Search

In the field of veterinary medicine, the detection of parasite eggs in the fecal samples of livestock animals represents one of the most challenging tasks, since their spread and diffusion may lead to severe clinical disease. Nowadays, the scanning procedure is typically performed by physicians with professional microscopes and requires a significant amount of time, domain knowledge, and resources. The Kubic FLOTAC Microscope (KFM) is a compact, low-cost, portable digital microscope that can autonomously analyze fecal specimens for parasites and hosts in both field and laboratory settings. It has been shown to acquire images that are comparable to those obtained with traditional optical microscopes, and it can complete the scanning and imaging process in just a few minutes, freeing up the operator's time for other tasks. To promote research in this area, the first AI-KFM challenge was organized, which focused on the detection of gastrointestinal nematodes (GINs) in cattle using RGB images. The challenge aimed to provide a standardized experimental protocol with a large number of samples collected in a well-known environment and a set of scores for the approaches submitted by the competitors. This paper describes the process of generating and structuring the challenge dataset and the approaches submitted by the competitors, as well as the lessons learned throughout this journey.

Abstract The widespread use of fingerprint authentication systems (FASs) in consumer electronics opens for the development of advanced presentation attacks, that is, procedures designed to bypass a FAS using a forged fingerprint. As a consequence, FAS are often equipped with a fingerprint presentation attack detection (FPAD) module, to recognise live fingerprints from fake replicas. In this work, a novel FPAD approach based on Convolutional Neural Networks (CNNs) and on an ad hoc adversarial data augmentation strategy designed to iteratively increase the considered detector robustness is proposed. In particular, the concept of adversarial fingerprint, that is, fake fingerprints disguised by using ad hoc fingerprint adversarial perturbation algorithms was leveraged to help the detector focus only on salient portions of the fingerprints. The procedure can be adapted to different CNNs, adversarial fingerprint algorithms and fingerprint scanners, making the proposed approach versatile and easily customisable todifferent working scenarios. To test the effectiveness of the proposed approach, the authors took part in the LivDet 2021 competition, an international challenge gathering experts to compete on fingerprint liveness detection under different scanners and fake replica generation approach, achieving first place out of 23 participants in the ‘Liveness Detection in Action track’.

Biomass is a crucial indicator of the carbon sequestration capacity of a vegetation ecosystem. Its dynamic is of interest because it impacts on the carbon cycle, which plays an important role in the global climate and its changes. This work presents a novel technique, able to transfer a calibrated regression model between different areas by exploiting an active learning methodology and using Shannon’s entropy as a discriminator for sample selection. Model calibration is performed based on a reference area for which an extended ground truth is available and implemented via regression bootstrap. Then, re-calibration samples for model transfer are selected through active learning, allowing for choosing a limited number of points to be investigated for training data collection. Different sampling strategies and regression techniques have been tested to demonstrate that a significant reduction in the number of calibration samples does not affect the estimation performance. The proposed workflow has been tested on a dataset concerning Finnish forests. Experimental results show that the joint exploitation of regression ensembles and active learning dramatically reduces the amount of field sampling, providing aboveground biomass estimates comparable to those obtained using literature techniques, which need extended training sets to build reliable predictions.

Within Artificial Intelligence, Deep Learning (DL) represents a paradigm that has been showing unprecedented performance in image and audio processing by supporting or even replacing humans in defect and anomaly detection. The railway sector is expected to benefit from DL applications, especially in predictive maintenance applications, where smart audio and video sensors can be leveraged yet kept distinct from safety-critical functions. Such separation is crucial, as it allows for improving system dependability with no impact on its safety certification. This is further supported by the development of DL in other transportation domains, such as automotive and avionics, opening for knowledge transfer opportunities and highlighting the potential of such a paradigm in railways. In order to summarize the recent state-of-the-art while inquiring about future opportunities, this paper reviews DL approaches for the analysis of data generated by acoustic and visual sensors in railway maintenance applications that have been published until August 31st, 2021. In this paper, the current state of the research is investigated and evaluated using a structured and systematic method, in order to highlight promising approaches and successful applications, as well as to identify available datasets, current limitations, open issues, challenges, and recommendations about future research directions.

Large amounts of interaction data are collected by messaging apps, mobile phone carriers, and social media. Creţu et al. propose a behavioral profiling attack model and show that the stability of people’s interaction networks over time can allow individuals to be re-identified in interaction datasets.

Bullying and cyberbullying are harmful social phenomena that involve the intentional, repeated use of power to intimidate or harm others. The ramifications of these actions are felt not just at the individual level but also pervasively throughout society, necessitating immediate attention and practical solutions. The BullyBuster project pioneers a multi-disciplinary approach, integrating artificial intelligence (AI) techniques with psychological models to comprehensively understand and combat these issues. In particular, employing AI in the project allows the automatic identification of potentially harmful content by analyzing linguistic patterns and behaviors in various data sources, including photos and videos. This timely detection enables alerts to relevant authorities or moderators, allowing for rapid interventions and potential harm mitigation. This paper, a culmination of previous research and advancements, details the potential for significantly enhancing cyberbullying detection and prevention by focusing on the system’s design and the novel application of AI classifiers within an integrated framework. Our primary aim is to evaluate the feasibility and applicability of such a framework in a real-world application context. The proposed approach is shown to tackle the pervasive issue of cyberbullying effectively.

Raster logs are scanned representations of the analog data recorded in subsurface drilling. Geologists rely on these images to interpret well-log curves and deduce the physical properties of geological formations. Scanned images contain various artifacts, including hand-written texts, brightness variability, scan defects, etc. The manual effort involved in reading the data is substantial. To mitigate this, unsupervised computer vision techniques are employed to extract and interpret the curves digitally. Existing algorithms predominantly require manual intervention, resulting in slow processing times, and are erroneous. This research aims to address these challenges by proposing VeerNet, a deep neural network architecture designed to semantically segment the raster images from the background grid to classify and digitize (i.e., extracting the analytic formulation of the written curve) the well-log data. The proposed approach is based on a modified UNet-inspired architecture leveraging an attention-augmented read–process–write strategy to balance retaining key signals while dealing with the different input–output sizes. The reported results show that the proposed architecture efficiently classifies and digitizes the curves with an overall F1 score of 35% and Intersection over Union of 30%, achieving 97% recall and 0.11 Mean Absolute Error when compared with real data on binary segmentation of multiple curves. Finally, we analyzed VeerNet’s ability in predicting Gamma-ray values, achieving a Pearson coefficient score of 0.62 when compared to measured data.

The field of Natural Language Processing (NLP) has undergone a significant transformation with the introduction of Transformers. From the first introduction of this technology in 2017, the use of transformers has become widespread and has had a profound impact on the field of NLP. In this survey, we review the open-access and real-world applications of transformers in NLP, specifically focusing on those where text is the primary modality. Our goal is to provide a comprehensive overview of the current state-of-the-art in the use of transformers in NLP, highlight their strengths and limitations, and identify future directions for research. In this way, we aim to provide valuable insights for both researchers and practitioners in the field of NLP. In addition, we provide a detailed analysis of the various challenges faced in the implementation of transformers in real-world applications, including computational efficiency, interpretability, and ethical considerations. Moreover, we highlight the impact of transformers on the NLP community, including their influence on research and the development of new NLP models.

The United Nations Framework Convention on Climate Change (UNFCCC) has recently established the Reducing Emissions from Deforestation and forest Degradation (REDD+) program, which requires countries to report their carbon emissions and sink estimates through national greenhouse gas inventories (NGHGI). Thus, developing automatic systems capable of estimating the carbon absorbed by forests without in situ observation becomes essential. To support this critical need, in this work, we introduce ReUse, a simple but effective deep learning approach to estimate the carbon absorbed by forest areas based on remote sensing. The proposed method’s novelty is in using the public above-ground biomass (AGB) data from the European Space Agency’s Climate Change Initiative Biomass project as ground truth to estimate the carbon sequestration capacity of any portion of land on Earth using Sentinel-2 images and a pixel-wise regressive UNet. The approach has been compared with two literature proposals using a private dataset and human-engineered features. The results show a more remarkable generalization ability of the proposed approach, with a decrease in Mean Absolute Error and Root Mean Square Error over the runner-up of 16.9 and 14.3 in the area of Vietnam, 4.7 and 5.1 in the area of Myanmar, 8.0 and 1.4 in the area of Central Europe, respectively. As a case study, we also report an analysis made for the Astroni area, a World Wildlife Fund (WWF) natural reserve struck by a large fire, producing predictions consistent with values found by experts in the field after in situ investigations. These results further support the use of such an approach for the early detection of AGB variations in urban and rural areas.

Glioblastoma Multiforme (GBM) is considered one of the most aggressive malignant tumors, characterized by a tremendously low survival rate. Despite alkylating chemotherapy being typically adopted to fight this tumor, it is known that O(6)-methylguanine-DNA methyltransferase (MGMT) enzyme repair abilities can antagonize the cytotoxic effects of alkylating agents, strongly limiting tumor cell destruction. However, it has been observed that MGMT promoter regions may be subject to methylation, a biological process preventing MGMT enzymes from removing the alkyl agents. As a consequence, the presence of the methylation process in GBM patients can be considered a predictive biomarker of response to therapy and a prognosis factor. Unfortunately, identifying signs of methylation is a non-trivial matter, often requiring expensive, time-consuming, and invasive procedures. In this work, we propose to face MGMT promoter methylation identification analyzing Magnetic Resonance Imaging (MRI) data using a Deep Learning (DL) based approach. In particular, we propose a Convolutional Neural Network (CNN) operating on suspicious regions on the FLAIR series, pre-selected through an unsupervised Knowledge-Based filter leveraging both FLAIR and T1-weighted series. The experiments, run on two different publicly available datasets, show that the proposed approach can obtain results comparable to (and in some cases better than) the considered competitor approach while consisting of less than 0.29% of its parameters. Finally, we perform an eXplainable AI (XAI) analysis to take a little step further toward the clinical usability of a DL-based approach for MGMT promoter detection in brain MRI.

As explainability seems to be the driver for a wiser adoption of Artificial Intelligence in healthcare and in critical applications, in general, a comprehensive study of this field is far from being completed. On one hand, a final definition and theoretical measurements of explainability have not been assessed, yet, on the other hand, some tools and frameworks for the practical evaluation of this feature are now present. This paper aims to present a concrete experience in using some of these explainability-related techniques in the problem of predicting the size of amino acids in real-world protein structures. In particular, the feature importance calculation embedded in Random Forest (RF) training is compared with the results of the Eli-5 tool applied to the Neural Network (NN) model. Both the predictors are trained on the same dataset, which is extracted from Protein Data Bank (PDB), considering 446 myoglobins structures and process it with several tools to implement a geometrical model and perform analyses on it. The comparison between the two models draws different conclusions about the residues’ geometry and their biological properties.

Continual mapping and monitoring of impervious surfaces are crucial activities to support sustainable urban management strategies and to plan effective actions for environmental changes. In this context, impervious surface coverage is increasingly becoming an essential indicator for assessing urbanization and environmental quality, with several works relying on satellite imagery to determine it. However, although satellite imagery is typically available with a frequency of 3–10 days worldwide, imperviousness maps are released at most annually as they require a huge human effort to be produced and validated. Attempts have been made to extract imperviousness maps from satellite images using machine learning, but (i) the scarcity of reliable and detailed ground truth (ii) together with the need to manage different spectral bands (iii) while making the resulting system easily accessible to the end users is limiting their diffusion. To tackle these problems, in this work we introduce a deep-learning-based approach to extract imperviousness maps from multi-spectral Sentinel-2 images leveraging a very detailed imperviousness map realised by the Italian department for environment protection as ground truth. We also propose a scalable and portable inference pipeline designed to easily scale the approach, integrating it into a web-based Geographic Information System (GIS) application. As a result, even non-expert GIS users can quickly and easily calculate impervious surfaces for any place on Earth (accuracy >95%), with a frequency limited only by the availability of new satellite images.

Machine Learning models are susceptible to attacks, such as noise, privacy invasion, replay, false data injection, and evasion attacks, which affect their reliability and trustworthiness. Evasion attacks, performed to probe and identify potential ML-trained models’ vulnerabilities, and poisoning attacks, performed to obtain skewed models whose behavior could be driven when specific inputs are submitted, represent a severe and open issue to face in order to assure security and reliability to critical domains and systems that rely on ML-based or other AI solutions, such as healthcare and justice, for example. In this study, we aimed to perform a comprehensive analysis of the sensitivity of Artificial Intelligence approaches to corrupted data in order to evaluate their reliability and resilience. These systems need to be able to understand what is wrong, figure out how to overcome the resulting problems, and then leverage what they have learned to overcome those challenges and improve their robustness. The main research goal pursued was the evaluation of the sensitivity and responsiveness of Artificial Intelligence algorithms to poisoned signals by comparing several models solicited with both trusted and corrupted data. A case study from the healthcare domain was provided to support the pursued analyses. The results achieved with the experimental campaign were evaluated in terms of accuracy, specificity, sensitivity, F1-score, and ROC area.

Dynamic contrast enhanced‐magnetic resonance imaging (DCE‐MRI) is a valid complementary diagnostic method for early detection and diagnosis of breast cancer. However, due to the amount of data, the examination is difficult without the support of a computer‐aided detection and diagnosis (CAD) system. Since magnetic resonance imaging data includes different tissues and patient movements (i.e. breathing) may introduce artefacts during acquisition, CADs need some stages aimed to identify breast parenchyma and to reduce motion artefacts. Among the major issues in developing a fully automated CAD, there are the accurate segmentation of lesions in regions of interest and their consequent staging (classification). This work introduces breast lesion automatic detection and diagnosis system (BLADeS), a comprehensive fully automated breast CAD aimed to support the radiologist during the patient diagnosis. The authors propose a hierarchical architecture that implements modules for breast segmentation, attenuation of motion artefacts, localisation of lesions and, finally, classification according to their malignancy. Performance was evaluated on 42 patients with histopathologically proven lesions, performing cross‐validation to ensure a fair comparison. Results show that BLADeS can be successfully used to perform a fully automated breast lesion diagnosis starting from T1‐weighted DCE‐MRI, without requiring any operator interaction in any of the processing stages.

The recent spread of Deep Learning (DL) in medical imaging is pushing researchers to explore its suitability for lesion segmentation in Dynamic Contrast-Enhanced Magnetic-Resonance Imaging (DCE-MRI), a complementary imaging procedure increasingly used in breast-cancer analysis. Despite some promising proposed solutions, we argue that a “naive” use of DL may have limited effectiveness as the presence of a contrast agent results in the acquisition of multimodal 4D images requiring thorough processing before training a DL model. We thus propose a pipelined approach where each stage is intended to deal with or to leverage a peculiar characteristic of breast DCE-MRI data: the use of a breast-masking pre-processing to remove non-breast tissues; the use of Three-Time-Points (3TP) slices to effectively highlight contrast agent time course; the application of a motion-correction technique to deal with patient involuntary movements; the leverage of a modified U-Net architecture tailored on the problem; and the introduction of a new “Eras/Epochs” training strategy to handle the unbalanced dataset while performing a strong data augmentation. We compared our pipelined solution against some literature works. The results show that our approach outperforms the competitors by a large margin (+9.13% over our previous solution) while also showing a higher generalization ability.

Radiomics leverages existing image datasets to provide non-visible data extraction via image post-processing, with the aim of identifying prognostic, and predictive imaging features at a sub-region of interest level. However, the application of radiomics is hampered by several challenges such as lack of image acquisition/analysis method standardization, impeding generalizability. As of yet, radiomics remains intriguing, but not clinically validated. We aimed to test the feasibility of a non-custom-constructed platform for disseminating existing large, standardized databases across institutions for promoting radiomics studies. Hence, University of Texas MD Anderson Cancer Center organized two public radiomics challenges in head and neck radiation oncology domain. This was done in conjunction with MICCAI 2016 satellite symposium using Kaggle-in-Class, a machine-learning and predictive analytics platform. We drew on clinical data matched to radiomics data derived from diagnostic contrast-enhanced computed tomography (CECT) images in a dataset of 315 patients with oropharyngeal cancer. Contestants were tasked to develop models for (i) classifying patients according to their human papillomavirus status, or (ii) predicting local tumor recurrence, following radiotherapy. Data were split into training, and test sets. Seventeen teams from various professional domains participated in one or both of the challenges. This review paper was based on the contestants' feedback; provided by 8 contestants only (47%). Six contestants (75%) incorporated extracted radiomics features into their predictive model building, either alone (n = 5; 62.5%), as was the case with the winner of the “HPV” challenge, or in conjunction with matched clinical attributes (n = 2; 25%). Only 23% of contestants, notably, including the winner of the “local recurrence” challenge, built their model relying solely on clinical data. In addition to the value of the integration of machine learning into clinical decision-making, our experience sheds light on challenges in sharing and directing existing datasets toward clinical applications of radiomics, including hyper-dimensionality of the clinical/imaging data attributes. Our experience may help guide researchers to create a framework for sharing and reuse of already published data that we believe will ultimately accelerate the pace of clinical applications of radiomics; both in challenge or clinical settings.

Now, data collection and analysis are becoming more and more important in a variety of application domains, as long as novel technologies advance. At the same time, we are experiencing a growing need for human⁻machine interaction with expert systems, pushing research toward new knowledge representation models and interaction paradigms. In particular, in the last few years, eHealth—which usually indicates all the healthcare practices supported by electronic elaboration and remote communications—calls for the availability of a smart environment and big computational resources able to offer more and more advanced analytics and new human⁻computer interaction paradigms. The aim of this paper is to introduce the HOLMeS (health online medical suggestions) system: A particular big data platform aiming at supporting several eHealth applications. As its main novelty/functionality, HOLMeS exploits a machine learning algorithm, deployed on a cluster-computing environment, in order to provide medical suggestions via both chat-bot and web-app modules, especially for prevention aims. The chat-bot, opportunely trained by leveraging a deep learning approach, helps to overcome the limitations of a cold interaction between users and software, exhibiting a more human-like behavior. The obtained results demonstrate the effectiveness of the machine learning algorithms, showing an area under ROC (receiver operating characteristic) curve (AUC) of 74.65% when some first-level features are used to assess the occurrence of different chronic diseases within specific prevention pathways. When disease-specific features are added, HOLMeS shows an AUC of 86.78%, achieving a greater effectiveness in supporting clinical decisions.

Web services composition is an emerging software development paradigm for the implementation of distributed computing systems, the impact of which is very relevant both in research and industry. When a complex functionality has to be delivered on the Internet, a service integrator can produce added value by delivering more abstract and complex services obtained by composition of existing ones. But while isolated services availability can be improved by tuning and reconfiguring their hosting servers, with Composed Web Services (CWS) basic services must be taken as they are. In this case, it is necessary to evaluate the composition effects. The authors propose a high-level analysis methodology, supported by a tool, based on the transformation of BPEL descriptions of CWS into models based on the fault tree availability evaluation formalism that enables a modeler, unfamiliar with the underlying combinatorial probabilistic mathematics, to evaluate the availability of CWS, given components availability and expected execution behavior.