Article
Construction & Building Technology
Gerhard Schubert, Ivan Bratoev, Frank Petzold
Summary: The benefits of design decision support systems in architectural planning have been proven in research and are increasingly used in practice. These systems provide objective information to support decision-making with well-founded data and statements. However, there are challenges to be addressed and a vision for the future of these systems is proposed, highlighting the transition from reactive to proactive assistance.
Article
Computer Science, Information Systems
Subhi M. Alrubei, Edward Ball, Jonathan M. Rigelsford
Summary: This article presents a distributed and decentralized architecture for implementing distributed artificial intelligence (DAI) using IoT hardware platforms. The DAI system utilizes a decentralized, self-managed blockchain technology to allow trusted interactions between distributed neurons. The proposed architecture has been analyzed, implemented, and tested using low-cost IoT devices, demonstrating the feasibility of implementing DAI while maintaining system accuracy. The integration of blockchain adds security and trust to the system.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Flavio Rosendo Da Silva Oliveira, Fernando Buarque De Lima Neto
Summary: This paper proposes an approach that integrates artificial intelligence techniques into decision support systems to solve complex decision problems. By providing reasonable explanations and feasible candidate solutions, this approach improves decision makers' efficiency and effectiveness. Two case studies in the health and public security areas demonstrate superior metrics in feasibility and plausibility for this proposed approach.
Review
Computer Science, Information Systems
Yuhan Du, Catherine McNestry, Lan Wei, Anna Markella Antoniadi, Fionnuala M. McAuliffe, Catherine Mooney
Summary: This paper reviews the current state of machine learning-based Clinical Decision Support Systems (CDSSs) in pregnancy care and identifies several areas for improvement, including lack of explainability, limited experimentation and validation, and lack of consideration for culture and race. Despite these limitations, studies have shown positive effects of CDSSs in pregnancy care, highlighting their potential to enhance clinical practice.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2023)
Review
Computer Science, Information Systems
Anindya Pradipta Susanto, David Lyell, Bambang Widyantoro, Shlomo Berkovsky, Farah Magrabi
Summary: This study aims to summarize the research literature evaluating machine learning (ML)-based clinical decision support (CDS) systems in healthcare settings. The findings suggest that ML-based CDS systems have been applied successfully in assisting clinical tasks, but their effects on decision-making, care delivery, and patient outcomes are mixed.
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
(2023)
Article
Computer Science, Information Systems
Cecilia Panigutti, Alan Perotti, Andre Panisson, Paolo Bajardi, Dino Pedreschi
Summary: The widespread use of algorithmic decision-making raises concerns about unintended bias in AI systems, especially in critical settings like healthcare. FairLens is introduced as a method to detect and explain biases in models, helping healthcare experts identify and address biases before using the model in clinical decision-making.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Raphael Y. Cohen, Aaron D. Sodickson
Summary: Current AI-driven research in radiology often lacks accessible resources and expertise for small and resource-limited labs. Clinicians participating in AI research typically have sufficient funding, staffing, and experience with AI and computing, or access to colleagues or facilities with such resources. However, the current clinician-oriented imaging data poses challenges for machine learning initiatives, making AI research and innovation inefficient and costly. This article presents a system and methodology that address infrastructure and platform needs while reducing staffing and resource barriers, enabling radiologists to drive new AI innovations.
JOURNAL OF DIGITAL IMAGING
(2023)
Article
Computer Science, Information Systems
Sijing Duan, Dan Wang, Ju Ren, Feng Lyu, Ye Zhang, Huaqing Wu, Xuemin Shen
Summary: This paper provides a comprehensive survey on distributed artificial intelligence (DAI) empowered by end-edge-cloud computing (EECC). It explores the benefits of the EECC paradigm in supporting distributed AI, introduces fundamental technologies for distributed AI, and discusses optimization technologies empowered by EECC for distributed training and inference. It also addresses security and privacy threats in the DAI-EECC architecture and reviews defense technologies. Furthermore, it presents promising applications enabled by DAI-EECC and highlights research challenges and open issues.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Article
Computer Science, Artificial Intelligence
Xihe Qiu, Xiaoyu Tan, Qiong Li, Shaotao Chen, Yajun Ru, Yaochu Jin
Summary: Precise medication dosing is crucial for ICU patients. This paper proposes an individualized dosing policy using a latent batch-constrained deep reinforcement learning algorithm to determine the optimal initial dose and minimize risks and complications associated with medication dosing.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Health Care Sciences & Services
Mengting Ji, Georgi Z. Genchev, Hengye Huang, Ting Xu, Hui Lu, Guangjun Yu
Summary: This study aimed to develop and validate a measurement instrument and test the interrelationships of evaluation variables for an artificial intelligence-enabled clinical decision support system evaluation framework. The results showed that user acceptance is the central dimension of artificial intelligence-enabled clinical decision support system success, directly influenced by perceived ease of use, information quality, service quality, and perceived benefit, and indirectly influenced through system quality and information quality.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Review
Medicine, General & Internal
Sira Kim, Eung-Hee Kim, Hun-Sung Kim
Summary: With the introduction of electronic medical records, the use of clinical decision support systems has increased. However, current CDSS technology is not yet mature and requires continuous updating, which demands significant time and manpower investments. Furthermore, previous research on the potential effectiveness and further development of CDSSs is lacking.
YONSEI MEDICAL JOURNAL
(2022)
Editorial Material
Computer Science, Theory & Methods
Pavan Balaji, Jidong Zhai, Min Si
Summary: The papers in the special section discuss the latest technologies and challenges of parallel and distributed computing techniques for AI, ML, and DL. These technologies have been widely adopted in various domains due to their capabilities in processing and modeling unstructured input data.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2021)
Review
Surgery
Tyler J. Loftus, Maria S. Altieri, Jeremy A. Balch, Kenneth L. Abbott, Jeff Choi, Jayson S. Marwaha, Daniel A. Hashimoto, Gabriel A. Brat, Yannis Raftopoulos, Heather L. Evans, Gretchen P. Jackson, Danielle S. Walsh, Christopher J. Tignanelli
Summary: This study summarizes the state-of-the-art artificial intelligence-enabled decision support in surgery and quantifies deficiencies in scientific rigor and reporting. The results show that these models are limited by reliance on internal validation, small sample sizes, and failure to report confidence intervals and clinical implementation.
Article
Clinical Neurology
Ela Marie Z. Akay, Adam Hilbert, Benjamin G. Carlisle, Vince I. Madai, Matthias A. Mutke, Dietmar Frey
Summary: This study systematically reviews the methodological robustness and clinical implementation constraints of AI-based clinical decision support systems in acute ischemic stroke. The findings reveal the heterogeneity of data sources, methods, and reporting practices, and suggest practical recommendations for successful implementation of AI research in stroke treatment and diagnosis.
Article
Computer Science, Theory & Methods
Haochen Hua, Yutong Li, Tonghe Wang, Nanqing Dong, Wei Li, Junwei Cao
Summary: In recent years, the widespread popularity of the Internet of Things (IoT) has greatly promoted the development of Artificial Intelligence (AI). However, the traditional cloud computing model may face difficulties in independently handling the massive data generated by IoT. In response, the new computing model of Edge Computing (EC) has gained extensive attention. Scholars have found that traditional methods have limitations in enhancing the performance of EC, leading to the exploration of AI as a solution. This article serves as a guide to explore new research ideas in optimizing EC using AI and applying AI to other fields under the EC architecture.
ACM COMPUTING SURVEYS
(2023)
Article
Materials Science, Multidisciplinary
A. Porter, K. Kanxheri, I. Lopez, A. Oh, L. Servoli, C. Talamonti
Summary: A new prototype 3D diamond dosimeter, featuring laser-written graphitic surface connections and bonding pads, was tested on medical dosimetry. The device was made with a polycrystalline chemical vapour deposition diamond substrate and showed potential advantages over single crystal diamond in terms of size and cost. The 3D design of the device allowed for more efficient charge collection and reduced distortion of the electric field close to the surface of the diamond. By removing metal-diamond contacts, the operating voltage was lowered without affecting dose-rate independence.
DIAMOND AND RELATED MATERIALS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Alessandra Zorz, Andrea D'Alessio, Federica Guida, Rehema Masaka Ramadan, Elisa Richetta, Lea Cuppari, Riccardo Pellerito, Gian Mauro Sacchetti, Marco Brambilla, Marta Paiusco, Michele Stasi, Roberta Matheoud
Summary: This study aims to investigate the changes in quantitative parameters of 18F-FDG PET imaging with respect to emission scan duration (ESD) and body-mass-index (BMI) in phantom and patients. Results show that a reduction in ESD may significantly impact the variations of SUVmax and SULmax in 18F-FDG PET/CT imaging. The use of SUL is recommended for lesion uptake quantification, as it is unaffected by BMI variation.
PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Paolo Bosco, Marta Lancione, Alessandra Retico, Anna Nigri, Domenico Aquino, Francesca Baglio, Irene Carne, Stefania Ferraro, Giovanni Giulietti, Antonio Napolitano, Fulvia Palesi, Luigi Pavone, Giovanni Savini, Fabrizio Tagliavini, Gandini Wheeler-Kingshott, Michela Tosetti, Laura Biagi
Summary: This study assessed the brain anatomical variability of MRI-derived measurements obtained from T1-weighted images according to standardized procedures. The results indicated some variability in the measurements obtained from multi-site and multi-vendor datasets, but no systematic biases were detected.
PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Leonardo Ubaldi, Sara Saponaro, Alessia Giuliano, Cinzia Talamonti, Alessandra Retico
Summary: This study aims to discriminate between high-grade (HGG) and low-grade (LGG) gliomas using a robust processing pipeline based on Radiomics and Machine Learning (ML) with multiparametric Magnetic Resonance Imaging (MRI) data. The results show that using MRI-reliable features improves the performance in glioma grade classification.
PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS
(2023)
Article
Engineering, Biomedical
Matthew J. Large, Marco Bizzarri, Lucio Calcagnile, Mirco Caprai, Anna Paola Caricato, Roberto Catalano, Giuseppe A. P. Cirrone, Tommaso Croci, Giacomo Cuttone, Sylvain Dunand, Michele Fabi, Luca Frontini, Benedetta Gianfelici, Catia Grimani, Maria Ionica, Keida Kanxheri, Michael L. F. Lerch, Valentino Liberali, Maurizio Martino, Giuseppe Maruccio, Giovanni Mazza, Mauro Menichelli, Anna Grazia Monteduro, Francesco Moscatelli, Arianna Morozzi, Stefania Pallotta, Andrea Papi, Daniele Passeri, Maddalena Pedio, Giada Petringa, Francesca Peverini, Lorenzo Piccolo, Pisana Placidi, Gianluca Quarta, Silvia Rizzato, Alessandro Rossi, Giulia Rossi, Vincent de Rover, Federico Sabbatini, Leonello Servoli, Alberto Stabile, Cinzia Talamonti, Luca Tosti, Mattia Villani, Richard J. Wheadon, Nicolas Wyrsch, Nicola Zema, Marco Petasecca
Summary: Microbeam radiation therapy (MRT) is a promising alternative radiotherapy treatment method that effectively controls radioresistant tumors while sparing healthy tissue. In this study, radiation-hardened a-Si:H diodes were characterized for x-ray dosimetry and real-time beam monitoring in high-flux beamlines for MRT. The devices showed excellent radiation hardness and accurate dosimetric performance, making them suitable for high dose-rate environments like FLASH and MRT.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Physics, Multidisciplinary
Francesca Lizzi, Ian Postuma, Francesca Brero, Raffaella Fiamma Cabini, Maria Evelina Fantacci, Alessandro Lascialfari, Piernicola Oliva, Lisa Rinaldi, Alessandra Retico
Summary: This study presents an improved version of the LungQuant automatic segmentation software, which uses three deep neural networks to evaluate lung involvement in COVID-19 pneumonia patients through CT scans. The new version introduces BB-net for defining lung boundaries, adds a new term in the U-net loss function for lesion segmentation, and includes a post-processing procedure to separate the right and left lungs. The results show that LungQuant v2 achieves high accuracy in lung and lesion segmentation with vDSC and sDSC scores of 0.96/0.97 and 0.69/0.83 respectively.
EUROPEAN PHYSICAL JOURNAL PLUS
(2023)
Article
Chemistry, Multidisciplinary
Alessandra Vendrame, Cristina Cappelletto, Paola Chiovati, Lorenzo Vinante, Masud Parvej, Angela Caroli, Giovanni Pirrone, Loredana Barresi, Annalisa Drigo, Michele Avanzo
Summary: Deep Bidirectional Long Short-Term Memory (BLSTM) recurrent neural networks were used to predict eligibility for deep inspiration breath-hold (DIBH) radiotherapy treatment in patients with left breast cancer based on analysis of respiratory signals. The BLSTM-RNN accurately classified patients eligible for DIBH, achieving high accuracy, specificity, sensitivity, F1 score, and AUC in the test dataset. This provides promising results for the development of an accurate and robust decision system to assist the radiotherapy team in assigning patients to DIBH.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Federico Campo, Alessandra Retico, Sara Calderoni, Piernicola Oliva
Summary: Magnetic resonance imaging (MRI) is important in identifying brain underpinnings in neuropsychiatric disorders, including Autism Spectrum Disorders (ASD). Two approaches, DNN and ComBat-GAM, are comparable in dealing with multicenter MRI data harmonization.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Alessandra Retico, Francesca Maggiorelli, Giulio Giovannetti, Eddy Boskamp, Fraser Robb, Marco Fantasia, Angelo Galante, Marcello Alecci, Gianluigi Tiberi, Michela Tosetti
Summary: The present study aims to optimize, construct, and validate a double-tuned H-1-Na-23 volume RF coil suitable for human head imaging at 7 T, based on the birdcage geometry. A four-ring model has been selected and evaluated through simulations based on Maxwell's equations to ensure RF magnetic field homogeneity and efficiency. The best-performing four-ring model has been built and tested on a workbench using a cylindrical phantom filled with a 0.05 M saline solution, demonstrating its potential for H-1-Na-23 human head imaging at 7 T.
Article
Radiology, Nuclear Medicine & Medical Imaging
Camilla Scapicchio, Andrea Chincarini, Elena Ballante, Luca Berta, Eleonora Bicci, Chandra Bortolotto, Francesca Brero, Raffaella Fiamma Cabini, Giuseppe Cristofalo, Salvatore Claudio Fanni, Maria Evelina Fantacci, Silvia Figini, Massimo Galia, Pietro Gemma, Emanuele Grassedonio, Alessandro Lascialfari, Cristina Lenardi, Alice Lionetti, Francesca Lizzi, Maurizio Marrale, Massimo Midiri, Cosimo Nardi, Piernicola Oliva, Noemi Perillo, Ian Postuma, Lorenzo Preda, Vieri Rastrelli, Francesco Rizzetto, Nicola Spina, Cinzia Talamonti, Alberto Torresin, Angelo Vanzulli, Federica Volpi, Emanuele Neri, Alessandra Retico
Summary: This study evaluated the performance of the LungQuant system, a software for quantitative analysis of chest CT, by comparing its results with independent visual evaluations by clinical experts. The aim was to assess the ability of the automated tool to extract quantitative information from lung CT relevant to the clinical assessment of COVID-19 pneumonia.
EUROPEAN RADIOLOGY EXPERIMENTAL
(2023)
Article
Instruments & Instrumentation
M. Menichelli, M. Bizzarri, M. Boscardin, L. Calcagnile, M. Caprai, A. P. Caricato, G. A. P. Cirrone, M. Crivellari, I. Cupparo, G. Cuttone, S. Dunand, L. Fano, B. Gianfelici, O. Hammad, M. Ionica, K. Kanxheri, M. Large, G. Maruccio, A. G. Monteduro, F. Moscatelli, A. Morozzi, A. Papi, D. Passeri, M. Pedio, M. Petasecca, G. Petringa, F. Peverini, G. Quarta, S. Rizzato, A. Rossi, G. Rossi, A. Scorzoni, L. Servoli, C. Talamonti, G. Verzellesi, N. Wyrsch
Summary: Hydrogenated amorphous silicon is commonly used in radiation-resistant detectors for particle beam flux measurements and space solar panels. This study focuses on p-i-n and charge selective contacts planar diode detectors with a thickness of 10 μm, which were irradiated with neutrons at two fluence values. The radiation resistance of the detectors was evaluated by measuring leakage current and response to x-ray photons. The results show that the leakage current increased by a factor of 2 after irradiation at 1016 neq/cm2, but was completely recovered after annealing for p-i-n devices. X-ray dosimetric sensitivity degraded after irradiation, but partially recovered for charge selective contact devices and increased for p-i-n devices after annealing. For the irradiation test at 5 x 1016 neq/cm2, noticeable degradation in leakage current and x-ray sensitivity was observed after storage, with a small recovery after annealing.
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT
(2023)
Article
Medicine, General & Internal
Fabrizio Gozzi, Marco Bertolini, Pietro Gentile, Laura Verzellesi, Valeria Trojani, Luca De Simone, Elena Bolletta, Valentina Mastrofilippo, Enrico Farnetti, Davide Nicoli, Stefania Croci, Lucia Belloni, Alessandro Zerbini, Chantal Adani, Michele De Maria, Areti Kosmarikou, Marco Vecchi, Alessandro Invernizzi, Fiorella Ilariucci, Magda Zanelli, Mauro Iori, Luca Cimino
Summary: This cross-sectional single-center study investigated the ability of anterior segment optical coherence tomography (AS-OCT) to distinguish vitreous involvement due to vitreoretinal lymphoma (VRL) from vitritis in uveitis. AS-OCT images from 28 patients were analyzed using radiomics software, and a classification model was built using xgboost python function. The model achieved an 87% accuracy in diagnosing VRL or uveitis.
Proceedings Paper
Engineering, Electrical & Electronic
M. Menichelli, L. Antognini, A. Bashiri, M. Bizzarri, L. Calcagnile, M. Caprai, A. P. Caricato, R. Catalano, G. A. P. Cirrone, T. Croci, G. Cuttone, S. Dunand, M. Fabi, L. Frontini, C. Grimani, M. Ionica, K. Kanxheri, M. Large, V. Liberali, M. Martino, G. Maruccio, G. Mazza, A. G. Monteduro, A. Morozzi, F. Moscatelli, S. Pallotta, A. Papi, D. Passeri, M. Pedio, M. Petasecca, G. Petringa, F. Peverini, L. Piccolo, P. Placidi, G. Quarta, S. Rizzato, G. Rossi, F. Sabbatini, A. Stabile, L. Servoli, C. Talamonti, L. Tosti, M. Villani, R. J. Wheadon, N. Wyrsch, N. Zema
Summary: This paper examines the dosimetric X-ray response of p-i-n diodes deposited on Polyimide. The linearity of the photocurrent response to X-rays versus dose-rate is studied, and the dosimetric sensitivity at various bias voltages is extracted. This study is repeated for devices with two different areas (2 mm x 2 mm and 5 mm x 5 mm), and the stability of X-ray response over time is also demonstrated.
2023 9TH INTERNATIONAL WORKSHOP ON ADVANCES IN SENSORS AND INTERFACES, IWASI
(2023)