Evaluating artificial intelligence for comparative radiography.

INTRODUCTION: Comparative radiography is a forensic identification and shortlisting technique based on the comparison of skeletal structures in ante-mortem and post-mortem images. The images (e.g., 2D radiographs or 3D computed tomographies) are manually superimposed and visually compared by a forensic practitioner. It requires a significant amount of time per comparison, limiting its utility in large comparison scenarios. METHODS: We propose and validate a novel framework for automating the shortlisting of candidates using artificial intelligence. It is composed of (1) a segmentation method to delimit skeletal structures' silhouettes in radiographs, (2) a superposition method to generate the best simulated "radiographs" from 3D images according to the segmented radiographs, and (3) a decision-making method for shortlisting all candidates ranked according to a similarity metric. MATERIAL: The dataset is composed of 180 computed tomographies and 180 radiographs where the frontal sinuses are visible. Frontal sinuses are the skeletal structure analyzed due to their high individualization capability. RESULTS: Firstly, we validate two deep learning-based techniques for segmenting the frontal sinuses in radiographs, obtaining high-quality results. Secondly, we study the framework's shortlisting capability using both automatic segmentations and superimpositions. The obtained superimpositions, based only on the superimposition metric, allowed us to filter out 40% of the possible candidates in a completely automatic manner. Thirdly, we perform a reliability study by comparing 180 radiographs against 180 computed tomographies using manual segmentations. The results allowed us to filter out 73% of the possible candidates. Furthermore, the results are robust to inter- and intra-expert-related errors.

Information fusion for infant age estimation from deciduous teeth using machine learning.

OBJECTIVES: Over the past few years, several methods have been proposed to improve the accuracy of age estimation in infants with a focus on dental development as a reliable marker. However, traditional approaches have limitations in efficiently combining information from different teeth and features. In order to address these challenges, this article presents a study on age estimation in infants with Machine Learning (ML) techniques, using deciduous teeth. MATERIALS AND METHODS: The involved dataset comprises 114 infant skeletons from the Granada osteological collection of identified infants, aged between 5 months of gestation and 3 years of age. The samples consist of features such as the maximum length and mineralization and alveolar stages of teeth. For the purpose of designing a method capable of combining all the information available from each individual, a Multilayer Perceptron model is proposed, one of the most popular artificial neural networks. This model has been validated using the leave-one-out experimental validation protocol. Through different groups of experiments, the study examines the informativeness of the aforementioned features, individually and in combination. RESULTS: The results indicate that the fusion of different variables allows for more accurate age estimates (RMSE = 66 days) than when variables are analyzed separately (RMSE = 101 days). Additionally, the study demonstrates the benefits of involving multiple teeth, which significantly reduces the RMSE compared to a single tooth. DISCUSSION: This article underlines the clear advantages of ML-based methods, emphasizing their potential to improve the accuracy and robustness when estimating the age of infants.

moGrams: A Network-Based Methodology for Visualizing the Set of Nondominated Solutions in Multiobjective Optimization.

An appropriate visualization of multiobjective nondominated solutions is a valuable asset for decision making. Although there are methods for visualizing the solutions in the design space, they do not provide any information about their relationship. In this paper, we propose a novel methodology that allows the visualization of the nondominated solutions in the design space and their relationships by means of a network. The nodes represent the solutions in the objective space while the edges show the relationships among the solutions in the design space. Our proposal (called moGrams) thus provides a joint visualization of both objective and design spaces. It aims at helping the decision maker to get more understanding of the problem so that (s)he can choose the most appropriate and flexible final solution. moGrams can be applied to any multicriteria problem in which the solutions are related by a similarity metric. Besides, the decision maker interaction is facilitated by modifying the network based on the current preferences to obtain a clearer view. An exhaustive experimental study is performed using four multiobjective problems with a variable number of objectives to show both usefulness and versatility of moGrams. The results exhibit interesting characteristics of our methodology for visualizing and analyzing solutions of multiobjective problems.

Study on the criteria for assessing skull-face correspondence in craniofacial superimposition.

Craniofacial superimposition has the potential to be used as an identification method when other traditional biological techniques are not applicable due to insufficient quality or absence of ante-mortem and post-mortem data. Despite having been used in many countries as a method of inclusion and exclusion for over a century it lacks standards. Thus, the purpose of this research is to provide forensic practitioners with standard criteria for analysing skull-face relationships. Thirty-seven experts from 16 different institutions participated in this study, which consisted of evaluating 65 criteria for assessing skull-face anatomical consistency on a sample of 24 different skull-face superimpositions. An unbiased statistical analysis established the most objective and discriminative criteria. Results did not show strong associations, however, important insights to address lack of standards were provided. In addition, a novel methodology for understanding and standardizing identification methods based on the observation of morphological patterns has been proposed.

Biomedical image segmentation using geometric deformable models and metaheuristics.

This paper describes a hybrid level set approach for medical image segmentation. This new geometric deformable model combines region- and edge-based information with the prior shape knowledge introduced using deformable registration. Our proposal consists of two phases: training and test. The former implies the learning of the level set parameters by means of a Genetic Algorithm, while the latter is the proper segmentation, where another metaheuristic, in this case Scatter Search, derives the shape prior. In an experimental comparison, this approach has shown a better performance than a number of state-of-the-art methods when segmenting anatomical structures from different biomedical image modalities.

Intensity-based image registration using scatter search.

OBJECTIVE: We present a novel intensity-based algorithm for medical image registration (IR). METHODS AND MATERIALS: The IR problem is formulated as a continuous optimization task, and our work focuses on the development of the optimization component. Our method is designed over an advanced scatter search template, and it uses a combination of restart and dynamic boundary mechanisms integrated within a multi-resolution strategy. RESULTS: The experimental validation is performed over two datasets of human brain magnetic resonance imaging. The algorithm is evaluated in both a stand-alone registration application and an atlas-based segmentation process targeted to the deep brain structures, considering a total of 16 and 18 scenarios, respectively. Five established IR techniques, both feature- and intensity-based, are considered for comparison purposes, and ground-truth data is used to quantitatively assess the quality of the results. Our approach ranked first in both studies and it is able to outperform all competitors in 12 of 16 registration scenarios and in 14 of 18 registration-based segmentation tasks. A statistical analysis confirms with high confidence (p<0.014) the accuracy and applicability of our method. CONCLUSIONS: With a proper, problem-specific design, scatter search is able to provide a robust, global optimization. The accuracy and reliability of the registration process are superior to those of classic gradient-based techniques.