Abstract
[No abstract available]

Abstract
Accurate surgical planning is critical in mandibular reconstruction to restore the oncology patient's function and aesthetics. However, the use of physical three-dimensional (3D) models is often limited by time-consuming manual segmentation procedures or the high cost of commercial solutions. This work addresses the need for an accessible, quick, and low-cost pipeline to obtain a 3D printed model of the segmented mandible from a Computed Tomography (CT) scan. The automatic segmentation stage relied on the two-dimensional U-Net architecture, which was trained and validated with slices across two public datasets (PDDCA, HaN-Seg) and tested with the other two public datasets (TCIA RT, Austrian). The best model achieved an average dice similarity coefficient (DSC) of 0.912 ± 0.077 across all test sets. The segmentation output was reconstructed into a 3D volume, improved through a post-processing method (with morphological closing, upsample, smoothing, and mesh reduction), and 3D printed through fused deposition modelling. The assessment of a stomatologist confirmed overall high anatomical fidelity to the CT and clinical utility, even though further improvements in important fine anatomical elements were suggested. This solution contributes to a promising alternative to producing 3D personalised mandibles for surgical planning, reducing time and manual effort while improving the quality and accessibility. Future work may explore the use of 3D DL architectures and a broader evaluation of the 3D mandible models.

Abstract
Deep learning has been extensively applied to medical imaging tasks over the past years, achieving outstanding results. However, the obscure reasoning of the models and the lack of supportive evidence causes both clinicians and patients to distrust the models' predictions, hindering their adoption in clinical practice. In recent years, the research community has focused on developing explanations capable of revealing a model's reasoning. Among various types of explanations, example-based explanations emerged as particularly intuitive for medical practitioners. Despite the intuitiveness and wide development of example-based explanations, no work provides a comprehensive review of existing example-based explainability works in the medical image domain. In this work, we review works that provide example-based explanations for medical imaging tasks, reflecting on their strengths and limitations. We identify the absence of objective evaluation metrics, the lack of clinical validation and privacy concerns as the main issues that hinder the deployment of example-based explanations in clinical practice. Finally, we reflect on future directions contributing towards the deployment of example-based explainability in clinical practice.

Abstract
Recent work by Oberti et al, (Astron. Astrophys., 667, 48, 2022) argued and made a compelling case that classical astronomical adaptive optics (AO) tomography performance can be further enhanced by carefully designing and optically configuring the system to leverage inherent super-resolution (SR) capabilities. Our goal here is to further materialise the concept by providing the means to compute SR-enabling tomographic reconstructors for AO and showcase its broad uptake on soon every 10 m-class VIS/NIR telescopes and Giant Segmented Mirror Telescopes of up to 40 m in diameter. To that end we indicate the necessary tomography generalisations where we: (i) clarify how model-and-deploy is a generic methodological umbrella for linear minimum-mean-squared-error (LMMSE) tomographic reconstructors arising naturally from the solution of the tomographic inverse problem, thus unifying various solutions presented as distinct in the literature within a single framework, (ii) recall how such solutions are found as limiting cases of a model-based optimal control problem, thus elucidating how pseudo-open-loop control is a feature of the latter that allows LMMSE reconstructors to be adapted to closed-loop systems, (iii) review the two forms of the LMMSE tomographic reconstructors, highlighting the necessary adaptations to accommodate super-resolution, (iv) review the implementation in either dense-format vector-matrix-multiplication or sparse iterative forms and (v) discuss the implications for runtime and off-line real-time implementations, anticipating widespread adoption. We illustrate our examples with physical-optics numerical simulations for 10 m and 40 m-scale systems showing the performance benefits of super-resolution in the order of several tens of nm rms and the computational burden associated.

Abstract
In the study, a new method for analyzing Electrocardiogram (ECG) signals is suggested, which is vital for detecting and treating heart diseases. The technique focuses on improving ECG signal classification, particularly in identifying different heart conditions like arrhythmias and myocardial infarctions. An enhanced version of the differential evolution (DE) algorithm integrated with neural networks is leveraged to classify these signals effectively. The process starts with preprocessing and extracting key features from ECG signals. These features are then processed by a multi-layer perceptron (MLP), a common neural network for ECG analysis. However, traditional MLP training methods have limitations, such as getting trapped in suboptimal solutions. To overcome this, an advanced DE algorithm is used, incorporating a partition-based strategy, opposition-based learning, and local search mechanisms. This improved DE algorithm optimizes the MLP by fine-tuning its weights and biases, using them as starting points for further refinement by the Gradient Descent with Momentum (GDM) local search algorithm. Extensive experiments demonstrate that this novel training approach yields better results than the traditional method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract