Modern Fingerprint Presentation Attack Detection (FPAD) modules have been particularly successful in avoiding attacks exploiting artificial fingerprint replicas against Automated Fingerprint Identification Systems (AFISs). As for several other domains, Machine and Deep Learning strongly contributed to this success, with all recent state-of-the-art detectors leveraging learning-based approaches. An insidious flip side is represented by adversarial attacks, namely, procedures intended to mislead a target detector. Indeed, despite this type of attack has been considered unrealistic, as it presupposes access to the communication channel between the sensor and the detector, in a recent work, we have highlighted the possibility of transferring a fingerprint adversarial attack from the digital domain to the physical one. In this work, we take a step further by introducing a new procedure designed to make the physical adversarial presentation attack i) more robust to the physical crafting of the PAI by exploiting explainability techniques, ii) easier to adapt to different fingerprint scanners and adversarial algorithms, and iii) usable in a black-box scenario. To quantify the impact of these novel adversarial presentation attacks family, designed to be robust to the physical crafting process, we assess the performance of both state-of-the-art PAD modules alone and integrated AFISs. Results highlight the approach’s feasibility, opening a new series of threats in the context of fingerprint PAD.

In biomedical image processing, Deep Learning (DL) is increasingly exploited in various forms and for diverse purposes. Despite unprecedented results, the huge number of parameters to learn, which necessitates a substantial number of annotated samples, remains a significant challenge. In medical domains, obtaining high-quality labelled datasets is still a challenging task. In recent years, several works have leveraged data augmentation to face this issue, mostly thanks to the introduction of generative models able to produce artificial samples having the same characteristics as the acquired ones. However, we claim that biological principles must be considered in this process, as all medical imaging techniques exploit one or more physical laws or properties directly associated with the physiological characteristics of the tissues under analysis. A notable example is the Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI), in which the kinetic of the contrast agent (CA) highlights both morphological and physiological aspects. In this paper, we introduce a novel generative approach explicitly relying on Physiologically Based Pharmacokinetic (PBPK) modelling and on an Intrinsic Deforming Autoencoder (DAE) to implement a physiologically-aware data augmentation strategy. As a case of study, we consider breast DCE-MRI. In particular, we tested our proposal on two private and one public datasets with different acquisition protocols, demonstrating that the proposed method significantly improves the performance of several DL-based lesion classifiers.

Level Crossings are among the most critical railway assets, concerning both the risk of accidents and their maintainability, due to intersections with promiscuous traffic and difficulties in remotely monitoring their health status. Failures can be originated from several factors, including malfunctions in the bar mechanisms and warning devices, such as light signals and bells. This paper focuses on the intelligent detection of anomalies in warning bells through non-intrusive acoustic monitoring by: (1) introducing a new concept for autonomous monitoring of level crossings; (2) generating and sharing a specific dataset collecting relevant audio signals from publicly available audio recordings; (3) implementing and evaluating a solution combining deep learning and transfer learning for warning bell detection. The results show a high accuracy in detecting anomalies and suggest viability of the approach in real-world applications, especially where network cameras with on-board microphones are installed for multi-purpose level crossing surveillance.

The increasing use of AI in industry and society not only expects but demands that we build human-centred competencies into our AI education programmes. The computing education community needs to adapt, and while the adoption of standalone ethics modules into AI programmes or the inclusion of ethical content into traditional applied AI modules is progressing, it is not enough. To foster student competencies to create AI innovations that respect and support the protection of individual rights and society, a novel ground-up approach is needed. This panel presents on one such approach, the development of a Human-Centred AI Masters (HCAIM) as well as the insights and lessons learned from the process. In particular, we discuss the design decisions that have led to the multi-institutional master's programme. Moreover, this panel allows for discussion on pedagogical and methodological approaches, content knowledge areas and the delivery of such a novel programme, along with challenges faced, to inform and learn from other educators that are considering developing such programmes.

Artificial Intelligence (AI) is becoming pervasive in most engineering domains, and railway transport is no exception. However, due to the plethora of different new terms and meanings associated with them, there is a risk that railway practitioners, as several other categories, will get lost in those ambiguities and fuzzy boundaries, and hence fail to catch the real opportunities and potential of machine learning, artificial vision, and big data analytics, just to name a few of the most promising approaches connected to AI. The scope of this paper is to introduce the basic concepts and possible applications of AI to railway academics and practitioners. To that aim, this paper presents a structured taxonomy to guide researchers and practitioners to understand AI techniques, research fields, disciplines, and applications, both in general terms and in close connection with railway applications such as autonomous driving, maintenance, and traffic management. The important aspects of ethics and explainability of AI in railways are also introduced. The connection between AI concepts and railway subdomains has been supported by relevant research addressing existing and planned applications in order to provide some pointers to promising directions.

Cancer is one of the leading causes of death in the western world, with medical imaging playing a key role for early diagnosis. Focusing on breast cancer, one of the emerging imaging methodologies is Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI). The flip side of using DCE-MRI is in its long acquisition times that often causes the patient to move. This results in motion artefacts, namely distortions in the acquired image that can affect DCE-MRI analysis. A possible solution consists in the use of Motion Correction Techniques (MCTs), i.e. procedures intended to re-align the post-contrast image to the corresponding pre-contrast (reference) one. This task is particularly critic in DCE-MRI, due to brightness variations introduced in post-contrast images by the contrast-agent flowing. To face this problem, in this work we introduce a new MCT for breast DCE-MRI leveraging Physiologically Based PharmacoKinetic (PBPK) modelling and Artificial Neural Networks (ANN) to determine the most suitable physiologically-compliant transformation. To this aim, we propose a Neural Registration Network relying on a very task-specific loss function explicitly designed to take into account the contrast agent flowing while enforcing a correct re-alignment. We compared the obtained results against some conventional motion correction techniques, evaluating the performance on a patient-by-patient basis. Results show that the proposed approach results to be the best performing even when compared against other techniques designed to take into account for brightness variations.

Nowadays, Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is increasingly succeeding as a complementary methodology for breast cancer, with Computer Aided Detection/Diagnosis (CAD) systems becoming essential technological tools to provide early detection and diagnosis of tumours. Several CADs make use of machine learning, resulting in a constant design of hand-crafted features aimed at better assisting the physician. In recent years, Deep learning (DL) approaches raised in popularity in many pattern recognition tasks thanks to their ability to learn compact hierarchical features that well fit the specific task to solve. If, on one and, this characteristic suggests to explore DL suitability for biomedical image processing, on the other, it is important to take into account the physiological inheritance of the images under analysis. With this goal in mind, in this work we propose "3TP U-Net", an U-Shaped Deep Convolutional Neural Network that exploits the well-known Three Time Points approach for the lesion segmentation task. Results show that our proposal is able to outperform not only the classical (non-deep) approaches but also some very recent deep proposal, achieving a median Dice Similarity Coefficient of 61.24%.

The use of biometric-based authentication systems spread over daily life consumer electronics. Over the years, researchers' interest shifted from hard (such as fingerprints, voice and keystroke dynamics) to soft biometrics (such as age, ethnicity and gender), mainly by using the latter to improve the authentication systems effectiveness. While newer approaches are constantly being proposed by domain experts, in the last years Deep Learning has raised in many computer vision tasks, also becoming the current state-of-art for several biometric approaches. However, since the automatic processing of data rich in sensitive information could expose users to privacy threats associated to their unfair use (i.e. gender or ethnicity), in the last years researchers started to focus on the development of defensive strategies in the view of a more secure and private AI. The aim of this work is to exploit Adversarial Perturbation, namely approaches able to mislead state-of-the-art CNNs by injecting a suitable small perturbation over the input image, to protect subjects against unwanted soft biometrics-based identification by automatic means. In particular, since ethnicity is one of the most critical soft biometrics, as a case of study we will focus on the generation of adversarial stickers that, once printed, can hide subjects ethnicity in a real-world scenario.

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.

Dynamic Contrast Enhanced - Magnetic Resonance Imaging (DCE-MRI) is gaining popularity as complementary diagnostic tool for breast cancer. In a typical Computer Aided Detection (CAD) processing, the identification and segmentation of the breast parenchyma is a crucial stage aimed to reduce computational effort and increase reliability, by reducing the number of voxels to analyse and removing foreign tissues and air. The aim of this work is to propose a fully-automated geometrical-based breast-mask extraction method in DCE-MRI, that combines three 2D Fuzzy C-Means clustering and geometrical breast anatomy characterization. In particular, seven well defined key-points have been considered in order to accurately segment breast parenchyma from air and chest-wall. The proposed approach has been validated on 30 DCE-MRI studies. The median segmentation accuracy and Dice similarity index were 97.86 (±0.49) and 92.66 (±1.48) respectively with p <; 0.05, and 100% of neoplastic lesion coverage.

Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated in the last decades a great potential in screening of high-risk women for breast cancer, in staging newly diagnosed patients and in assessing therapy effects. The aim of this work is to propose a novel model-based measure for quality evaluation of image registration techniques in DCE-MRI. The proposed measure is based on a compartmental model of blood plasma and of the extra vascular extra cellular space (EES) for tumour tissue. Its suitability for evaluating image registration techniques has been indirectly verified by considering the results obtained, after each image registration technique, by a CAD segmentation system, developed in our previous work. In particular, it has been shown that the ranking obtained by means of the proposed quality assessment measure is in agreement with the ranking of the CAD segmentation systems, proving that our measure can correctly evaluate image registration techniques in the DCE-MRI context.