In recent years it has been assessed that in people with type 2 diabetes the likelihood of developing Alzheimer's disease increases by more than 50%. The purpose of the analysis proposed in this paper is to identify visually the correlation between Alzheimer's disease and type 2 diabetes and determine whether Alzheimer's disease is a form of brain diabetes mellitus. A dataset containing genomic microarray data relating to the two diseases is used for the analysis. First, we conduct an exploratory analysis using clustering techniques to perform a first screening of the samples and divide them into two different clusters. Then, we propose a predictive model for the classification and identify the genes equally expressed in the two types of samples. This makes it possible to select genes with significant values for the research in progress, on which pathway analysis must be performed to identify the classes they belong to. We also study the gene expression alterations of genes belonging to a specific pathway to determine if the differential expression is statistically significant. We provide a visual representation of connections in the pathways of both the diseases. Results indicate that there is a set of genes of significant importance for both type 2 diabetes and Alzheimer's disease, but that there is also a significant correlation with other neurodegenerative diseases. Consequently, it is possible to define the Alzheimer's disease as a form of cerebral diabetes mellitus.

Acute Leukemia is classified in terms of two distinct classes: Acute Lymphoblastic Leukemia (ALL) and Acute Myeloid Leukemia (AML). This paper aims at defining a feature selection analysis process mainly based on Deep Learning for classifying the acute leukemia type. The considered dataset consists in data of patients affected by both the leukemia types. Both the leukemia types are characterized by a list of identical genes for all the patients. The analysis exploits feature selection techniques for reducing the consistent number of variables (genes). To this aim, we use linear models for differential expression for microarray data, and an autoencoder based unsupervised deep learning model to simplify and speed up the classification. Then, classification models have been implemented with the use of a deep neural network (DNN), obtaining an accuracy of approximately 92%. Moreover, the results have been compared with the ones provided by an approach based on support vector machines (SVM), giving an accuracy of 87,39%. Another feature selection approach based on genetic algorithms has been experimented, with worse performances. We also conducted a gene enrichment analysis based on the functional annotation of the differentially expressed genes. As a result, a differentially expressed pathway between the two pathologies has been detected.

Abstract In the last few years, the integration of researches in Computer Science and medical fields has made available to the scientific community an enormous amount of data, stored in databases. In this paper, we analyze the data available in the Parkinson’s Progression Markers Initiative (PPMI), a comprehensive observational, multi-center study designed to identify progression biomarkers important for better treatments for Parkinson’s disease. The data of PPMI participants are collected through a comprehensive battery of tests and assessments including Magnetic Resonance Imaging and DATscan imaging, collection of blood, cerebral spinal fluid, and urine samples, as well as cognitive and motor evaluations. To this aim, we propose a technique to identify a correlation between the biomedical data in the PPMI dataset for verifying the consistency of medical reports formulated during the visits and allow to correctly categorize the various patients. To correlate the information of each patient’s medical report, Information Retrieval and Machine Learning techniques have been adopted, including the Latent Semantic Analysis, Text2Vec and Doc2Vec techniques. Then, patients are grouped and classified into affected or not by using clustering algorithms according to the similarity of medical reports. Finally, we have adopted a visualization system based on the D3 framework to visualize correlations among medical reports with an interactive chart, and to support the doctor in analyzing the chronological sequence of visits in order to diagnose Parkinson’s disease early.

Autism Spectrum Disorder (ASD) is a term used to describe a constellation of early-onset social communication deficits and repetitive sensorimotor behaviours associated with a strong genetic component as well as other causes. This paper aims at creating a tool for automatically isolating segments of the speech useful for extract prosody features for identifying children with ASD. In particular, in this first phase of the research, we are interested in the creation of a large dataset of ’a’ vowels of ASD and not ASD people. The ’a’ vowel contains relevant information on the voice quality and emotional states. The proposed methodology is divided into 2 phases. In the former the input audio is analyzed to determine the vowel onset and offset points, useful to extract the vowel regions. Then a spectrogram graphically visualizing the identified vowels is provided as input to the second phase, where a convolutional neural network classifies whether the histogram represents the vowel ’a’. The convolutional network reaches an average accuracy of 95.00% (standard deviation ± 2.60%) on a dataset of 640 samples with Stratified 5-Fold Cross-Validation.

Melanoma is the deadliest form of skin cancer and it is diagnosed mainly visually, starting from initial clinical screening and followed by dermoscopic analysis, biopsy and histopathological examination. A dermatologist's recognition of melanoma may be subject to errors and may take some time to diagnose it. In this regard, deep learning can be useful in the study and classification of skin cancer. In particular, by classifying images with Deep Neural Network methodologies, it is possible to obtain comparable or even superior results compared to those of dermatologists. In this paper, we propose a methodology for the classification of melanoma by adopting different deep learning techniques applied to a common dataset, composed of images from the ISIC dataset and consisting of different types of skin diseases, including melanoma on which we applied a specific pre-processing phase. In particular, a comparison of the results is performed in order to select the best effective neural network to be applied to the problem of recognition and classification of melanoma. Moreover, we also evaluate the impact of the preprocessing phase on the final classification. Different metrics such as accuracy, sensitivity, and specificity have been selected to assess the goodness of the adopted neural networks and compare them also with the manual classification of dermatologists.

Over the last few years, biometrics has emerged as an increasingly reliable solution to recognize people using their physiological or behavioural characteristics. Despite their advantages, biometric systems raise many practical, ethical and legal issues. While, understandably, main concerns involve privacy and the risk of covert surveillance, profiling, and social control, another relevant question is the potential exclusion of individuals that, due to injuries, disability or genetic defects, may not meet the physical requirements used for the identification. In such situations, the risk comes out from the limits of current biometrics systems, which could exclude entire classes of individuals with negative spillovers on the possibility of access services and even exercise rights. In this paper, we focus on the recognition of iris suffering from Coloboma, a congenital abnormality of membranes of the eye. We first show how this pathological state impacts on the performance of the Daugman's algorithm, which represents the most widespread method used for the iris localization step in eye-based biometrics. Second, we designed and tested a classifier based on Convolutional Neural Network able to detect the presence of Coloboma with 95.45% accuracy. This result opens up new perspectives towards the definition of more sophisticated "diversity-aware" biometric systems.

Melanoma is the deadliest form of skin cancer. It mainly requires a visual diagnosis by dermatologists. However, a dermatologist's recognition of melanoma may be subject to errors and may take some time to diagnose correctly it. To this aim, in the last twenty years, Computer-Aided Diagnosis systems based on artificial vision are increasingly adopted to support dermatologists in the early diagnosis of melanoma. However, these systems exploits only a reduced set of parameters or they implement a melanoma classifier that tries to substitute the dermatologists, without supporting their experience in the classification of skin lesions. This paper proposes a mobile application for supporting the clinician decision in the diagnosis of melanoma directly in the dermatologist environment by using Augmented Reality technology. In particular, computer-generated perceptual information is added to the image of patient skin reporting the values of various parameters and the lesion classification based on deep learning approach for analyzing skin lesions and identifying melanoma.

In recent years, the integration of researches in Computer Science and medical fields has made available to the scientific community an enormous amount of data, stored in databases. In this paper, we analyze the data available in the Parkinson's Progression Markers Initiative (PPMI), a comprehensive observational, multi-center study designed to identify progression biomarkers important for better treatments for Parkinson's disease. The data of PPMI participants are collected through a comprehensive battery of tests and assessments including Magnetic Resonance Imaging and DATscan imaging, collection of blood, cerebral spinal fluid, and urine samples, as well as cognitive and motor evaluations. To this aim, we propose a technique to identify a correlation between the biomedical data in the PPMI dataset for verifying the consistency of medical reports formulated during the visits and allow to correctly categorize the various patients. To correlate the information of each patient's medical report, Information Retrieval techniques have been adopted, including the Latent Semantic Analysis technique suitable for constructing a concept space on patient information. Then, patients are grouped and classified into affected or not by using clustering algorithms according to the similarity of medical reports projected in the concept space. Results revealed that the proposed technique reached 95% of effectiveness in the classification of patients.