Search

Image forgery detection is important for sensitive domains such as courts of law. The main challenge is to develop a robust model that is sensitive to tampering traces. Existing techniques perform well on a limited dataset but do not generalize well across the datasets. Moreover, these techniques cannot reliably detect tampering that distorts the texture pattern of the image. The noise patterns remain consistent throughout a digital image if its contents are not altered. Based on this hypothesis, a robust descriptor FFT-DRLBP (Fast Fourier Transformation - Discriminative Robust Local Binary Patterns) is introduced, which first estimates noise patterns using FFT and encodes the discrepancies in noise patterns using DRLBP. Features extracted are passed to Support Vector Machine (SVM) for deciding whether the image is authentic or tampered. Intensive experiments are performed on benchmark datasets to validate the performance of the method. It achieved an accuracy of 99.21% on the combination of two challenging datasets. The comparison shows that it outperforms state-of-the-art methods and is vigorous to image forgery attacks even in the presence of various post-processing operations. The performance of the method is also validated using cross-dataset experiments, which ensures its robustness and generalization.

Now-a-days, videos can be easily recorded and forged with user-friendly editing tools. These videos can be shared on social networks to make false propaganda. During the process of spatial forgery, the texture and micro-patterns of the frames become inconsistent, which can be observed in the difference of two consecutive frames. Based on this observation, a method has been proposed for detection of forged video segments and localization of forged frames. Employing the Chrominance value of Consecutive frame Difference (CCD) and Discriminative Robust Local Binary Pattern (DRLBP), a new descriptor is introduced to model the inconsistency embedded in the frames due to forgery. Support Vector Machine (SVM) is used to detect whether the pair of consecutive frames is forged. If at least one pair of consecutive frames is detected as forged, the video segment is predicted as forged and the forged frames are localized. Intensive experiments are performed to validate the performance of the method on a combined dataset of videos, which were tampered by copy-move and splicing methods. The detection accuracy on large dataset is 96.68 percent and video accuracy is 98.32 percent. The comparison shows that it outperforms the state-of-the-art methods, even through cross dataset validation.

Angela Bonaccorso,1,2,* Alessandro Ortis,3,* Teresa Musumeci,1,2 Claudia Carbone,1,2 Mazhar Hussain,3 Valentina Di Salvatore,1 Sebastiano Battiato,3 Francesco Pappalardo,1,2 Rosario Pignatello1,2 1Department of Drug and Health Sciences, University of Catania, Catania, Italy; 2NANOMED–Research Centre for Nanomedicine and Pharmaceutical Nanotechnology, University of Catania, Catania, 95125, Italy; 3Department of Mathematics and Computer Science, University of Catania, Catania, Italy*These authors contributed equally to this workCorrespondence: Teresa Musumeci, Email teresa.musumeci@unict.itBackground: 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.Keywords: nanomedicine, intranasal administration, pharmacokinetic, DTE, DTP, machine learning

Ultrasound imaging is frequently employed to aid with fetal development. It benefits from being real-time, inexpensive, non-intrusive, and simple. Artificial intelligence is becoming increasingly significant in medical imaging and can assist in resolving many problems related to the classification of fetal organs. Processing fetal ultrasound (US) images increasingly uses deep learning (DL) techniques. This paper aims to assess the development of existing DL classification systems for use in a real maternal-fetal healthcare setting. This experimental process has employed two publicly available datasets, such as FPSU23 Dataset and Fetal Imaging. Two novel deep learning architectures have been designed in the proposed architecture based on 3-residual and 4-residual blocks with different convolutional filter sizes. The hyperparameters of the proposed architectures were initialized through Bayesian Optimization. Following the training process, deep features were extracted from the average pooling layers of both models. In a subsequent step, the features from both models were optimized using an improved version of the Generalized Normal Distribution Optimizer (GNDO). Finally, neural networks are used to classify the fused optimized features of both models, which were first combined using a new fusion technique. The best classification scores, 98.5 and 88.6% accuracy, were obtained after multiple steps of analysis. Additionally, a comparison with existing state-of-the-art methods revealed a notable improvement in the suggested architecture’s accuracy.

In this study, copper was removed from an aqueous solution through electromembrane extraction (EME), a new approach that utilises a two-chamber electrochemical cell. It consists of two electrodes (stainless steel cathode and graphite anode) and a solid liquid membrane (SLM). SLM is composed of supporting polypropylene membrane impregnated with1-octanol as an organic solvent and bis(2-ethylhexyl) phosphate (DEHP) as a carrier. The effects of process parameters such as applied voltage, pH and copper concentration on the removal of copper were investigated. Response surface methodology (RSM) was applied to optimise these parameters and their interactions. Results indicated that pH has the major effect on the removal of copper, followed by applied voltage. The squared interaction term in the RSM model has the highest contribution (70.5%), followed by the linear term, thereby confirming the significant interaction among the variables. The optimum conditions include an applied voltage of 60V, pH of 5.18 and initial copper concentration of 5 ppm, which yield to a removal efficiency of 80% after 6 hours of operation. The findings demonstrate the use of electromembrane extraction as an efficient method for the removal of heavy metals and provide valuable insights for future application to other environmental and water treatment processes.

Abstract Background Despite the efficacy and safety of DIGIFab, it is relatively expensive and has limited availability. In addition, alternative interventions, such as therapeutic plasma exchange, may need to be considered in massive digoxin overdoses. Although few case reports describe its efficacy. Case presentation We report a case of a 17-year-old white male patient brought by family members to our emergency department in Riyadh, Saudi Arabia. After intentionally ingesting 48 mg of digoxin tablets to commit suicide, the patient’s initial digoxin serum level was 8.04 ng/mL. The patient was resuscitated in the emergency department. After admission to the intensive care unit, the patient underwent therapeutic plasma exchange, because of insufficient DIGIFab doses. Afterward, the serum digoxin levels drastically decreased, and his symptoms reverted. The patient was successfully managed and discharged 7 days after admission. Conclusion Despite insufficient evidence and a limited number of case reports describing the use of extracorporeal treatment in digoxin overdose, we noted the significant impact of therapeutic plasma exchange on our patient. However, therapeutic plasma exchange’s use in routine treatment requires stronger evidence to confirm its benefits.

Risk analysis is an important technique to estimate impacts on the environment for adopting effective measures to avoid risks. This field study was conducted to investigate the risk of brick kiln (BK) smoke on the shoots of Acacia arabica. Different phenotypic parameters including morphology and growth of shoots and epidermal imprints of the leaves were studied in the vicinity of a brick kiln situated 500 meters away from Lahore-Raiwind Road, Lahore, Pakistan. Results show that smoke exposure has posed differential effects on shoots i.e. some shoots of same tree remained normal, others died and still others were badly affected by the smoke. Moreover, the number of leaves and fresh weight in the smoke affected shoots significantly reduced as compared with normal ones. The study of the epidermal imprints of the leaves of these normal and smoke effected shoots revealed that the mean values of the stomatal size of both adaxial and abaxial surfaces of the normal and smoke effected leaves were not statistically significant. However, the number of stomata on both epidermal layers of smoke effected leaves was significantly reduced as compared with normal ones. This study showed that due to the exposure to BK smoke, the growth of Acacia arabica trees in the field was significantly suppressed.

Background Computed tomography perfusion (CTP) predictions of infarct core play an important role in the determination of treatment eligibility in large‐vessel occlusion acute ischemic stroke. Prior studies have demonstrated that blood glucose can affect cerebral blood flow. Here, we examine the influence of acute and chronic hyperglycemia on CTP estimations of infarct core. Methods From our prospectively collected multicenter observational cohort, we identified patients with large‐vessel occlusion acute ischemic stroke who underwent CTP with RAPID (IschemaView, Stanford, CA) postprocessing, followed by endovascular therapy with substantial reperfusion (Thrombolysis in Cerebral Infarction 2b–3) within 90 minutes, and final infarct volume determination by magnetic resonance imaging 48 to 72 hours posttreatment. Core volume overestimations and underestimations were defined as a difference of at least 20 mL between CTP‐RAPID predicted infarct core and Diffusion Weighted Imaging (DWI) final infarct volume. Primary outcome was the association of presentation glucose and hemoglobin A1c (HgbA1c) with underestimation of core volume and was measured using multivariable logistic regression adjusted for comorbidities and presentation characteristics. Secondary outcomes included frequency of overestimation of infarct core. Results Among 256 patients meeting inclusion criteria, median age was 67 (interquartile range [IQR], 57–77) years, 51.6% were women, and 132 (51.6%) and 93 (36.3%) had elevated presentation glucose and elevated HgbA1c, respectively. Median CTP‐predicted core was 6 mL (IQR, 0–30 mL), median DWI final infarct volume was 14 mL (IQR, 6‐43 mL), and median difference was 12 mL (IQR, 5–35 mL). Twenty‐eight (10.9%) patients had infarct core overestimation and 68 (26.6%) had underestimation. Compared with those with no underestimation, patients with underestimation had elevated blood glucose (median, 119 [IQR, 103–155] versus 138 [IQR, 117–195] mg/dL; P = 0.002) and HgbA1c (median, 5.80% [IQR, 5.40–6.40] versus 6.40% [IQR, 5.50–7.90]; P = 0.009). In multivariable analysis, underestimation was independently associated with elevated glucose (adjusted odds ratio [OR], 2.10; P = 0.038) and HgbA1c (adjusted OR, 2.37; P = 0.012). Overestimation was associated with lower presentation blood glucose (median, 109 [IQR, 99–132] in overestimation versus 127 [IQR, 107–172] mg/dL in no overestimation; P = 0.003) and HgbA1c (5.6%[IQR 5.1–6.2] in overestimation versus 5.90%[IQR, 5.50–6.70] in no overestimation; P = 0.012). Conclusions Acute and chronic hyperglycemia were strongly associated with CTP underestimation in patients with large‐vessel occlusion acute ischemic stroke undergoing endovascular therapy. Glycemic state should be considered when interpreting CTP findings in patients with large‐vessel occlusion acute ischemic stroke.