Najoua Essoukri Ben Amara

Electrical Impedance Tomography (EIT) as a non-invasive imaging method, faces two main challenges due to the inherent difficulty in solving the inverse image reconstruction problem. The main difficulty lies in simultaneously achieving two key goals: Accurately estimating conductivity values and clearly reproducing structural boundaries. Existing methods typically excel at one aspect while compromising the other. In this work, we present an advanced ensemble learning approach combining complementary deep learning models to overcome these challenges. The method integrates two specialized ensembles: A gradient-boosting framework with an enhanced 1D-CNN-GRU for conductivity prediction and a Dense Attention Network (DA-Net) for boundary shape reconstruction, unified through a stacking ensemble with a custom loss function optimizing both conductivity accuracy and structural preservation by combining Rooted Mean Squared Error (RMSE) for quantitative accuracy and Image Correlation Coefficient (ICC) in a weighted formulation. The model is first validated in a well-controlled water tank setting. Simulation results show an ICC of 0.975 and Relative Image Error (RIE) of 0.171. Experimental validation further confirms the method’s robustness, maintaining consistent reconstruction quality for different object positions and materials. The method was then evaluated using a more complex, simulated lung model that includes realistic anatomical features, changes in conductivity distribution, and tissue anomalies. Results demonstrate improved performance compared to baseline methods by an average 2.67% increase in ICC and 24.55% reduction in RIE. The results confirm that the novel systematic ensemble approach successfully addresses the dual challenges of conductivity prediction and boundary preservation for effective anomaly detection in EIT imaging.

In recent years, deep learning networks have demonstrated remarkable progress in the semantic segmentation of historical documents. Nonetheless, their limited explainability remains a critical concern, as these models frequently operate as black boxes, thereby constraining confidence in the trustworthiness of their outputs. To enhance transparency and reliability in their deployment, increasing attention has been directed toward explainable artificial intelligence (XAI) techniques. These techniques typically produce fine-grained attribution maps in the form of heatmaps, illustrating feature contributions from different blocks and layers within a deep neural network (DNN). However, such maps often closely resemble the segmentation outputs themselves, and there is currently no consensus regarding appropriate explainability metrics for semantic segmentation. To overcome these challenges, we present SegClarity, a novel workflow designed to integrate explainability into the analysis of historical documents. The workflow combines visual and quantitative evaluations specifically tailored to segmentation-based applications. Furthermore, we introduce the Attribution Concordance Score (ACS), a new explainability metric that provides quantitative insights into the consistency and reliability of attribution maps. To evaluate the effectiveness of our approach, we conducted extensive qualitative and quantitative experiments using two datasets of historical document images, two U-Net model variants, and four attribution-based XAI methods. A qualitative assessment involved four XAI methods across multiple U-Net layers, including comparisons at the input level with state-of-the-art perturbation methods RISE and MiSuRe. Quantitatively, five XAI evaluation metrics were employed to benchmark these approaches comprehensively. Beyond historical document analysis, we further validated the workflow’s generalization by demonstrating its transferability to the Cityscapes dataset, a challenging benchmark for urban scene segmentation. The results demonstrate that the proposed workflow substantially improves the interpretability and reliability of deep learning models applied to the semantic segmentation of historical documents. To enhance reproducibility, we have released SegClarity’s source code along with interactive examples of the proposed workflow.

The rapid expansion of digital imagery, combined with increasingly sophisticated editing tools, has made image forgery a widespread and critical concern in fields such as journalism, forensics, and social media. This study provides a comprehensive review of Copy-Move Forgery Detection (CMFD) methods, focusing on the latest advances in deep learning-based techniques. We analyze key real-world challenges, summarize the most relevant recent solutions, and highlight persistent limitations that hinder robustness, accuracy, and practical deployment. A comparative review and qualitative analysis of prominent deep learning architectures reported in the literature is conducted to examine their relative efficiency, resilience, and trade-offs under diverse forgery scenarios. Finally, the paper highlights future research directions, including the development of more adaptable and generalizable models, the design of comprehensive benchmark datasets, the pursuit of real-time detection frameworks, and the enhancement of interpretability and transparency in CMFD systems.

Identifying the optimal current injection pattern is crucial in electrical impedance tomography (EIT) to improve image reconstruction accuracy. This study compares the performance of a newly proposed rotating radial current injection pattern with the commonly used in EIT, which are the adjacent and opposite injection patterns. The evaluation is realized on a biomimetic thorax-shaped resistor mesh phantom by evaluating quantitative metrics derived from measured boundary voltages, including condition number ($k$), dynamic range (DR), and mean sensitivity ($S$). The investigation is based on the evaluation of the image correlation coefficient (ICC) and the structural similarity index measure $(SSIM)$, comparing reconstructed images from simulation and measurement data to assess reconstruction accuracy. Results demonstrate that the rotating radial pattern achieves an ICC of 0.98, an SSIM of 0.82, a lower $k$, a higher $S$, and an increased DR compared to the adjacent and opposite patterns. These findings highlight the potential of the rotating radial pattern to advance EIT imaging performance for diverse applications in lung imaging.

Blue-emitting bismuth-doped lanthanum oxide (La₂O₃: Bi³⁺) with various concentrations of Bi was synthesized using the sol–gel combustion method and used for visualization of latent fingerprints (LFPs). An X-ray diffraction (XRD) study revealed the hexagonal structure of the phosphors and total incorporation of the bismuth in the La₂O₃ matrix. Field Emission Scanning Electron Microscopy (FE-SEM) and Fourier Transform Infrared Spectroscopy (FTIR) were used to study the morphology and the relative vibrations of the synthesized samples. Photoluminescence (PL) studies showed strong blue emission around 460 nm due to the ³P₁ → ¹S₀ transition. Clear bright-blue fingerprint images were obtained with the powder dusting method on various surfaces like aluminum, compact discs, glass, wood and marble. A first evaluation of these images indicated a clear visualization of all three levels of details and a very high contrast ranging from 0.41 on marble to 0.90 on aluminum. As a further step, we used an algorithm for extracting fingerprint minutiae with which we succeeded in detecting all three levels of fingerprint details and even the most difficult ones, like open and closed pores. According to these analyses, La₂O₃: Bi phosphor is demonstrated to be an effective blue fluorescent powder for excellent visualization of latent fingerprints.