Abstract
Mammography imaging remains the gold standard for breast cancer detection and diagnosis, but challenges in image quality can lead to misdiagnosis, increased radiation exposure, and higher healthcare costs. This comprehensive review evaluates traditional and machine learning-based techniques for improving mammography image quality, aiming to benefit clinicians and enhance diagnostic accuracy. Our literature search, spanning 2015 - 2024, identified 115 articles focusing on contrast enhancement and noise reduction methods, including histogram equalization, filtering, unsharp masking, fuzzy logic, transform-based techniques, and advanced machine learning approaches. Machine learning, particularly architectures integrating denoising autoencoders with convolutional neural networks, emerged as highly effective in enhancing image quality without compromising detail. The discussion highlights the success of these techniques in improving mammography images' visual quality. However, challenges such as high noise ratios, inconsistent evaluation metrics, and limited open-source datasets persist. Addressing these issues offers opportunities for future research to further advance mammography image enhancement methodologies.

Abstract
Missing data is a common challenge in real-world datasets and can arise for various reasons. This has led to the classification of missing data mechanisms as missing completely at random, missing at random, or missing not at random. Currently, the literature offers various algorithms for imputing missing data, each with advantages tailored to specific mechanisms and levels of missingness. This paper introduces a novel approach to missing data imputation using the well-established label propagation algorithm, named Label Propagation for Missing Data Imputation (LPMD). The method combines, weighs, and propagates known feature values to impute missing data. Experiments on benchmark datasets highlight its effectiveness across various missing data scenarios, demonstrating more stable results compared to baseline methods under different missingness mechanisms and levels. The algorithms were evaluated based on processing time, imputation quality (measured by mean absolute error), and impact on classification performance. A variant of the algorithm (LPMD2) generally achieved the fastest processing time compared to other five imputation algorithms from the literature, with speed-ups ranging from 0.7 to 23 times. The results of LPMD were also stable regarding the mean absolute error of the imputed values compared to their original counterparts, for different missing data mechanisms and rates of missing values. In real applications, missingness can behave according to different and unknown mechanisms, so an imputation algorithm that behaves stably for different mechanisms is advantageous. The results regarding ML models produced using the imputed datasets were also comparable to the baselines. © 2013 IEEE.

Abstract

Abstract
ydata-profiling is an open-source Python package for advanced exploratory data analysis that enables users to generate data profiling reports in a simple, fast, and efficient manner, fostering a standardized and visual understanding of the data. Beyond traditional descriptive properties and statistics, ydata-profiling follows a Data-Centric AI approach to exploratory analysis, as it focuses on the automatic detection and highlighting of complex data characteristics often associated with potential data quality issues, such as high ratios of missing or imbalanced data, infinite, unique, or constant values, skewness, high correlation, high cardinality, non-stationarity, seasonality, duplicate records, and other inconsistencies. The source code, documentation, and examples are available in the GitHub repository: https://github.com/ydataai/ydata-profiling.

Abstract
We present a methodology to assess cell level alterations on the human retina responsible for functional changes observable in the Optical Coherence Tomography data in healthy ageing and in disease conditions, in the absence of structural alterations. The methodology is based in a 3D multilayer Monte Carlo computational model of the human retina. The optical properties of each layer are obtained by solving the Maxwell's equations for 3D domains representative of small regions of those layers, using a Discontinuous Galerkin Finite Element Method (DG-FEM). Here we present the DG-FEM Maxwell 3D model and its validation against Mie's theory for spherical scatterers. We also present an application of our methodology to the assessment of cell level alterations responsible for the OCT data in Diabetic Macular Edema. It was possible to identify which alterations are responsible for the changes observed in the OCT scans of the diseased groups.

Abstract
The goal of this work is to develop a computational model of the human retina and simulate light scattering through its structure aiming to shed light on data obtained by optical coherence tomography in human retinas. Currently, light propagation in scattering media is often described by Mie's solution to Maxwell's equations, which only describes the scattering patterns for homogeneous spheres, thus limiting its application for scatterers of more complex shapes. In this work, we propose a discontinuous Galerkin method combined with a low-storage Runge-Kutta method as an accurate and efficient way to numerically solve the time-dependent Maxwell's equations. In this work, we report on the validation of the proposed methodology by comparison with Mie's solution, a mandatory step before further elaborating the numerical scheme towards the propagation of electromagnetic waves through the human retina.