Obtaining bone models that represent certain types of fractures is limited by the need for such fractures to occur in real life and to be processed from medical images. This work aims to propose a method that starts from the design of specific fracture patterns in order to be projected on 3D geometric bone models, being prepared for their subsequent geometric fracturing. The process of projecting expert-generated fracture patterns has been approached in such a way that they contain geometrical and topological information for the subsequent fracture of the triangle mesh representing the bone model, giving information about the validity of the fracture pattern due to the design process, the validation performed, and the relationships between the fracture lines. Different 3D models of long bones have been used (femur, humerus, ulna and fibula). Also, different types of fracture patterns have been created. These patterns have been used to obtain their projection on three-dimensional bones. In this study, an expert validation of the fracture patterns projected on the bone models is performed. A forensic validation of the fracture patterns used as starting point for the projection is also performed for cases in which this fracture is produced by impact, for which there is scientific evidence based on forensic analysis. This validation also supports the experts, giving them the necessary feedback to complete or modify their fracture patterns according to criteria analyzed from a forensic point of view. The patterns fit the bone models correctly, despite the irregularities of the bone models, and correspond to the expected projection. In addition, it provides us with a clear line of work, by using the topological information of the fracture pattern and the bone model, which allows us to establish a consistent basis for future guided fractures.
Fracture pattern acquisition and representation in human bones play a crucial role in medical simulation, diagnostics, and treatment planning. This article presents a comprehensive review of methodologies employed in acquiring and representing bone fracture patterns. Several techniques, including segmentation algorithms, curvature analysis, and deep learning-based approaches, are reviewed to determine their effectiveness in accurately identifying fracture zones. Additionally, diverse methods for representing fracture patterns are evaluated. The challenges inherent in detecting accurate fracture zones from medical images, the complexities arising from multifragmentary fractures, and the need to automate fracture reduction processes are elucidated. A detailed analysis of the suitability of each representation method for specific medical applications, such as simulation systems, surgical interventions, and educational purposes, is provided. The study explores insights from a broad spectrum of research articles, encompassing diverse methodologies and perspectives. This review elucidates potential directions for future research and contributes to advancements in comprehending the acquisition and representation of fracture patterns in human bone.
24 April 2024 in International Journal of Computational Intelligence Systems
The acquisition of bone models to perform simulations is a complex and expensive process. The hierarchical structure of bones is very complex, so that studies are mainly focused on the larger scales of bones. The objective of this work is to perform a fracture simulation at the microscale level. For this purpose, the first part of the process focuses on segmenting a bone model and selecting an area of it to generate a representation of the microstructures that make up the bone tissue from a microscopic point of view. The second part is dedicated to carry out a fracture simulation in the microscopic bone model. The developed algorithm follows a statistical approach and solves the main problems of the traditional approach (FEM) to perform a bone fracture simulation. The method returns the path that a fracture follows and demonstrates how bone structures affect fracture growth. The parameters used are configurable and can be adapted for specific cases. In addition, users can reproduce as many clinical cases as desired within seconds without have to manually segment images obtained from a microscope. The data obtained may be exported to obtain synthetic images that could be used to generate datasets for machine learning tasks or other purposes.
Bone fracture modeling is a major challenge in medical image analysis and simulation, requiring accurate strategies to faithfully represent complex fracture patterns. This study conducts a comprehensive analysis of three subdivision strategies: approximation, triangulation, and a hybrid approach. The approximation method preserves mesh topology but exhibits visual inconsistencies with non-horizontal fractures. Triangulation accurately represents fractures but alters mesh topology. The hybrid approach balances geometric accuracy and visual fidelity by dynamically adjusting an approximation threshold. This minimizes deviations from the original fracture pattern and maintains visual quality. Using quality metrics, we evaluate these strategies for geometric accuracy, visual fidelity, and mesh topology. Our results indicate that the hybrid approach effectively balances accuracy and visual quality, making it a promising solution for bone fracture modeling. Expert validation and quantitative metrics underscore the importance of tailored approaches for different fracture patterns. This study significantly advances computational models for clinical and research applications, offering enhanced tools for improving the accuracy and realism of bone fracture simulations, ultimately benefiting surgical planning, prosthetic design, and medical training.
Chest X-ray (CXR) imaging remains the most widely used radiological modality for assessing pulmonary and cardiothoracic disease, yet its interpretation is inherently constrained by tissue superposition, subtle radiographic findings and marked inter-observer variability. Recent advances in artificial intelligence (AI) have driven significant progress in automated CXR analysis, supported by large public datasets, evolving annotation strategies and increasingly expressive deep learning architectures. This review presents a comprehensive synthesis of approaches for pulmonary abnormality detection, encompassing convolutional neural networks, transformers, multimodal and vision–language models and self-supervised representation learning. We critically discuss their strengths, limitations and vulnerability to label noise, domain shift and shortcut learning. In parallel, we examine dataset properties, annotation practices, robustness challenges, explainability methods and the heterogeneity of evaluation protocols that hinder fair comparison and clinical translation. Building on these observations, the review identifies key future directions, including foundation models, multimodal integration, federated and domain-generalized training, longitudinal modeling, synthetic data generation and standardized clinical evaluation frameworks. By integrating methodological and clinical perspectives, this work offers an up-to-date reference for researchers and clinicians and outlines a roadmap toward reliable, interpretable and clinically deployable AI systems for chest radiography.