One for all? Assessing the quality of Italian hospital care with the "benefit of the doubt" composite indicator methods.

Quality assessment in healthcare systems is challenging due to the multidimensional nature of healthcare services. This study evaluates the overall quality provided by hospitals using composite indicators under the Benefit of the Doubt (BoD) approach, which determines the weights of the indicators with minimal assumptions. We used data from 2015-2020 for Italian Local Health Authorities (LHAs) for 21 outcome measures, applying various non-parametric methods to address aggregation and weighting challenges. Our results show that the BoD measures are robust and effectively capture the dynamics of the quality of LHA, even during external shocks such as the COVID-19 pandemic. This research highlights the importance of methodological choices in the construction of composite indicators and demonstrates the effectiveness of the BoD approach in providing a comprehensive measure of healthcare quality.

MITS-GAN: Safeguarding medical imaging from tampering with generative adversarial networks.

The progress in generative models, particularly Generative Adversarial Networks (GANs), opened new possibilities for image generation but raised concerns about potential malicious uses, especially in sensitive areas like medical imaging. This study introduces MITS-GAN, a novel approach to prevent tampering in medical images, with a specific focus on CT scans. The approach disrupts the output of the attacker's CT-GAN architecture by introducing finely tuned perturbations that are imperceptible to the human eye. Specifically, the proposed approach involves the introduction of appropriate Gaussian noise to the input as a protective measure against various attacks. Our method aims to enhance tamper resistance, comparing favorably to existing techniques. Experimental results on a CT scan demonstrate MITS-GAN's superior performance, emphasizing its ability to generate tamper-resistant images with negligible artifacts. As image tampering in medical domains poses life-threatening risks, our proactive approach contributes to the responsible and ethical use of generative models. This work provides a foundation for future research in countering cyber threats in medical imaging. Models and codes are publicly available.1.

Nose-to-Brain Drug Delivery and Physico-Chemical Properties of Nanosystems: Analysis and Correlation Studies of Data from Scientific Literature.

Background: In the last few decades, nose-to-brain delivery has been investigated as an alternative route to deliver molecules to the Central Nervous System (CNS), bypassing the Blood-Brain Barrier. The use of nanotechnological carriers to promote drug transfer via this route has been widely explored. The exact mechanisms of transport remain unclear because different pathways (systemic or axonal) may be involved. Despite the large number of studies in this field, various aspects still need to be addressed. For example, what physicochemical properties should a suitable carrier possess in order to achieve this goal? To determine the correlation between carrier features (eg, particle size and surface charge) and drug targeting efficiency percentage (DTE%) and direct transport percentage (DTP%), correlation studies were performed using machine learning. Methods: Detailed analysis of the literature from 2010 to 2021 was performed on Pubmed in order to build "NANOSE" database. Regression analyses have been applied to exploit machine-learning technology. Results: A total of 64 research articles were considered for building the NANOSE database (102 formulations). Particle-based formulations were characterized by an average size between 150-200 nm and presented a negative zeta potential (ZP) from -10 to -25 mV. The most general-purpose model for the regression of DTP/DTE values is represented by Decision Tree regression, followed by K-Nearest Neighbors Regressor (KNeighbor regression). Conclusion: A literature review revealed that nose-to-brain delivery has been widely investigated in neurodegenerative diseases. Correlation studies between the physicochemical properties of nanosystems (mean size and ZP) and DTE/DTP parameters suggest that ZP may be more significant than particle size for DTP/DTE predictability.

COVID-19 Infection Percentage Estimation from Computed Tomography Scans: Results and Insights from the International Per-COVID-19 Challenge.

COVID-19 analysis from medical imaging is an important task that has been intensively studied in the last years due to the spread of the COVID-19 pandemic. In fact, medical imaging has often been used as a complementary or main tool to recognize the infected persons. On the other hand, medical imaging has the ability to provide more details about COVID-19 infection, including its severity and spread, which makes it possible to evaluate the infection and follow-up the patient's state. CT scans are the most informative tool for COVID-19 infection, where the evaluation of COVID-19 infection is usually performed through infection segmentation. However, segmentation is a tedious task that requires much effort and time from expert radiologists. To deal with this limitation, an efficient framework for estimating COVID-19 infection as a regression task is proposed. The goal of the Per-COVID-19 challenge is to test the efficiency of modern deep learning methods on COVID-19 infection percentage estimation (CIPE) from CT scans. Participants had to develop an efficient deep learning approach that can learn from noisy data. In addition, participants had to cope with many challenges, including those related to COVID-19 infection complexity and crossdataset scenarios. This paper provides an overview of the COVID-19 infection percentage estimation challenge (Per-COVID-19) held at MIA-COVID-2022. Details of the competition data, challenges, and evaluation metrics are presented. The best performing approaches and their results are described and discussed.

Boosting multiple sclerosis lesion segmentation through attention mechanism.

Magnetic resonance imaging is a fundamental tool to reach a diagnosis of multiple sclerosis and monitoring its progression. Although several attempts have been made to segment multiple sclerosis lesions using artificial intelligence, fully automated analysis is not yet available. State-of-the-art methods rely on slight variations in segmentation architectures (e.g. U-Net, etc.). However, recent research has demonstrated how exploiting temporal-aware features and attention mechanisms can provide a significant boost to traditional architectures. This paper proposes a framework that exploits an augmented U-Net architecture with a convolutional long short-term memory layer and attention mechanism which is able to segment and quantify multiple sclerosis lesions detected in magnetic resonance images. Quantitative and qualitative evaluation on challenging examples demonstrated how the method outperforms previous state-of-the-art approaches, reporting an overall Dice score of 89% and also demonstrating robustness and generalization ability on never seen new test samples of a new dedicated under construction dataset.

Development and User Evaluation of a Food-recognition app (FoodRec): Experimental Data and Qualitative Analysis.

Background: different studies revealed strong correlation between smoking cessation and a worsening of the diet, whose consequence include loss of appetite, weight loss, etc. Objective: the objective of FoodRec project is to exploit technology to monitor the dietary habits of people during their smoke quitting process, catching relevant changes which can affect the patient health and the success of the process. This work was an uncontrolled pre-test post-test open pilot study in which an interdisciplinary group created an app for food recognition (FoodRec) to monitor their mood status and dietary habits during the test period. Methods: participants used the FoodRec App for two consecutive weeks for usability and suitability assessment. Tests included 149 smokers involved in a smoke quitting process, aged between 19 and 80. For the quantitative test, data were analyzed regarding users features, meals uploads, mood states and drink intakes. For the qualitative test, a user evaluation test of the app has been performed with four assignments being carried out on a group of 50 participants. Results: the App was perceived as extremely user-friendly and lightweight. It also turned out to be useful in the perception of users' dietary habits and helpful in relieving the stress of a food intake reduction process. Conclusion: this work investigated the role and impact of the FoodRec App in a large international and multicultural context. The experience gained in the current study will be used to modify and refine the large international RCT protocol version of the app.

Impact of Eating Context on Dietary Choices of College Students: Evidence from the HEALTHY-UNICT Project.

While personal characteristics have been evaluated as determinants of dietary choices over the years, only recently studies have looked at the impact of eating context. Examining eating context, however, can be challenging. Here, we propose the use of a web-app for the Ecological Momentary Assessment of dietary habits among 138 college students from Catania (Italy) and therefore for examining the impact of eating context on dietary choices. Eating away from home was associated with lower odds of consuming vegetables, fruits, and legumes and higher odds of consuming processed meat, salty snacks, and alcoholic drinks compared with eating at home. Eating in the company of other people was associated with higher odds of consuming vegetables, red meat, fish, legumes, milk, and sugar-sweetened beverages and lower odds of consuming nuts than eating alone. This study proposed a new way to capture and assess how eating environment might affect dietary habits. Based on our results, meal location and social context have significant effects on the dietary choices of college students, pointing to the need to incorporate these aspects into further epidemiological studies.

The Face Deepfake Detection Challenge.

Multimedia data manipulation and forgery has never been easier than today, thanks to the power of Artificial Intelligence (AI). AI-generated fake content, commonly called Deepfakes, have been raising new issues and concerns, but also new challenges for the research community. The Deepfake detection task has become widely addressed, but unfortunately, approaches in the literature suffer from generalization issues. In this paper, the Face Deepfake Detection and Reconstruction Challenge is described. Two different tasks were proposed to the participants: (i) creating a Deepfake detector capable of working in an "in the wild" scenario; (ii) creating a method capable of reconstructing original images from Deepfakes. Real images from CelebA and FFHQ and Deepfake images created by StarGAN, StarGAN-v2, StyleGAN, StyleGAN2, AttGAN and GDWCT were collected for the competition. The winning teams were chosen with respect to the highest classification accuracy value (Task I) and "minimum average distance to Manhattan" (Task II). Deep Learning algorithms, particularly those based on the EfficientNet architecture, achieved the best results in Task I. No winners were proclaimed for Task II. A detailed discussion of teams' proposed methods with corresponding ranking is presented in this paper.

Development of a Web-App for the Ecological Momentary Assessment of Dietary Habits among College Students: The HEALTHY-UNICT Project.

The transition from adolescence to adulthood is a critical period for the development of healthy behaviors. Yet, it is often characterized by unhealthy food choices. Considering the current pandemic scenario, it is also essential to assess the effects of coronavirus disease-19 (COVID-19) on lifestyles and diet, especially among young people. However, the assessment of dietary habits and their determinants is a complex issue that requires innovative approaches and tools, such as those based on the ecological momentary assessment (EMA). Here, we describe the first phases of the "HEALTHY-UNICT" project, which aimed to develop and validate a web-app for the EMA of dietary data among students from the University of Catania, Italy. The pilot study included 138 students (mean age 24 years, SD = 4.2; 75.4% women), who used the web-app for a week before filling out a food frequency questionnaire with validation purposes. Dietary data obtained through the two tools showed moderate correlations, with the lowest value for butter and margarine and the highest for pizza (Spearman's correlation coefficients of 0.202 and 0.699, respectively). According to the cross-classification analysis, the percentage of students classified into the same quartile ranged from 36.9% for vegetable oil to 58.1% for pizza. In line with these findings, the weighted-kappa values ranged from 0.15 for vegetable oil to 0.67 for pizza, and most food categories showed values above 0.4. This web-app showed good usability among students, assessed through a 19-item usability scale. Moreover, the web-app also had the potential to evaluate the effect of the COVID-19 pandemic on students' behaviors and emotions, showing a moderate impact on sedentary activities, level of stress, and depression. These findings, although interesting, might be confirmed by the next phases of the HEALTHY-UNICT project, which aims to characterize lifestyles, dietary habits, and their relationship with anthropometric measures and emotions in a larger sample of students.

Advanced eNose-Driven Pedestrian Tracking Pipeline for Intelligent Car Driver Assisting System: Preliminary Results.

From a biological point of view, alcohol human attentional impairment occurs before reaching a Blood Alcohol Content (BAC index) of 0.08% (0.05% under the Italian legislation), thus generating a significant impact on driving safety if the drinker subject is driving a car. Car drivers must keep a safe driving dynamic, having an unaltered physiological status while processing the surrounding information coming from the driving scenario (e.g., traffic signs, other vehicles and pedestrians). Specifically, the identification and tracking of pedestrians in the driving scene is a widely investigated problem in the scientific community. The authors propose a full, deep pipeline for the identification, monitoring and tracking of the salient pedestrians, combined with an intelligent electronic alcohol sensing system to properly assess the physiological status of the driver. More in detail, the authors propose an intelligent sensing system that makes a common air quality sensor selective to alcohol. A downstream Deep 1D Temporal Residual Convolutional Neural Network architecture will be able to learn specific embedded alcohol-dynamic features in the collected sensing data coming from the GHT25S air-quality sensor of STMicroelectronics. A parallel deep attention-augmented architecture identifies and tracks the salient pedestrians in the driving scenario. A risk assessment system evaluates the sobriety of the driver in case of the presence of salient pedestrians in the driving scene. The collected preliminary results confirmed the effectiveness of the proposed approach.

Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap.

This paper proposes a novel approach for semi-supervised domain adaptation for holistic regression tasks, where a DNN predicts a continuous value y∈R given an input image x. The current literature generally lacks specific domain adaptation approaches for this task, as most of them mostly focus on classification. In the context of holistic regression, most of the real-world datasets not only exhibit a covariate (or domain) shift, but also a label gap-the target dataset may contain labels not included in the source dataset (and vice versa). We propose an approach tackling both covariate and label gap in a unified training framework. Specifically, a Generative Adversarial Network (GAN) is used to reduce covariate shift, and label gap is mitigated via label normalisation. To avoid overfitting, we propose a stopping criterion that simultaneously takes advantage of the Maximum Mean Discrepancy and the GAN Global Optimality condition. To restore the original label range-that was previously normalised-a handful of annotated images from the target domain are used. Our experimental results, run on 3 different datasets, demonstrate that our approach drastically outperforms the state-of-the-art across the board. Specifically, for the cell counting problem, the mean squared error (MSE) is reduced from 759 to 5.62; in the case of the pedestrian dataset, our approach lowered the MSE from 131 to 1.47. For the last experimental setup, we borrowed a task from plant biology, i.e., counting the number of leaves in a plant, and we ran two series of experiments, showing the MSE is reduced from 2.36 to 0.88 (intra-species), and from 1.48 to 0.6 (inter-species).

Deep Neuro-Vision Embedded Architecture for Safety Assessment in Perceptive Advanced Driver Assistance Systems: The Pedestrian Tracking System Use-Case.

In recent years, the automotive field has been changed by the accelerated rise of new technologies. Specifically, autonomous driving has revolutionized the car manufacturer's approach to design the advanced systems compliant to vehicle environments. As a result, there is a growing demand for the development of intelligent technology in order to make modern vehicles safer and smarter. The impact of such technologies has led to the development of the so-called Advanced Driver Assistance Systems (ADAS), suitable to maintain control of the vehicle in order to avoid potentially dangerous situations while driving. Several studies confirmed that an inadequate driver's physiological condition could compromise the ability to drive safely. For this reason, assessing the car driver's physiological status has become one of the primary targets of the automotive research and development. Although a large number of efforts has been made by researchers to design safety-assessment applications based on the detection of physiological signals, embedding them into a car environment represents a challenging task. These mentioned implications triggered the development of this study in which we proposed an innovative pipeline, that through a combined less invasive Neuro-Visual approach, is able to reconstruct the car driver's physiological status. Specifically, the proposed contribution refers to the sampling and processing of the driver PhotoPlethysmoGraphic (PPG) signal. A parallel enhanced low frame-rate motion magnification algorithm is used to reconstruct such features of the driver's PhotoPlethysmoGraphic (PPG) data when that signal is no longer available from the native embedded sensor platform. A parallel monitoring of the driver's blood pressure levels from the PPG signal as well as the driver's eyes dynamics completes the reconstruction of the driver's physiological status. The proposed pipeline has been tested in one of the major investigated automotive scenarios i.e., the detection and monitoring of pedestrians while driving (pedestrian tracking). The collected performance results confirmed the effectiveness of the proposed approach.

A Robust Document Identification Framework through f-BP Fingerprint.

The identification of printed materials is a critical and challenging issue for security purposes, especially when it comes to documents such as banknotes, tickets, or rare collectable cards: eligible targets for ad hoc forgery. State-of-the-art methods require expensive and specific industrial equipment, while a low-cost, fast, and reliable solution for document identification is increasingly needed in many contexts. This paper presents a method to generate a robust fingerprint, by the extraction of translucent patterns from paper sheets, and exploiting the peculiarities of binary pattern descriptors. A final descriptor is generated by employing a block-based solution followed by principal component analysis (PCA), to reduce the overall data to be processed. To validate the robustness of the proposed method, a novel dataset was created and recognition tests were performed under both ideal and noisy conditions.

Fighting Deepfakes by Detecting GAN DCT Anomalies.

To properly contrast the Deepfake phenomenon the need to design new Deepfake detection algorithms arises; the misuse of this formidable A.I. technology brings serious consequences in the private life of every involved person. State-of-the-art proliferates with solutions using deep neural networks to detect a fake multimedia content but unfortunately these algorithms appear to be neither generalizable nor explainable. However, traces left by Generative Adversarial Network (GAN) engines during the creation of the Deepfakes can be detected by analyzing ad-hoc frequencies. For this reason, in this paper we propose a new pipeline able to detect the so-called GAN Specific Frequencies (GSF) representing a unique fingerprint of the different generative architectures. By employing Discrete Cosine Transform (DCT), anomalous frequencies were detected. The ß statistics inferred by the AC coefficients distribution have been the key to recognize GAN-engine generated data. Robustness tests were also carried out in order to demonstrate the effectiveness of the technique using different attacks on images such as JPEG Compression, mirroring, rotation, scaling, addition of random sized rectangles. Experiments demonstrated that the method is innovative, exceeds the state of the art and also give many insights in terms of explainability.

A Benchmark Evaluation of Adaptive Image Compression for Multi Picture Object Stereoscopic Images.

A stereopair consists of two pictures related to the same subject taken by two different points of view. Since the two images contain a high amount of redundant information, new compression approaches and data formats are continuously proposed, which aim to reduce the space needed to store a stereoscopic image while preserving its quality. A standard for multi-picture image encoding is represented by the MPO format (Multi-Picture Object). The classic stereoscopic image compression approaches compute a disparity map between the two views, which is stored with one of the two views together with a residual image. An alternative approach, named adaptive stereoscopic image compression, encodes just the two views independently with different quality factors. Then, the redundancy between the two views is exploited to enhance the low quality image. In this paper, the problem of stereoscopic image compression is presented, with a focus on the adaptive stereoscopic compression approach, which allows us to obtain a standardized format of the compressed data. The paper presents a benchmark evaluation on large and standardized datasets including 60 stereopairs that differ by resolution and acquisition technique. The method is evaluated by varying the amount of compression, as well as the matching and optimization methods resulting in 16 different settings. The adaptive approach is also compared with other MPO-compliant methods. The paper also presents an Human Visual System (HVS)-based assessment experiment which involved 116 people in order to verify the perceived quality of the decoded images.

Estimation of unreported SARS-CoV-2 cases in Italy using a Susceptible-Exposed-Infectious-Recovered-Dead model.

BACKGROUND: An important epidemiological characteristic that might modulate the pandemic potential of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the proportion of undocumented cases. METHODS: Here, we employed a Susceptible-Exposed-Infectious-Recovered-Dead (SEIRD) model to estimate the proportion of unreported SARS-CoV-2 cases in Italy from the reported number of deaths prior to the adoption of national control measures. RESULTS: We estimated 115 894 infectious individuals (95% confidence interval (CI) = 95 318-140 455) and a total of 144 116 cases (95% CI = 119 030-173 959) on 20 March, 2020. These estimates resulted in 67.3% (95% CI = 60.3%-73.0%) unreported infectious individuals and in 67.4% (95% CI = 60.5%-73.0%) total cases. As such, given the substantial volume of undocumented cases, the case fatality risk would drop from an apparent 8.6% to an estimated 2.6% (95% CI = 2.2%-2.9%). CONCLUSIONS: Our findings partially explain the case fatality risk observed in Italy with a high proportion of unreported SARS-CoV-2 cases. Moreover, we underline that the fraction of undocumented infectious individuals is a critical epidemiological characteristic that needs to be taken into for a better understanding of the SARS-CoV-2 epidemic.

Modeling the Novel Coronavirus (SARS-CoV-2) Outbreak in Sicily, Italy.

Italy was the first country in Europe which imposed control measures of travel restrictions, quarantine and contact precautions to tackle the epidemic spread of the novel coronavirus (SARS-CoV-2) in all its regions. While such efforts are still ongoing, uncertainties regarding SARS-CoV-2 transmissibility and ascertainment of cases make it difficult to evaluate the effectiveness of restrictions. Here, we employed a Susceptible-Exposed-Infectious-Recovered-Dead (SEIRD) model to assess SARS-CoV-2 transmission dynamics, working on the number of reported patients in intensive care unit (ICU) and deaths in Sicily (Italy), from 24 February to 13 April. Overall, we obtained a good fit between estimated and reported data, with a fraction of unreported SARS-CoV-2 cases (18.4%; 95%CI = 0-34.0%) before 10 March lockdown. Interestingly, we estimated that transmission rate in the community was reduced by 32% (95%CI = 23-42%) after the first set of restrictions, and by 80% (95%CI = 70-89%) after those adopted on 23 March. Thus, our estimates delineated the characteristics of SARS-CoV2 epidemic before restrictions taking into account unreported data. Moreover, our findings suggested that transmission rates were reduced after the adoption of control measures. However, we cannot evaluate whether part of this reduction might be attributable to other unmeasured factors, and hence further research and more accurate data are needed to understand the extent to which restrictions contributed to the epidemic control.

Estimation of Unreported Novel Coronavirus (SARS-CoV-2) Infections from Reported Deaths: A Susceptible-Exposed-Infectious-Recovered-Dead Model.

In the midst of the novel coronavirus (SARS-CoV-2) epidemic, examining reported case data could lead to biased speculations and conclusions. Indeed, estimation of unreported infections is crucial for a better understanding of the current emergency in China and in other countries. In this study, we aimed to estimate the unreported number of infections in China prior to the 23 January 2020 restrictions. To do this, we developed a Susceptible-Exposed-Infectious-Recovered-Dead (SEIRD) model that estimated unreported infections from the reported number of deaths. Our approach relied on the fact that observed deaths were less likely to be affected by ascertainment biases than reported infections. Interestingly, we estimated that the basic reproductive number (R0) was 2.43 (95%CI = 2.42-2.44) at the beginning of the epidemic and that 92.9% (95%CI = 92.5%-93.1%) of total cases were not reported. Similarly, the proportion of unreported new infections by day ranged from 52.1% to 100%, with a total of 91.8% (95%CI = 91.6%-92.1%) of infections going unreported. Agreement between our estimates and those from previous studies proves that our approach is reliable for estimating the prevalence and incidence of undocumented SARS-CoV-2 infections. Once it has been tested on Chinese data, our model could be applied to other countries with different surveillance and testing policies.

A Report on Smoking Detection and Quitting Technologies.

Mobile health technologies are being developed for personal lifestyle and medical healthcare support, of which a growing number are designed to assist smokers to quit. The potential impact of these technologies in the fight against smoking addiction and on improving quitting rates must be systematically evaluated. The aim of this report is to identify and appraise the most promising smoking detection and quitting technologies (e.g., smartphone apps, wearable devices) supporting smoking reduction or quitting programs. We searched PubMed and Scopus databases (2008-2019) for studies on mobile health technologies developed to assist smokers to quit using a combination of Medical Subject Headings topics and free text terms. A Google search was also performed to retrieve the most relevant smartphone apps for quitting smoking, considering the average user's rating and the ranking computed by the search engine algorithms. All included studies were evaluated using consolidated criteria for reporting qualitative research, such as applied methodologies and the performed evaluation protocol. Main outcome measures were usability and effectiveness of smoking detection and quitting technologies supporting smoking reduction or quitting programs. Our search identified 32 smoking detection and quitting technologies (12 smoking detection systems and 20 smoking quitting smartphone apps). Most of the existing apps for quitting smoking require the users to register every smoking event. Moreover, only a restricted group of them have been scientifically evaluated. The works supported by documented experimental evaluation show very high detection scores, however the experimental protocols usually lack in variability (e.g., only right-hand patients, not natural sequence of gestures) and have been conducted with limited numbers of patients as well as under constrained settings quite far from real-life use scenarios. Several recent scientific works show very promising results but, at the same time, present obstacles for the application on real-life daily scenarios.