Abstract
The large gap between the generalization level of state-of-the-art machine learning and human learning systems calls for the development of artificial intelligence (AI) models that are truly inspired by human cognition. In tasks related to image analysis, searching for pixel-level regularities has reached a power of information extraction still far from what humans capture with image-based observations. This leads to poor generalization when even small shifts occur at the level of the observations. We explore a perspective on this problem that is directed to learning the generative process with causality-related foundations, using models capable of combining symbolic manipulation, probabilistic reasoning, and pattern recognition abilities. We briefly review and explore connections of research from machine learning, cognitive science, and related fields of human behavior to support our perspective for the direction to more robust and human-like artificial learning systems.

Abstract
With the objective of developing new methods to acquire diagnostic information, the reconstruction of the broadband absorption coefficient spectra (mu a[lambda]) of healthy and chromophobe renal cell carcinoma kidney tissues was performed. By performing a weighted sum of the absorption spectra of proteins, DNA, oxygenated, and deoxygenated hemoglobin, lipids, water, melanin, and lipofuscin, it was possible to obtain a good match of the experimental mu a(lambda) of both kidney conditions. The weights used in those reconstructions were estimated using the least squares method, and assuming a total water content of 77% in both kidney tissues, it was possible to calculate the concentrations of the other tissue components. It has been shown that with the development of cancer, the concentrations of proteins, DNA, oxygenated hemoglobin, lipids, and lipofuscin increase, and the concentration of melanin decreases. Future studies based on minimally invasive spectral measurements will allow cancer diagnosis using the proposed approach.

Abstract
Lung cancer remains the leading cause of cancer related deaths globally, responsible for approximately 1.8 million deaths each year. A key contributor to this high mortality rate is the late-stage diagnosis of the disease, underscoring the urgent need for effective early detection strategies. Low-dose computed tomography (CT) has shown great value in early screening, particularly when paired with clinical information. Clinical data, while valuable, lacks spatial and morphological insights essential for comprehensive evaluation. Combining both modalities offers a more holistic approach for lung cancer classification. This study presents AI-based methods for lung cancer classification using unimodal approaches - structured clinical data and chest CT imaging - alongside a novel multimodal deep learning framework that integrates both data types to classify lung nodules as malignant or benign. For the clinical modality, machine learning models including logistic regression, random forests, LightGBM, XGBoost, and multilayer perceptrons were evaluated with extensive hyperparameter tuning. In the imaging modality, ResNet18 and ResNet34 convolutional neural networks were used, with and without data augmentation. The study explored both intermediate and late fusion strategies to combine modality-specific representations. Results show that multimodal models consistently outperformed their unimodal counterparts, achieving a best-case area under the ROC curve (AUC) of 0.9138, with an accuracy of 0.8424 and an F1-score of 0.8422. These findings highlight the complementary strengths of imaging and clinical data and support the growing potential of multimodal deep learning in improving diagnostic accuracy in lung cancer classification. © 2025 IEEE.

Abstract
The Vision Transformer (ViT) architecture has emerged as a potential game-changer in computer vision, offering scalability and global attention that have generated considerable interest in recent years. Its adaptability has fueled enthusiasm for its application. This work investigates the boundaries of the architecture, focusing on developing new techniques targeting explicitly complex tasks, such as medical imaging datasets, which often exhibit high variability, class imbalance, and limited sample sizes. We propose a set of mixed regularisation and augmentation techniques to enhance the performance of models. These include a novel loss function and a smoothly differentiable activation function, leading to more stable training and model performance. The results show that incorporating these techniques improves model performance and training convergence.

Abstract
Epidermal Growth Factor Receptor (EGFR) is one of the most frequently mutated genes in lung cancer. Its mutation status characterization is crucial for personalized treatment in Non-Small-Cell Lung Cancer (NSCLC). Biopsy is the gold standard for characterizing the EGFR mutation status. However, it is an invasive time-consuming method and is often burdensome or even impractical for some patients. Therefore, it is of utmost importance to identify alternative non-invasive methods for classifying this mutation. Computed Tomography (CT) images represent a non-invasive, safer and faster method to directly characterize lung cancer. This study developed a comprehensive radiomic approach for EGFR mutation classification using CT images, in which two preprocessing strategies were compared and five machine learning algorithms were evaluated across different datasets. We analyzed two independent datasets individually and combined, implementing lung containing nodule versus bounding box around nodule preprocessing approaches. Radiomic features were extracted using PyRadiomics and selected through Principal Component Analysis (PCA) (65-95% variance thresholds) and pairwise correlation filtering. The results demonstrated that the lung with nodule strategy achieved better and more consistent performance compared to the bounding box around the nodule method. The best performance (AUC=0.780) was achieved using Random Forest with correlation filtering. The results suggest that radiomics may be a potential support tool for EGFR classification when biopsy is not feasible or recommended. This would enable safer and more efficient personalized treatment. Nevertheless, the results underscore the need for larger, diverse datasets to improve model robustness for characterizing such complex and variable information before clinical integration. © 2025 IEEE.

Abstract
Modulation instability (MI) of the continuous wave (cw) has been associated with the onset of stable solitons in conservative and dissipative systems. The cubic complex Ginzburg-Landau equation (CGLE) is a prototype of a damped, driven, nonlinear, and dispersive system. The inclusion of nonlinear gradients is essential to stabilize pulses whether stationary or oscillatory. The soliton solutions of this model have been reasonably studied; however, its cw solution characteristics and stability have not been reported yet. Here, we obtain the cw solutions of the cubic CGLE with nonlinear gradient terms and study its short- and long-term evolution under the effect of small perturbations. We have found that, for each admissible amplitude, there are two branches of cw solutions, and all of them are unstable. Then, through direct integration of the evolution equation, we study the evolution of those cw solutions, observing the emergence of plain and oscillatory solitons. Depending on whether the cw and/or its perturbation are sinusoidal, we can obtain a train of a finite number of pulses or bound states.