus rectus, precuneus, and cerebellum, all critical regions known to be strongly involved in the pathophysiological mechanisms of AD. Classification accuracy was 76% AD vs. CN, 72% MCIc vs. CN, 66% MCIc vs. MCInc (nested 20-fold cross validation). Our data encourage the application of computer-based diagnosis in clinical practice of AD opening new prospective in the early management of AD patients.

@article{Canini2014,
abstract = {Digital technologies have opened new opportunities for psychological testing, allowing new computerized testing tools to be developed and/or paper and pencil testing tools to be translated to new computerized devices. The question that rises is whether these implementations may introduce some technology-specific effects to be considered in neuropsychological evaluations. Two core aspects have been investigated in this work: the efficacy of tests and the clinical ecology of their administration (the ability to measure real-world test performance), specifically (1) the testing efficacy of a computerized test when response to stimuli is measured using a touch-screen compared to a conventional mouse-control response device; (2) the testing efficacy of a computerized test with respect to different input modalities (visual versus verbal); and (3) the ecology of two computerized assessment modalities (touch-screen and mouse-control), including preference measurements of participants. Our results suggest that (1) touch-screen devices are suitable for administering experimental tasks requiring precise timings for detection, (2) intrinsic nature of neuropsychological tests should always be respected in terms of stimuli presentation when translated to new digitalized environment, and (3) touch-screen devices result in ecological instruments being proposed for the computerized administration of neuropsychological tests with a high level of preference from elderly people.},
author = {Canini, M. and Battista, P. and {Della Rosa}, P.A. and Catrical{\`{a}}, E. and Salvatore, C. and Gilardi, M.C. and Castiglioni, I.},
doi = {10.1155/2014/804723},
journal = {Computational and Mathematical Methods in Medicine},
title = {{Computerized neuropsychological assessment in aging: Testing efficacy and clinical ecology of different interfaces}},
volume = {2014},
pages = {13},
year = {2014},
url = {https://www.hindawi.com/journals/cmmm/2014/804723/},
note = {[Role: coauthor]}
}

Digital technologies have opened new opportunities for psychological testing, allowing new computerized testing tools to be developed and/or paper and pencil testing tools to be translated to new computerized devices. The question that rises is whether these implementations may introduce some technology-specific effects to be considered in neuropsychological evaluations. Two core aspects have been investigated in this work: the efficacy of tests and the clinical ecology of their administration (the ability to measure real-world test performance), specifically (1) the testing efficacy of a computerized test when response to stimuli is measured using a touch-screen compared to a conventional mouse-control response device; (2) the testing efficacy of a computerized test with respect to different input modalities (visual versus verbal); and (3) the ecology of two computerized assessment modalities (touch-screen and mouse-control), including preference measurements of participants. Our results suggest that (1) touch-screen devices are suitable for administering experimental tasks requiring precise timings for detection, (2) intrinsic nature of neuropsychological tests should always be respected in terms of stimuli presentation when translated to new digitalized environment, and (3) touch-screen devices result in ecological instruments being proposed for the computerized administration of neuropsychological tests with a high level of preference from elderly people.

@inbook{Cava2014b,
abstract = {Bioinformatics traditionally deals with computational approaches to the analysis of big data from high-throughput technologies as genomics, proteomics, and sequencing. Bioinformatics analysis allows extraction of new information from big data that might help to better assess the biological details at a molecular and cellular level. The wide-scale and high-dimensionality of Bioinformatics data has led to an increasing need of high performance computing and repository. In this chapter, the authors demonstrate the advantages of cloud computing in Bioinformatics research for high-throughput technologies.},
author = {Cava, C. and Gallivanone, F. and Salvatore, C. and {Della Rosa}, P.A. and Castiglioni, I.},
booktitle = {Cloud Technology: Concepts, Methodologies, Tools, and Applications},
doi = {10.4018/978-1-4666-6539-2.ch059},
isbn = {9781466665408},
title = {{Bioinformatics clouds for high-throughput technologies}},
volume = {3},
pages = {1294-1311},
year = {2014},
publisher = {IGI Global},
url = {http://www.igi-global.com/gateway/chapter/119907},
note = {[Role: coauthor]}
}

Bioinformatics traditionally deals with computational approaches to the analysis of big data from high-throughput technologies as genomics, proteomics, and sequencing. Bioinformatics analysis allows extraction of new information from big data that might help to better assess the biological details at a molecular and cellular level. The wide-scale and high-dimensionality of Bioinformatics data has led to an increasing need of high performance computing and repository. In this chapter, the authors demonstrate the advantages of cloud computing in Bioinformatics research for high-throughput technologies.

@inbook{Cava2014a,
abstract = {{\textcopyright} 2014 by IGI Global. All rights reserved.Bioinformatics traditionally deals with computational approaches to the analysis of big data from high-throughput technologies as genomics, proteomics, and sequencing. Bioinformatics analysis allows extraction of new information from big data that might help to better assess the biological details at a molecular and cellular level. The wide-scale and high-dimensionality of Bioinformatics data has led to an increasing need of high performance computing and repository. In this chapter, the authors demonstrate the advantages of cloud computing in Bioinformatics research for high-throughput technologies.},
author = {Cava, C. and Gallivanone, F. and Salvatore, C. and {Della Rosa}, P.A. and Castiglioni, I.},
booktitle = {Handbook of Research on Cloud Infrastructures for Big Data Analytics},
doi = {10.4018/978-1-4666-5864-6.ch020},
isbn = {9781466658653},
title = {{Bioinformatics clouds for high-throughput technologies}},
pages = {489-507},
year = {2014},
publisher = {IGI Global},
url = {http://www.igi-global.com/gateway/chapter/103227},
note = {[Role: coauthor]}
}

© 2014 by IGI Global. All rights reserved.Bioinformatics traditionally deals with computational approaches to the analysis of big data from high-throughput technologies as genomics, proteomics, and sequencing. Bioinformatics analysis allows extraction of new information from big data that might help to better assess the biological details at a molecular and cellular level. The wide-scale and high-dimensionality of Bioinformatics data has led to an increasing need of high performance computing and repository. In this chapter, the authors demonstrate the advantages of cloud computing in Bioinformatics research for high-throughput technologies.

@article{Salvatore2014,
abstract = {Background: Supervised machine learning has been proposed as a revolutionary approach for identifying sensitive medical image biomarkers (or combination of them) allowing for automatic diagnosis of individual subjects. The aim of this work was to assess the feasibility of a supervised machine learning algorithm for the assisted diagnosis of patients with clinically diagnosed Parkinson's disease (PD) and Progressive Supranuclear Palsy (PSP). Method: Morphological T1-weighted Magnetic Resonance Images (MRIs) of PD patients (28), PSP patients (28) and healthy control subjects (28) were used by a supervised machine learning algorithm based on the combination of Principal Components Analysis as feature extraction technique and on Support Vector Machines as classification algorithm. The algorithm was able to obtain voxel-based morphological biomarkers of PD and PSP. Results: The algorithm allowed individual diagnosis of PD versus controls, PSP versus controls and PSP versus PD with an Accuracy, Specificity and Sensitivity. {\textgreater}. 90{\%}. Voxels influencing classification between PD and PSP patients involved midbrain, pons, corpus callosum and thalamus, four critical regions known to be strongly involved in the pathophysiological mechanisms of PSP. Comparison with existing methods: Classification accuracy of individual PSP patients was consistent with previous manual morphological metrics and with other supervised machine learning application to MRI data, whereas accuracy in the detection of individual PD patients was significantly higher with our classification method. Conclusions: The algorithm provides excellent discrimination of PD patients from PSP patients at an individual level, thus encouraging the application of computer-based diagnosis in clinical practice. {\textcopyright} 2013 Elsevier B.V.},
author = {Salvatore, C. and Cerasa, A. and Castiglioni, I. and Gallivanone, F. and Augimeri, A. and Lopez, M. and Arabia, G. and Morelli, M. and Gilardi, M.C. and Quattrone, A.},
doi = {10.1016/j.jneumeth.2013.11.016},
journal = {Journal of Neuroscience Methods},
title = {{Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy}},
volume = {222},
pages = {230-237},
year = {2014},
url = {http://www.sciencedirect.com/science/article/pii/S0165027013003993},
note = {[Role: first author]}
}

Background: Supervised machine learning has been proposed as a revolutionary approach for identifying sensitive medical image biomarkers (or combination of them) allowing for automatic diagnosis of individual subjects. The aim of this work was to assess the feasibility of a supervised machine learning algorithm for the assisted diagnosis of patients with clinically diagnosed Parkinson's disease (PD) and Progressive Supranuclear Palsy (PSP). Method: Morphological T1-weighted Magnetic Resonance Images (MRIs) of PD patients (28), PSP patients (28) and healthy control subjects (28) were used by a supervised machine learning algorithm based on the combination of Principal Components Analysis as feature extraction technique and on Support Vector Machines as classification algorithm. The algorithm was able to obtain voxel-based morphological biomarkers of PD and PSP. Results: The algorithm allowed individual diagnosis of PD versus controls, PSP versus controls and PSP versus PD with an Accuracy, Specificity and Sensitivity. \textgreater. 90%. Voxels influencing classification between PD and PSP patients involved midbrain, pons, corpus callosum and thalamus, four critical regions known to be strongly involved in the pathophysiological mechanisms of PSP. Comparison with existing methods: Classification accuracy of individual PSP patients was consistent with previous manual morphological metrics and with other supervised machine learning application to MRI data, whereas accuracy in the detection of individual PD patients was significantly higher with our classification method. Conclusions: The algorithm provides excellent discrimination of PD patients from PSP patients at an individual level, thus encouraging the application of computer-based diagnosis in clinical practice. © 2013 Elsevier B.V.

@inproceedings{Cava2013,
abstract = {Specific genome copy number alterations, such as deletions and amplifications are an important factor in tumor development and progression, and are also associated with changes in gene expression. By combining analyses of gene expression and genome copy number we identified genes as candidate biomarkers of BC which were validated as prognostic factors of the disease progression. These results suggest that the proposed combined approach may become a valuable method for BC prognosis. {\textcopyright} 2013 IEEE.},
author = {Cava, C. and Zoppis, I. and Mauri, G. and Ripamonti, M. and Gallivanone, F. and Salvatore, C. and Gilardi, M.C. and Castiglioni, I.},
booktitle = {Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS},
doi = {10.1109/EMBC.2013.6609573},
isbn = {9781457702167},
title = {{Combination of gene expression and genome copy number alteration has a prognostic value for breast cancer}},
year = {2013},
pages = {608-611},
url = {http://ieeexplore.ieee.org/abstract/document/6609573/},
note = {[Role: coauthor]}
}

Specific genome copy number alterations, such as deletions and amplifications are an important factor in tumor development and progression, and are also associated with changes in gene expression. By combining analyses of gene expression and genome copy number we identified genes as candidate biomarkers of BC which were validated as prognostic factors of the disease progression. These results suggest that the proposed combined approach may become a valuable method for BC prognosis. © 2013 IEEE.

@article{Gallivanone2013,
abstract = {We have developed, optimized, and validated a method for partial volume effect (PVE) correction of oncological lesions in positron emission tomography (PET) clinical studies, based on recovery coefficients (RC) and on PET measurements of lesion-to-background ratio (L/B m) and of lesion metabolic volume. An operator-independent technique, based on an optimised threshold of the maximum lesion uptake, allows to define an isocontour around the lesion on PET images in order to measure both lesion radioactivity uptake and lesion metabolic volume. RC are experimentally derived from PET measurements of hot spheres in hot background, miming oncological lesions. RC were obtained as a function of PET measured sphere-to-background ratio and PET measured sphere metabolic volume, both resulting from the threshold-isocontour technique. PVE correction of lesions of a diameter ranging from 10 mm to 40 mm and for measured L/B m from 2 to 30 was performed using measured RC curves tailored at answering the need to quantify a large variety of real oncological lesions by means of PET. Validation of the PVE correction method resulted to be accurate ({\textgreater}89{\%}) in clinical realistic conditions for lesion diameter {\textgreater} 1 cm, recovering {\textgreater}76{\%} of radioactivity for lesion diameter {\textless} 1 cm. Results from patient studies showed that the proposed PVE correction method is suitable and feasible and has an impact on a clinical environment. {\textcopyright} 2013 F. Gallivanone et al.},
author = {Gallivanone, F. and Canevari, C. and Gianolli, L. and Salvatore, C. and {Della Rosa}, P.A. and Gilardi, M.C. and Castiglioni, I.},
doi = {10.1155/2013/780458},
journal = {BioMed Research International},
title = {{A partial volume effect correction tailored for 18F-FDG-PET oncological studies}},
volume = {2013},
pages = {12},
year = {2013},
url = {https://www.hindawi.com/journals/bmri/2013/780458/},
note = {[Role: coauthor]}
}

We have developed, optimized, and validated a method for partial volume effect (PVE) correction of oncological lesions in positron emission tomography (PET) clinical studies, based on recovery coefficients (RC) and on PET measurements of lesion-to-background ratio (L/B m) and of lesion metabolic volume. An operator-independent technique, based on an optimised threshold of the maximum lesion uptake, allows to define an isocontour around the lesion on PET images in order to measure both lesion radioactivity uptake and lesion metabolic volume. RC are experimentally derived from PET measurements of hot spheres in hot background, miming oncological lesions. RC were obtained as a function of PET measured sphere-to-background ratio and PET measured sphere metabolic volume, both resulting from the threshold-isocontour technique. PVE correction of lesions of a diameter ranging from 10 mm to 40 mm and for measured L/B m from 2 to 30 was performed using measured RC curves tailored at answering the need to quantify a large variety of real oncological lesions by means of PET. Validation of the PVE correction method resulted to be accurate (\textgreater89%) in clinical realistic conditions for lesion diameter \textgreater 1 cm, recovering \textgreater76% of radioactivity for lesion diameter \textless 1 cm. Results from patient studies showed that the proposed PVE correction method is suitable and feasible and has an impact on a clinical environment. © 2013 F. Gallivanone et al.

@inproceedings{Castiglioni2013,
  title={Machine learning performs differential individual diagnosis of PD and PSP by brain MRI studies},
  author={Castiglioni, I. and Cerasa, A. and Salvatore, C. and Gallivanone, F. and Augimeri, A. and Lopez, M. and Gilardi, M.C. and Quattrone, A.},
  booktitle={Movement Disorders},
  volume={28 Suppl 1},
  pages={71-72},
  year={2013},
  url = {http://www.mdsabstracts.com/abstract.asp?MeetingID=798&id=106223},
  note = {[Role: coauthor | Abstract in conference proceedings]}
}

@inproceedings{Gallivanone2012,
abstract = {SPM has been widely used for the operator independent assessment of functional and molecular differences in human PET or MRI brain images. Despite the large diffusion of dedicated image systems and protocols, the use of SPM methodology to preclinical studies have been described in a limited number of studies, particularly for PET. Aim of this work was to optimize and adopt SPM analysis for the identification of patterns of altered metabolism due to acute stress in rat brain using PET with 18F-FDG. {\textcopyright} 2012 IEEE.},
author = {Gallivanone, F. and {Di Grigoli}, G. and Salvatore, C. and Valtorta, S. and Gilardi, M.C. and Moresco, R.M. and Castiglioni, I.},
booktitle = {Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), 2012 IEEE},
doi = {10.1109/NSSMIC.2012.6551658},
isbn = {9781467320306},
title = {{Acute stress studies in rats by 18FDG PET and SPM}},
year = {2012},
pages = {2886-2889},
url = {http://ieeexplore.ieee.org/document/6551658/},
note = {[Role: coauthor]}
}

SPM has been widely used for the operator independent assessment of functional and molecular differences in human PET or MRI brain images. Despite the large diffusion of dedicated image systems and protocols, the use of SPM methodology to preclinical studies have been described in a limited number of studies, particularly for PET. Aim of this work was to optimize and adopt SPM analysis for the identification of patterns of altered metabolism due to acute stress in rat brain using PET with 18F-FDG. © 2012 IEEE.

@inproceedings{Grosso2012b,
abstract = {Decision support systems for the assisted medical diagnosis offer the main feature of giving assessments which are poorly affected from arbitrary clinical reasoning. Aim of this work was to assess the feasibility of a decision support system for the assisted diagnosis of brain cancer, such approach presenting potential for early diagnosis of tumors and for the classification of the degree of the disease progression. For this purpose, a supervised learning algorithm combined with a pattern recognition method was developed and cross-validated in 18F-FDG PET studies of a model of a brain tumour implantation. {\textcopyright} 2012 IEEE.},
author = {Grosso, E. and Lopez, M. and Salvatore, C. and Gallivanone, F. and {Di Grigoli}, G. and Valtorta, S. and Moresco, R. and Gilardi, M.C. and Ramirez, J. and Gorriz, J.M. and Castiglioni, I.},
booktitle = {Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS},
doi = {10.1109/EMBC.2012.6347424},
isbn = {9781424441198},
title = {{A decision support system for the assisted diagnosis of brain tumors: A feasibility study for 18F-FDG PET preclinical studies}},
pages = {6255-6258},
year = {2012},
url = {http://ieeexplore.ieee.org/document/6347424/},
note = {[Role: coauthor]}
}

Decision support systems for the assisted medical diagnosis offer the main feature of giving assessments which are poorly affected from arbitrary clinical reasoning. Aim of this work was to assess the feasibility of a decision support system for the assisted diagnosis of brain cancer, such approach presenting potential for early diagnosis of tumors and for the classification of the degree of the disease progression. For this purpose, a supervised learning algorithm combined with a pattern recognition method was developed and cross-validated in 18F-FDG PET studies of a model of a brain tumour implantation. © 2012 IEEE.

@article{Grosso2012a,
abstract = {Decision support systems for the assisted medical diagnosis offer the main feature of giving assessments which are poorly affected from arbitrary clinical reasoning. Aim of this work was to assess the feasibility of a decision support system for the assisted diagnosis of brain cancer, such approach presenting potential for early diagnosis of tumors and for the classification of the degree of the disease progression. For this purpose, a supervised learning algorithm combined with a pattern recognition method was developed and cross-validated in 18F-FDG PET studies of a model of a brain tumour implantation.},
author = {Grosso, E. and Lopez, M. and Salvatore, C. and Gallivanone, F. and {Di Grigoli}, G. and Valtorta, S. and Moresco, R. and Gilardi, M.C. and Ramirez, J. and Gorriz, J.M. and Castiglioni, I.},
journal = {Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society},
title = {{A Decision Support System for the assisted diagnosis of brain tumors: a feasibility study for 18F-FDG PET preclinical studies.}},
pages = {6255-6258},
year = {2012},
volume = {2012},
url = {http://ieeexplore.ieee.org/document/6347424/},
note = {[Role: coauthor]}
}

Decision support systems for the assisted medical diagnosis offer the main feature of giving assessments which are poorly affected from arbitrary clinical reasoning. Aim of this work was to assess the feasibility of a decision support system for the assisted diagnosis of brain cancer, such approach presenting potential for early diagnosis of tumors and for the classification of the degree of the disease progression. For this purpose, a supervised learning algorithm combined with a pattern recognition method was developed and cross-validated in 18F-FDG PET studies of a model of a brain tumour implantation.