Search Results (10)

The rise of AI-generated synthetic media, or deepfakes, has introduced unprecedented opportunities and challenges across various fields, including entertainment, cybersecurity, and digital communication. Using advanced frameworks such as Generative Adversarial Networks (GANs) and Diffusion Models (DMs), deepfakes are capable of producing highly realistic yet fabricated content, while these advancements enable creative and innovative applications, they also pose severe ethical, social, and security risks due to their potential misuse. The proliferation of deepfakes has triggered phenomena like “Impostor Bias”, a growing skepticism toward the authenticity of multimedia content, further complicating trust in digital interactions. This paper is mainly based on the description of a research project called FF4ALL (FF4ALL-Detection of Deep Fake Media and Life-Long Media Authentication) for the detection and authentication of deepfakes, focusing on areas such as forensic attribution, passive and active authentication, and detection in real-world scenarios. By exploring both the strengths and limitations of current methodologies, we highlight critical research gaps and propose directions for future advancements to ensure media integrity and trustworthiness in an era increasingly dominated by synthetic media. Full article

The glycosylphosphatidylinositol (GPI) is a glycol–lipid that anchors several proteins to the cell surface. The GPI-anchor pathway is crucial for the correct function of proteins involved in cell function, and it is fundamental in early neurogenesis and neural development. The PIG gene family is a group of genes involved in this pathway with six genes identified so far, and defects in these genes are associated with a rare inborn metabolic disorder manifesting with a spectrum of clinical phenotypes in newborns and children. Among them, the PIGO gene encodes for phosphatidylinositol glycan anchor biosynthesis class O protein (PIGO), an enzyme participating in this cascade, and the loss of its function often leads to a severe clinical picture characterized by global developmental delay, seizures, Hirschsprung disease, and other congenital malformations. To date, 19 patients with confirmed PIGO deficiency have been described in the literature with a host of clinical and radiological manifestations. We report a case of a male term newborn with two compound heterozygous variants of the PIGO genes, presenting with encephalopathy, drug-resistant epilepsy, and gastrointestinal abnormalities. Brain MRI first showed diffusion restriction in the ponto-medullary tegmentum, ventral mesencephalon, superior cerebellar peduncles, cerebral peduncles, and globi pallidi. This pattern of lesion distribution has been described as part of the neuroradiological spectrum of PIG genes-related disorders. However, after one month of life, he also showed a previously undescribed MRI pattern characterized by extensive cortical and subcortical involvement of the brain hemispheres. The presence of two different mutations in both the PIGO genes may have been responsible for the particularly severe clinical picture and worse outcome, leading to the death of the newborn in the sixth month of life despite therapeutic attempts. This case expands the neuroradiological spectrum and may bring new insights on glycosylation-related disorders brain manifestations. Full article

Bacterial meningoencephalitis in newborns is a severe and life-threatening pathology, which results from meningeal infection and the subsequent involvement of the brain parenchyma. The severity of the acute onset of symptoms and the risk of neurodevelopmental adverse sequelae in children strongly depend on the timing of the infection, the immunological protection transmitted by the mother to the fetus during pregnancy, and the neonate’s inflammatory and immune system response after birth. Although the incidence of neonatal meningitis and meningoencephalitis and related mortality declined in the past twenty years with the improvement of prenatal care and with the introduction of intrapartum antibiotic prophylaxis against Streptococcus beta Hemolyticus group B (Streptococcus Agalactiae) in the 1990s, bacterial meningitis remains the most common form of cerebrospinal fluid infection in pediatric patients. To date, the rate of unfavorable neurological outcomes is still from 20% to 60%, and the possibility of containing its rate strongly depends on early diagnosis, therapy, and a multidisciplinary approach, which involves neonatologists, neurologists, neuroradiologists, and physiotherapists. Neonatal meningitis remains difficult to diagnose because the responsible bacteria vary with gestational age at birth, age at presentation, and environmental context. The clinical presentation, especially in the newborn, is very ambiguous. From a clinical point of view, the definitive test for diagnosis is lumbar puncture in patients with symptoms suggestive of neurological involvement. Therefore, neuroimaging is key for raising clinical suspicion of meningitis or corroborating the diagnosis based on clinical and laboratory data. Our pictorial review offers a practical approach to neonatal meningoencephalitis by describing the epidemiology, the pathophysiology of bacterial meningoencephalitis, defining the indications and suggesting optimized protocols for neuroimaging techniques, and showing the main neuroimaging findings to reach the diagnosis and offering proper follow-up of bacterial meningitis. Moreover, we tried identifying some peculiar MRI patterns related to some bacteria. Full article

Background: Hypoxic-ischemic encephalopathy (HIE) is a severe pathology, and no unique predictive biomarker has been identified. Our aims are to identify associations of perinatal and outcome parameters with morphological anomalies and ADC values from MRI. The secondary aims are to define a predictive ADC threshold value and detect ADC value fluctuations between MRIs acquired within 7 days (MR0) and at 1 year (MR1) of birth in relation to perinatal and outcome parameters. Methods: Fifty-one term children affected by moderate HIE treated with hypothermia and undergoing MRI0 and MRI1 were recruited. Brain MRIs were evaluated through the van Rooij score, while ADC maps were co-registered on a standardized cerebral surface, on which 29 ROIs were drawn. Statistical analysis was performed in Matlab, with the statistical significance value at 0.05. Results: ADC0 < ADC1 in the left and right thalami, left and right frontal white matter, right visual cortex, and the left dentate nucleus of children showing abnormal perinatal and neurodevelopmental parameters. At ROC analysis, the best prognostic ADC cut-off value was 1.535 mm²/s × 10⁻⁶ (sensitivity 80%, specificity 86%) in the right frontal white matter. ADC1 > ADC0 in the right visual cortex and left dentate nucleus, positively correlated with multiple abnormal perinatal and neurodevelopmental parameters. The van Rooij score was significantly higher in children presenting with sleep disorders. Conclusions: ADC values could be used as prognostic biomarkers to predict children’s neurodevelopmental outcomes. Further studies are needed to address these crucial topics and validate our results. Early and multidisciplinary perinatal evaluation and the subsequent re-assessment of children are pivotal to identify physical and neuropsychological disorders to guarantee early and tailored therapy. Full article

Information regarding the incidence and the prognostic impact of thrombotic events (TE) in non-promyelocytic acute myeloid leukemia (AML) is sparse. Although several risk factors associated with an increased risk of TE development have been recognized, we still lack universally approved guidelines for identification and management of these complications. We retrospectively analyzed 300 consecutive patients with newly diagnosed AML. Reporting the incidence of venous TE (VTE) and arterial TE (ATE) was the primary endpoint. Secondarily, we evaluated baseline patient- and disease-related characteristics with a possible influence of VTE-occurrence probability. Finally, we evaluated the impact of TE on survival. Overall, the VTE incidence was 12.3% and ATE incidence was 2.3%. We identified three independent predictors associated with early-VTE: comorbidities (p = 0.006), platelets count >50 × 10⁹/L (p = 0.006), and a previous history of VTE (p = 0.003). Assigning 1 point to each variable, we observed an overall cumulative incidence of VTE of 18.4% in the high-risk group (≥2 points) versus 6.4% in the low-risk group (0–1 point), log-rank = 0.002. Overall, ATE, but not VTE, was associated with poor prognosis (p < 0.001). In conclusion, TE incidence in AML patients is not negligible. We proposed an early-VTE risk score that could be useful for a proper management of VTE prophylaxis. Full article

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. Full article

Hypofibrinogenemia (HF) in adult acute lymphoblastic leukemia (ALL) of B lineage is uncommon and mostly associated with asparaginase (ASP) delivery. Since we noticed a significant reduction in fibrinogen (FBG) plasma levels even before the first ASP dose, we aim to assess the levels of FBG during induction treatment and explore if the FBG fall correlated with therapies other than asparaginase and/or specific leukemia biological features. We retrospectively analyzed FBG levels in 115 patients with B-ALL. In 74 (64%) out of 115 patients FBG decline occurred during the steroid prephase. In univariate analysis, such a steroid-related HF was significantly associated with BCR-ABL1 rearrangement (p = 0.00158). None of those experiencing HF had significant modifications of liver function tests during induction treatment. Our retrospective study suggests that in B-ALL, steroid therapy can also induce HF and that such an event is preferentially observed in patients carrying BCR-ABL1 rearrangements. The pathogenesis of this phenomenon is still unclear. We attempt to explain it by applying the International Society of Thrombosis and Hemostasis-Disseminated Intravascular Coagulation score (ISTH-DIC score); nonetheless additional studies are needed to clarify further the mechanisms of HF in this subset of patients. Full article

Pneumocystis jirovecii pneumonia (PJP) is an opportunistic infection affecting immunocompromised patients. Patients with acute myeloid leukemia (AML) are not considered at high risk of PJP, thus, prophylaxis is not recommended. Between 2010 and 2020 we retrospectively analyzed 251 AML patients. We performed molecular diagnosis and genotyping of Pneumocystis jirovecii in 67 bronchoalveolar lavage samples. Eleven cases of PJP were diagnosed, with a prevalence of 4.3%. Our study confirms that the most widespread genotype in Europe is genotype 1; in our patients, 70% presented with genotype 1 and 30% the genotype 3. Full article

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. Full article

Background: Non-specific neck pain (NNP) affects 30–50% of the general population, and it often leads to severe disability. Several manual therapy techniques are available to reduce pain and disability and to improve cervical range of motion and functional activities. Muscle Energy Technique (MET) showed more evidence for treating such a disorder. The aim of this current scientific literature analysis was to compare the clinical effects of MET with the other manual or rehabilitative treatments for non-specific acute and chronic neck pain. Methods: The literature search was conducted using the following databases: PubMed, Medline, PEDro, Cochrane Database, and Google Scholar from 2010 to January 2020. Clinical trials about MET were included. The quality of the trials was assessed according to the PEDro scale. Results: Twenty-one papers according to inclusion and exclusion criteria were selected: 15 studies about non-specific acute neck pain and 6 studies about non-specific chronic neck pain. Conclusions: This analysis suggests that the MET approach has a good clinical effect on reducing neck pain in patients with acute neck pain and improves cervical range of motion in patients with chronic neck pain, and is better if combined with a traditional rehabilitative approach. This review’s findings should be considered with caution for physiotherapy practice because of the studies’ methodologic limitations. On the basis of the current available and limited evidence, clinicians could combine MET with traditional physiotherapy and other manual techniques when treating people with non-specific neck pain. Full article