Augmented reality, artificial intelligence and machine learning in Industry 4.0: case studies at SI-Lab Bruno A, Coscetti S, Leone G. R., Germanese D., Magrini M., Martinelli M., Moroni D., Pascali M. A., Pieri G., Reggiannini M., Tampucci M. In recent years, the impressive advances in artificial intelligence, computer vision, pervasive computing, and augmented reality made them rise to pillars of the fourth industrial revolution. This short paper aims to provide a brief survey of current use cases in factory applications and industrial inspection under active development at the Signals and Images Lab, ISTI-CNR, Pisa.Source: Ital-IA 2022 - Convegno nazionale CINI sull'Intelligenza Artificiale, Torino, Italy, 9-11/02/2022 DOI: 10.5281/zenodo.6322733 Metrics:
Exploring UAVs for structural health monitoring Germanese D., Moroni D., Pascali M. A., Tampucci M., Berton A. The preservation and maintenance of architectural heritage on a large scale deserve the design, development, and exploitation of innovative methodologies and tools for sustainable Structural Heritage Monitoring (SHM). In the framework of the Moscardo Project (https://www.moscardo.it/), the role of Unmanned Aerial Vehicles (UAVs) in conjunction with a broader IoT platform for SHM has been investigated. UAVs resulted in significant aid for a safe, fast and routinely operated inspection of buildings in synergy with data collected in situ thanks to a network of pervasive wireless sensors (Bacco et al. 2020). The main idea has been to deploy an acquisition layer made of a network of low power sensors capable of collecting environmental parameters and building vibration modes. This layer has been connected to a service layer through gateways capable of performing data analysis and presenting aggregated results thanks to an integrated dashboard. In this architecture, the UAV has emerged as a particular network node for extending the acquisition layer by adding several imaging capabilities.Source: D-SITe 2022 - Drones. Systems of Information on culTural hEritage. For a spatial and social investigation, pp. 640–643, Pavia, Italy, 16-18/06/2022
Artificial Intelligence for chest imaging against COVID-19: an insight into image segmentation methods Buongiorno R., Germanese D., Colligiani L., Fanni S. C., Romei C., Colantonio S. The coronavirus disease 2019 (COVID-19), caused by the Severe Acute Respiratory Syndrome Coronavirus 2, emerged in late 2019 and soon developed as a pandemic leading to a world health crisis.
Chest imaging examination plays a vital role in the clinical management and prognostic evaluation of COVID-19 since the imaging pathological findings reflect the inflammatory process of the lungs.
Particularly, thanks to its highest sensitivity and resolution, Computer Tomography chest imaging serves well in the distinction of the different parenchymal patterns and manifestations of COVID-19. It is worth noting that detecting and quantifying such manifestations is a key step in evaluating disease impact and tracking its progression or regression over time. Nevertheless, the visual inspection or, even worse, the manual delimitation of such manifestations may be greatly time-consuming and overwhelming for radiologists, especially when pressed by the urgent needs of patient care.
Image segmentation tools, powered by Artificial Intelligence, may sensibly reduce radiologists' workload as they may automate or, at least, facilitate the delineation of the pathological lesions and the other regions of interest for disease assessment. This delineation lays the basis for further diagnostic and prognostic analyses based on quantitative information extracted from the segmented lesions.
This chapter overviews the Artificial Intelligence methods for the segmentation of chest Computed Tomography images. The focus is in particular on Deep Learning approaches, as these have lately become the mainstream approach to image segmentation. A novel method, leveraging attention-based learning, is presented and evaluated. Finally, a discussion of the potential, limitations, and still open challenges of the field concludes the chapter.Source: Artificial Intelligence in Healthcare and COVID-19. Amsterdam: Elsevier, 2022
SI-Lab annual research report 2021 Righi M., Leone G. R., Carboni A., Caudai C., Colantonio S., Kuruoglu E. E., Leporini B., Magrini M., Paradisi P., Pascali M. A., Pieri G., Reggiannini M., Salerno E., Scozzari A., Tonazzini A., Fusco G., Galesi G., Martinelli M., Pardini F., Tampucci M., Berti A., Bruno A., Buongiorno R., Carloni G., Conti F., Germanese D., Ignesti G., Matarese F., Omrani A., Pachetti E., Papini O., Benassi A., Bertini G., Coltelli P., Tarabella L., Straface S., Salvetti O., Moroni D. The Signal & Images Laboratory is an interdisciplinary research group in computer vision, signal analysis, intelligent vision systems and multimedia data understanding. It is part of the Institute of Information Science and Technologies (ISTI) of the National Research Council of Italy (CNR). This report accounts for the research activities of the Signal and Images Laboratory of the Institute of Information Science and Technologies during the year 2021.Source: ISTI Annual reports, 2022 DOI: 10.32079/isti-ar-2022/003 Metrics:
UIP-net: a decoder-encoder CNN for the detection and quantification of usual interstitial pneumoniae pattern in lung CT scan images Buongiorno R., Germanese D., Romei C., Tavanti L., De Liperi A., Colantonio S. A key step of the diagnosis of Idiopathic Pulmonary Fibrosis (IPF) is the examination of high-resolution computed tomography images (HRCT).
IPF exhibits a typical radiological pattern, named Usual Interstitial Pneumoniae (UIP) pattern, which can be detected in non-invasive HRCT investigations, thus avoiding surgical lung biopsy. Unfortunately, the visual recognition and quantification of UIP pattern can be challenging even for experienced radiologists due to the poor inter and intra-reader agreement.
This study aimed to develop a tool for the semantic segmentation and the quantification of UIP pattern in patients with IPF using a deep-learning method based on a Convolutional Neural Network (CNN), called UIP-net. The proposed CNN, based on an encoder-decoder architecture, takes as input a thoracic HRCT image and outputs a binary mask for the automatic discrimination between UIP pattern and healthy lung parenchyma.
To train and evaluate the CNN, a dataset of 5000 images, derived by 20 CT scans of different patients, was used. The network performance yielded 96.7% BF-score and 85.9% sensitivity.
Once trained and tested, the UIP-net was used to obtain the segmentations of other 60 CT scans of different patients to estimate the volume of lungs affected by the UIP pattern. The measurements were compared with those obtained using the reference software for the automatic detection of UIP pattern, named Computer Aided Lungs Informatics for Pathology Evaluation and Rating (CALIPER), through
the Bland-Altman plot.
The network performance assessed in terms of both BF-score and sensitivity on the test-set and resulting from the comparison with CALIPER demonstrated that CNNs have the potential to reliably detect and quantify pulmonary disease in order to evaluate its progression and become a supportive tool for radiologists.Source: ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges, pp. 389–405, Milan, Italy - Virtual event, 10-15/01/2021 DOI: 10.1007/978-3-030-68763-2_30 Metrics:
SI-Lab Annual Research Report 2020 Leone G. R., Righi M., Carboni A., Caudai C., Colantonio S., Kuruoglu E. E., Leporini B., Magrini M., Paradisi P., Pascali M. A., Pieri G., Reggiannini M., Salerno E., Scozzari A., Tonazzini A., Fusco G., Galesi G., Martinelli M., Pardini F., Tampucci M., Buongiorno R., Bruno A., Germanese D., Matarese F., Coscetti S., Coltelli P., Jalil B., Benassi A., Bertini G., Salvetti O., Moroni D. The Signal & Images Laboratory (http://si.isti.cnr.it/) is an interdisciplinary research group in computer vision, signal analysis, smart vision systems and multimedia data understanding. It is part of the Institute for Information Science and Technologies of the National Research Council of Italy. This report accounts for the research activities of the Signal and Images Laboratory of the Institute of Information Science and Technologies during the year 2020.Source: ISTI Annual Report, ISTI-2021-AR/001, pp.1–38, 2021 DOI: 10.32079/isti-ar-2021/001 Metrics:
A deep learning approach for hepatic steatosis estimation from ultrasound imaging Colantonio S., Salvati A., Caudai C., Bonino F., De Rosa L., Pascali M. A., Germanese D., Brunetto M. R., Faita F. This paper proposes a simple convolutional neural model as a novel method to predict the level of hepatic steatosis from ultrasound data. Hepatic steatosis is the major histologic feature of non-alcoholic fatty liver disease (NAFLD), which has become a major global health challenge. Recently a new definition for FLD, that take into account the risk factors and clinical characteristics of subjects, has been suggested; the proposed criteria for Metabolic Disfunction-Associated Fatty Liver Disease (MAFLD) are based on histological (biopsy), imaging or blood biomarker evidence of fat accumulation in the liver (hepatic steatosis), in subjects with overweight/obesity or presence of type 2 diabetes mellitus. In lean or normal weight, non-diabetic individuals with steatosis, MAFLD is diagnosed when at least two metabolic abnormalities are present. Ultrasound examinations are the most used technique to non-invasively identify liver steatosis in a screening settings. However, the diagnosis is operator dependent, as accurate image processing techniques have not entered yet in the diagnostic routine. In this paper, we discuss the adoption of simple convolutional neural models to estimate the degree of steatosis from echographic images in accordance with the state-of-the-art magnetic resonance spectroscopy measurements (expressed as percentage of the estimated liver fat). More than 22,000 ultrasound images were used to train three networks, and results show promising performances in our study (150 subjects).Source: ICCCI 2021 - 13th International Conference on Computational Collective Intelligence, pp. 703–714, Rhodes, Greece, 29/09/2021,1/10/ 2021 DOI: 10.1007/978-3-030-88113-9_57 Metrics:
Monitoring ancient buildings: real deployment of an IoT system enhanced by UAVs and virtual reality Bacco M., Barsocchi P., Cassarà P., Germanese D., Gotta A., Leone G. R., Moroni D., Pascali M. A., Tampucci M. The historical buildings of a nation are the tangible signs of its history and culture. Their preservation deserves considerable attention, being of primary importance from a historical, cultural, and economic point of view. Having a scalable and reliable monitoring system plays an important role in the Structural Health Monitoring (SHM): therefore, this paper proposes an Internet Of Things (IoT) architecture for a remote monitoring system that is able to integrate, through the Virtual Reality (VR) paradigm, the environmental and mechanical data acquired by a wireless sensor network set on three ancient buildings with the images and context information acquired by an Unmanned Aerial Vehicle (UAV). Moreover, the information provided by the UAV allows to promptly inspect the critical structural damage, such as the patterns of cracks in the structural components of the building being monitored. Our approach opens new scenarios to support SHM activities, because an operator can interact with real-time data retrieved from a Wireless Sensor Network (WSN) by means of the VR environment.Source: IEEE access (2020). doi:10.1109/ACCESS.2020.2980359 DOI: 10.1109/access.2020.2980359 Metrics:
Analisi di immagini tomografiche ad alta risoluzione attraverso reti neurali convoluzionali per lo studio delle interstiziopatie polmonari Buongiorno R., Colantonio S., Germanese D. Le interstiziopatie polmonari (Interstitial Lung Disease, ILD) sono patologie croniche che causano la cicatrizzazione del parenchima polmonare e dell'interstizio alveolare e la compromissione della funzionalità respiratoria. Dal momento che sono più di 200 le patologie raggruppate nella categoria delle ILD, una precisa identificazione è fondamentale per individuare la terapia migliore e formulare una prognosi. L'esame radiologico di riferimento è la tomografia computerizzata del torace ad alta risoluzione (High Resolution Computed Tomography, HRCT) e rappresenta un passaggio cruciale nel processo di diagnosi; nell'analizzare le immagini, infatti, il radiologo deve stabilire se vi è Usual Interstitial Pneumoniae (UIP), ovvero presenza di pattern istopatologici tipici della malattia, e valutarne l'estensione, correlata con la gravità delle alterazioni fisiologiche. Tuttavia, l'incidenza rara delle interstiziopatie fa sì che non tutti i radiologi abbiano un grado di esperienza adatto a individuare visivamente l'anomalia. Inoltre, la malattia si diffonde lungo tutti i polmoni e la segmentazione manuale risulta faticosa.
Nel tentativo di rimediare alla variabilità intra- ed inter-osservatore, sono state sviluppate tecniche per il riconoscimento automatico dei pattern UIP; vi sono approcci basati sull'analisi dell'istogramma e della texture dell'immagine ma, dal momento che i classificatori sono stati addestrati su label definite da operatori clinici diversi, presentano comunque un bias che è causa di identificazioni errate, o mancate, dei pattern.
Il deep learning, invece, si distingue dalle tecniche tradizionali perché fornisce strumenti che imparano autonomamente a classificare i dati. L'obiettivo del lavoro è stato, quindi, progettare e sviluppare la UIP-net, una rete neurale convoluzionale ad-hoc per la segmentazione automatica dei pattern UIP in immagini HRCT di pazienti con Fibrosi Idiopatica Polmonare (IPF), che è una sotto-categoria delle ILD.Source: ISTI Technical Reports 007/2020, 2020, 2020 DOI: 10.32079/isti-tr-2020/007 Metrics:
Analisi di immagini tomografiche ad alta risoluzione attraverso reti neurali convoluzionali per lo studio delle interstiziopatie polmonari Buongiorno R. The term Interstitial Lung Disease (ILD) refers to a large group of lung disorders, most of which cause scars of the interstitium, usually referred to as pulmonary fibrosis. Fibrosis reduces the ability of the air sacs to capture and carry oxygen into the bloodstream, leading to a progressive loss of the ability to breathe. Although ILDs are rare if taken individually, together they represent the most frequent cause of non-obstructive chronic lung disease. Nowadays, there are more than 200 different types of ILDs with varying causes, prognosis and therapies. Thus, identifying the correct type of ILD is necessary to make an accurate diagnosis.
The Idiopathic Pulmonary Fibrosis (IPF) is a chronic, progressive fibrosing interstitial pneumonia, which is classified among the ILDs with the poorest prognosis. The high variability and unpredictability of IPF course have traditionally made its clinical management hard. The recent introduction of antifibrotic drugs has opened novel therapeutic options for mild to moderate IPF. In this respect, treatment decisions highly rely on the assessment and quantification of IPF impact on the interstitium and its progression over time. High-Resolution Computed Tomography (HRCT) has demonstrated to have a key role in this frame, as it represents a non-invasive diagnostic modality to evaluate and quantify the extent of lung interstitium affected by IPF. In fact, IPF shows a typical radiological pattern, called Usual Interstitial Pneumonia (UIP) pattern, whose presence is usually assessed by radiologists to diagnose IPF. The HRCT features that characterize the UIP pattern are the presence and positioning of specific lung parenchymal anomalies, known as honeycombing , ground-glass opacification and fine reticulation. These anomalies appear in the HRCT scans with specific textural characteristics that are detected via a visual inspection of the imaging data. Assessing the diffusion of these anomalies is instrumental to understand the impact of IPF and to monitor its evolution over time. Quantitative and reliable approaches are in high demand in this respect, as the visual examination by radiologists suffers, by its nature, of poor reproducibility.
To overcome this issue, much research is being conducted to develop new techniques for automatic detection of lung diseases that may support radiologists during the diagnostic pathway, particularly in HRCT image analysis. Indeed, HRCT images evaluation by a Machine Learning (ML)- based algorithm might provide low-cost, reliable, real time automatic identification of UIP pattern with human-level accuracy in order to objectively quantify the percentage of lung volume affected by the disease in a reproducible way.
The purpose of this study was to develop a tool for UIP pattern recognition in HRCT images of patients with IPF using a deep-learning method based on a Convolutional Neural Network (CNN), called UIP-net. UIP-net takes as input a lung HRCT image with 492x492 pixels and outputs the corresponding binary map for the discrimination of disease and normal tissue. To train and evaluate the CNN, a dataset of 5000 images, derived by 20 CT scans from the same scanner, was used. The network performance yielded 83.7% BF-score and 84.6% sensitivity but in order to refine the binary masks produced by UIP-net, a post-processing operation was carried out. With post-processing, vessels, air-ways and tissue wrongly classified as belonging to the lungs were removed from the outputted masks. After post-processing, the results increased to 96.7% BF-score and 85.9% sensitivity. Thus, the network performance, in terms of BF-score and sensitivity, demonstrated that CNNs have the potential to reliably detect disease in order to evaluate its progression and become a supportive tool for radiologists.
Future works include adding more data to the training set in order to add multiple layers to the network to distinguish and quantify the different HRCT features of UIP pattern, improving the reproducibility and reliability of the CNN and using it for the detection of HRCT manifestations of Covid-19.
Can Magnetic Resonance Radiomics Analysis Discriminate Parotid Gland Tumors? A Pilot Study Gabelloni M., Faggioni L., Attanasio S., Vani V., Goddi A., Colantonio S., Germanese D., Caudai C., Bruschini L., Scarano M., Seccia V., Neri E. Our purpose is to evaluate the performance of magnetic resonance (MR) radiomics analysis for differentiating between malignant and benign parotid neoplasms and, among the latter, between pleomorphic adenomas and Warthin tumors. We retrospectively evaluated 75 T2-weighted images of parotid gland lesions, of which 61 were benign tumors (32 pleomorphic adenomas, 23 Warthin tumors and 6 oncocytomas) and 14 were malignant tumors. A receiver operating characteristics (ROC) curve analysis was performed to find the threshold values for the most discriminative features and determine their sensitivity, specificity and area under the ROC curve (AUROC). The most discriminative features were used to train a support vector machine classifier. The best classification performance was obtained by comparing a pleomorphic adenoma with a Warthin tumor (yielding sensitivity, specificity and a diagnostic accuracy as high as 0.8695, 0.9062 and 0.8909, respectively) and a pleomorphic adenoma with malignant tumors (sensitivity, specificity and a diagnostic accuracy of 0.6666, 0.8709 and 0.8043, respectively). Radiomics analysis of parotid tumors on conventional T2-weighted MR images allows the discrimination of pleomorphic adenomas from Warthin tumors and malignant tumors with a high sensitivity, specificity and diagnostic accuracy.Source: Diagnostics (Basel) 10 (2020). doi:10.3390/diagnostics10110900 DOI: 10.3390/diagnostics10110900 Metrics:
Architectural Heritage: 3D Documentation and Structural Monitoring Using UAV Germanese D, Pascali M. A., Berton A., Leone G. R., Moroni D., Jalil B., Tampucci M., Benassi A. Architectural heritage preservation and dissemination is a very important topic in Cultural Heritage. Since ancient structures may present areas which are dangerous or difficult to access, Unmanned Aerial Vehicles may be a smart solution for the safe and fast data acquisition. In this paper, we propose a method for the long term monitoring of cracking
patterns, based on image processing and marker-based technique. Also the paper includes the description of a pipeline for the reconstruction of interactive 3D scene of the historic structure to disseminate the acquired data, to provide the general public with info regarding the structural health of the structure, and possibly to support the drone pilot during the survey. The Introduction provides a state of the art about the crack monitoring from visible images; it follows a description of the proposed method, and the results of the experimentation carried out in a real
case study (the Ancient Fortress in Livorno, Italy). A specific section is devoted to the description of the front-end of augmented reality designed for heritage dissemination and to support the drone usage. Details about the future works conclude the paper.Source: Visual Pattern Extraction and Recognition for Cultural Heritage Understanding (VIPERC 2019), pp. 1–12, Pisa, January 30, 2019
A preliminary study for a marker-based crack monitoring in ancient structures Germanese D., Pascali M. A., Berton A., Leone G. R., Jalil B., Moroni D., Salvetti O., Tampucci M. Historical buildings are undeniably valuable documents of the history of the world. Their preservation has attracted considerable attention among modern societies, being a major issues both from economical and cultural point of view.
This paper describes how image processing and marker-based application may support the long-term monitoring of crack patterns in the context of cultural heritage preservation, with a special focus on ancient structures. In detail, this work includes a state of the art about the most used techniques in structural monitoring, a description of the proposed methodology and the experimentation details. A discussion about the results and future works concludes the paper.Source: 2nd International Conference on Applications of Intelligent Systems, Las Palmas de Gran Canaria, Spain, 07-09 January 2019 DOI: 10.1145/3309772.3309795 Metrics:
An E-Nose for the Monitoring of Severe Liver Impairment: A Preliminary Study Germanese D., Colantonio S., D'Acunto M., Romagnoli V., Salvati A., Brunetto M. Biologically inspired to mammalian olfactory system, electronic noses became popular during the last three decades. In literature, as well as in daily practice, a wide range of applications are reported. Nevertheless, the most pioneering one has been (and still is) the assessment of the human breath composition. In this study, we used a prototype of electronic nose, called Wize Sniffer (WS) and based it on an array of semiconductor gas sensor, to detect ammonia in the breath of patients suffering from severe liver impairment. In the setting of severely impaired liver, toxic substances, such as ammonia, accumulate in the systemic circulation and in the brain. This may result in Hepatic Encephalopathy (HE), a spectrum of neuro-psychiatric abnormalities which include changes in cognitive functions, consciousness, and behaviour. HE can be detected only by specific but time-consuming and burdensome examinations, such as blood ammonia levels assessment and neuro-psychological tests. In the presented proof-of-concept study, we aimed at investigating the possibility of discriminating the severity degree of liver impairment on the basis of the detected breath ammonia, in view of the detection of HE at its early stage.Source: Sensors (Basel) 19 (2019). doi:10.3390/s19173656 DOI: 10.3390/s19173656 Metrics:
La radiomica come elemento fondante della medicina di precisione in ambito oncologico Colantonio S., Carlini E., Caudai C., Germanese D., Manghi P., Pascali M. A., Barucci A., Farnesi D., Zoppetti N., Colcelli V., Pini R., Carpi R., Esposito M., Neri E., Romei C., Occhipinti M. Questo documento introduce e inquadra le attività che un gruppo interdisciplinare di ricercatori e clinici sta portando avanti grazie a tecniche di analisi di immagini, machine learning e intelligenza artificiale, a supporto della medicina di precisione in ambito oncologico. Partendo dalla comprensione del fenomeno fisico e dalla caratterizzazione dei processi biologici che sottendono alla formazione delle immagini biomedicali, attraverso tecniche di analisi radiomica dei dati radiologici e di mining di dati complessi, terogenei e multisorgente, le soluzioni studiate mirano a supportare i clinici nel continuum dei processi diagnostici, prognostici e terapeutici in ambito oncologico.Source: Ital-IA: primo Convegno Nazionale CINI sull'Intelligenza Artificiale, Roma, Italy, 18-19 marzo 2019
Radiomics to predict prostate cancer aggressiveness: a preliminary study Germanese D., Mercatelli L., Colantonio S., Miele V., Pascali M. A., Caudai C., Zoppetti N., Carpi R., Barucci A., Bertelli E., Agostini S. Radiomics is encouraging a paradigm shift in oncological diagnostics towards the symbiosis of radiology and Artificial Intelligence (AI) techniques. The aim is to exploit very accurate, robust image processing algorithms and provide quantitative information about the phenotypic differences of cancer traits. By exploring the association between this quantitative information and patients' prognosis, AI algorithms are boosting the power of radiomics in the perspective of precision oncology. However, the choice of the most suitable AI method can determine the success of a radiomic application. The current state-of-the art methods in radiomics aim at extracting statistical features from biomedical images and, then, process them with Machine Learning (ML) techniques. Many works have been reported in the literature presenting various combinations of radiomic features and ML methods. In this preliminary study, we aim to analyse the performance of a radiomic approach to predict prostate cancer (PCa) aggressiveness from multiarametric Magnetic Resonance Imaging (mp-MRI). Clinical mp-MRI data were collected from patients with histology-confirmed PCa and labelled by a team of expert radiologists. Such data were used to extract and select two sets of radiomic features; hence, the classification performances of five classifiers were assessed. This analysis is meant as a preliminary step towards the overall goal of investigating the potential of radiomic-based analyses.Source: BIBE 2019: 19th annual IEEE International Conference on Bioinformatics and Bioengineering, pp. 972–976, Athens, Greece, 28-30 October 2019 DOI: 10.1109/bibe.2019.00181 Metrics:
Metodologie di visione artificiale per la documentazione e il monitoraggio strutturale di costruzioni antiche mediante droni Leone G. R., Germanese D., Moroni D., Pascali M. A., Tampucci M., Berton A. La manutenzione e la salvaguardia del complesso patrimonio architettonico italiano rappresentano un'importante sfida che deve essere quotidianamente affrontata dalle soprintendenze e dalla amministrazioni locali e regionali. In quest'ambito, lo sviluppo delle tecnologie ICT può contribuire ad una gestione più efficiente e accurata del costruito storico. In questo intervento, si presenta un sistema di visione artificiale basato sull'utilizzo di droni che permette di monitorare lo stato di conservazione di edifici e strutture nel tempo, andando a quantificare l'entità di lesioni e ammaloramenti. Un frontend di realtà virtuale, ottenuto mediante tecniche fotogrammetriche, permette inoltre di visualizzare i dati trasmessi dal drone contestualmente ai dati raccolti da una rete di sensori wireless per il monitoraggio in situ delle strutture. Il sistema è stato testato in tre diversi casi di studio in Toscana.Source: Ital-IA 2019, primo Convegno Nazionale CINI sull'Intelligenza Artificiale, WORKSHOP AI for CULTURAL HERITAGE, Roma, 18-19 Marzo 2019
May radiomic data predict prostate cancer aggressiveness? Germanese D., Colantonio S., Caudai C., Pascali M. A., Barucci A., Zoppetti N., Agostini S., Bertelli E., Mercatelli L., Miele V., Carpi R. Radiomics can quantify tumor phenotypic characteristics non-invasively by defining a signature correlated with biological information. Thanks to algorithms derived from computer vision to extract features from images, and machine learning methods to mine data, Radiomics is the perfect case study of application of Artificial Intelligence in the context of precision medicine. In this study we investigated the association between radiomic features extracted from multi-parametric magnetic resonance imaging (mp-MRI)of prostate cancer (PCa) and the tumor histologic subtypes (using Gleason Score) using machine learning algorithms, in order to identify which of the mp-MRI derived radiomic features can distinguish high and low risk PCa.Source: CAIP 2019 - International Conference on Computer Analysis of Images and Patterns, pp. 65–75, Salerno, Italy, 6 September, 2019 DOI: 10.1007/978-3-030-29930-9_7 Metrics:
Towards chronic liver dysfunction self-monitoring: a proof-of-concept study Germanese D., Colantonio S., D'Acunto M., Brunetto M., Romagnoli V., Salvati A. The liver is our very own chemical processing plant as it plays a vital role in maintaining the body's metabolic balance. Liver's health is assessed by a group of clinical tests (such as blood tests, ultrasonographic imaging, liver biopsy) most of which are invasive and burdensome for the patients. In the setting of severely scarred liver, toxic substances, such as ammonia, have fewer opportunities to be detoxified. Accumulation of ammonia in the systemic circulation and in the brain may result in Hepatic Encephalopathy (HE), a spectrum of neuropsychiatric abnormalities which entails changes in consciousness, intellectual functions, behavior. Minimal HE has attracted increasing attention, as it does not cause detectable changes in personality or behaviour, but the complex and sustained attention is impaired. Hence, it can be detected only by specific but biased, time-consuming and burdensome examinations, such as blood ammonia levels assessment and neuro-psychological tests. The obstrusivity of the majority of the liver function clinical tests, and, in case of minimal HE, the lack of reliable examinations, are encouraging the scientific community to look for alternative diagnostic methods. For this purpose, the exploitation of a non-invasive technique such as breath analysis, to identify chronic liver disease, discriminate among its degree of severity and detect the onset of HE, could be a step forward for clinical diagnosis. In this paper, we report a proof-of-concept study that aimed at detecting ammonia in the breath of patients suffering from chronic liver disease by means of a low-cost, easy-to-use, gas-sensors based device. Not only, we also aimed at investigating the possibility of discriminating the several severity degree of liver impairment on the basis of the detected ammonia.Source: ISCC 2019 - IEEE Symposium on Computers and Communications, Barcelona, Spain, 29 June - 3 July, 2019 DOI: 10.1109/iscc47284.2019.8969605 Metrics: