Evaluating a Periapical Lesion Detection CNN on a Clinically Representative CBCT Dataset-A Validation Study.

The aim of this validation study was to comprehensively evaluate the performance and generalization capability of a deep learning-based periapical lesion detection algorithm on a clinically representative cone-beam computed tomography (CBCT) dataset and test for non-inferiority. The evaluation involved 195 CBCT images of adult upper and lower jaws, where sensitivity and specificity metrics were calculated for all teeth, stratified by jaw, and stratified by tooth type. Furthermore, each lesion was assigned a periapical index score based on its size to enable a score-based evaluation. Non-inferiority tests were conducted with proportions of 90% for sensitivity and 82% for specificity. The algorithm achieved an overall sensitivity of 86.7% and a specificity of 84.3%. The non-inferiority test indicated the rejection of the null hypothesis for specificity but not for sensitivity. However, when excluding lesions with a periapical index score of one (i.e., very small lesions), the sensitivity improved to 90.4%. Despite the challenges posed by the dataset, the algorithm demonstrated promising results. Nevertheless, further improvements are needed to enhance the algorithm's robustness, particularly in detecting very small lesions and the handling of artifacts and outliers commonly encountered in real-world clinical scenarios.

Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs.

An important factor for the development of spinal degeneration, pain and the outcome of spinal surgery is known to be the balance of the spine. It must be analyzed in an upright, standing position to ensure physiological loading conditions and visualize load-dependent deformations. Despite the complex 3D shape of the spine, this analysis is currently performed using 2D radiographs, as all frequently used 3D imaging techniques require the patient to be scanned in a prone position. To overcome this limitation, we propose a deep neural network to reconstruct the 3D spinal pose in an upright standing position, loaded naturally. Specifically, we propose a novel neural network architecture, which takes orthogonal 2D radiographs and infers the spine's 3D posture using vertebral shape priors. In this work, we define vertebral shape priors using an atlas and a spine shape prior, incorporating both into our proposed network architecture. We validate our architecture on digitally reconstructed radiographs, achieving a 3D reconstruction Dice of 0.95, indicating an almost perfect 2D-to-3D domain translation. Validating the reconstruction accuracy of a 3D standing spine on real data is infeasible due to the lack of a valid ground truth. Hence, we design a novel experiment for this purpose, using an orientation invariant distance metric, to evaluate our model's ability to synthesize full-3D, upright, and patient-specific spine models. We compare the synthesized spine shapes from clinical upright standing radiographs to the same patient's 3D spinal posture in the prone position from CT.

Automated pneumothorax triaging in chest X-rays in the New Zealand population using deep-learning algorithms.

INTRODUCTION: The primary aim was to develop convolutional neural network (CNN)-based artificial intelligence (AI) models for pneumothorax classification and segmentation for automated chest X-ray (CXR) triaging. A secondary aim was to perform interpretability analysis on the best-performing candidate model to determine whether the model's predictions were susceptible to bias or confounding. METHOD: A CANDID-PTX dataset, that included 19,237 anonymized and manually labelled CXRs, was used for training and testing candidate models for pneumothorax classification and segmentation. Evaluation metrics for classification performance included Area under the receiver operating characteristic curve (AUC-ROC), sensitivity and specificity, whilst segmentation performance was measured using mean Dice and true-positive (TP)-Dice coefficients. Interpretability analysis was performed using Grad-CAM heatmaps. Finally, the best-performing model was implemented for a triage simulation. RESULTS: The best-performing model demonstrated a sensitivity of 0.93, specificity of 0.95 and AUC-ROC of 0.94 in identifying the presence of pneumothorax. A TP-Dice coefficient of 0.69 is given for segmentation performance. In triage simulation, mean reporting delay for pneumothorax-containing CXRs is reduced from 9.8 ± 2 days to 1.0 ± 0.5 days (P-value < 0.001 at 5% significance level), with sensitivity 0.95 and specificity of 0.95 given for the classification performance. Finally, interpretability analysis demonstrated models employed logic understandable to radiologists, with negligible bias or confounding in predictions. CONCLUSION: AI models can automate pneumothorax detection with clinically acceptable accuracy, and potentially reduce reporting delays for urgent findings when implemented as triaging tools.

Curation of the CANDID-PTX Dataset with Free-Text Reports.

Supplemental material is available for this article. Keywords: Conventional Radiography, Thorax, Trauma, Ribs, Catheters, Segmentation, Diagnosis, Classification, Supervised Learning, Machine Learning © RSNA, 2021.

VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images.

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.

A Framework for the generation of digital twins of cardiac electrophysiology from clinical 12-leads ECGs.

Cardiac digital twins (Cardiac Digital Twin (CDT)s) of human electrophysiology (Electrophysiology (EP)) are digital replicas of patient hearts derived from clinical data that match like-for-like all available clinical observations. Due to their inherent predictive potential, CDTs show high promise as a complementary modality aiding in clinical decision making and also in the cost-effective, safe and ethical testing of novel EP device therapies. However, current workflows for both the anatomical and functional twinning phases within CDT generation, referring to the inference of model anatomy and parameters from clinical data, are not sufficiently efficient, robust and accurate for advanced clinical and industrial applications. Our study addresses three primary limitations impeding the routine generation of high-fidelity CDTs by introducing; a comprehensive parameter vector encapsulating all factors relating to the ventricular EP; an abstract reference frame within the model allowing the unattended manipulation of model parameter fields; a novel fast-forward electrocardiogram (Electrocardiogram (ECG)) model for efficient and bio-physically-detailed simulation required for parameter inference. A novel workflow for the generation of CDTs is then introduced as an initial proof of concept. Anatomical twinning was performed within a reasonable time compatible with clinical workflows (<4h) for 12 subjects from clinically-attained magnetic resonance images. After assessment of the underlying fast forward ECG model against a gold standard bidomain ECG model, functional twinning of optimal parameters according to a clinically-attained 12 lead ECG was then performed using a forward Saltelli sampling approach for a single subject. The achieved results in terms of efficiency and fidelity demonstrate that our workflow is well-suited and viable for generating biophysically-detailed CDTs at scale.

Bone age estimation with the Greulich-Pyle atlas using 3T MR images of hand and wrist.

The age estimation of the hand bones by means of X-ray examination is a pillar of the forensic age estimation. Since the associated radiation exposure is controversial, the search for ionizing radiation-free alternatives such as MRI is part of forensic research. The aim of the current study was to use the Greulich-Pyle (GP) atlas on MR images of the hand and wrist to provide reference values for assessing the age of the hand bones. 3T hand MR images of 238 male participants between the ages of 13 and 21 were acquired using 3D gradient echo sequences (VIBE, DESS). Two readers rated the images using the X-ray-based GP atlas method. A descriptive analysis and a transitional analysis were used for the statistical processing of the data. The agreement between and within the raters was assessed. In addition, a comparison was made with the chronological age and with X-ray studies. The descriptive analysis and the transition analysis showed similar results. Both evaluations showed good agreement with X-ray studies. The comparison with the chronological age showed a difference of 0.37 and 0.54 years for the two readers. The age estimate based on the cross-validated transition analysis showed a mean error of -0.28 years. Inter- and intra-rater agreement were good. In summary, it can be concluded that age estimation of hand bones with MR images is routinely applicable with the GP atlas as an alternative without ionizing radiation. However, in order to reduce the estimation error, a multi-factorial assessment based on examinations of several body regions is still recommended.

The four-minute approach revisited: accelerating MRI-based multi-factorial age estimation.

OBJECTIVES: This feasibility study aimed to investigate the reliability of multi-factorial age estimation based on MR data of the hand, wisdom teeth and the clavicles with reduced acquisition time. METHODS: The raw MR data of 34 volunteers-acquired on a 3T system and using acquisition times (TA) of 3:46 min (hand), 5:29 min (clavicles) and 10:46 min (teeth)-were retrospectively undersampled applying the commercially available CAIPIRINHA technique. Automatic and radiological age estimation methods were applied to the original image data as well as undersampled data to investigate the reliability of age estimates with decreasing acquisition time. Reliability was investigated determining standard deviation (SSD) and mean (MSD) of signed differences, intra-class correlation (ICC) and by performing Bland-Altman analysis. RESULTS: Automatic age estimation generally showed very high reliability (SSD < 0.90 years) even for very short acquisition times (SSD ≈ 0.20 years for a total TA of 4 min). Radiological age estimation provided highly reliable results for images of the hand (ICC ≥ 0.96) and the teeth (ICC ≥ 0.79) for short acquisition times (TA = 16 s for the hand, TA = 2:21 min for the teeth), imaging data of the clavicles allowed for moderate acceleration (TA = 1:25 min, ICC ≥ 0.71). CONCLUSIONS: The results demonstrate that reliable multi-factorial age estimation based on MRI of the hand, wisdom teeth and the clavicles can be performed using images acquired with a total acquisition time of 4 min.

Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge.

Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be challenging due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, an initial set of training data is generally needed for constructing priors or for training. Furthermore, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provided 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results showed that the performance of CT WHS was generally better than that of MRI WHS. The segmentation of the substructures for different categories of patients could present different levels of challenge due to the difference in imaging and variations of heart shapes. The deep learning (DL)-based methods demonstrated great potential, though several of them reported poor results in the blinded evaluation. Their performance could vary greatly across different network structures and training strategies. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated good performance, though the accuracy and computational efficiency could be limited. The challenge, including provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mmwhs/).

Automated age estimation from MRI volumes of the hand.

Highly relevant for both clinical and legal medicine applications, the established radiological methods for estimating unknown age in children and adolescents are based on visual examination of bone ossification in X-ray images of the hand. Our group has initiated the development of fully automatic age estimation methods from 3D MRI scans of the hand, in order to simultaneously overcome the problems of the radiological methods including (1) exposure to ionizing radiation, (2) necessity to define new, MRI specific staging systems, and (3) subjective influence of the examiner. The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation. Based on this theoretical background, we comprehensively evaluate machine learning methods (random forests, deep convolutional neural networks) with different simplifications of the image information used as an input for learning. Trained on a large dataset of 328 MR images, we compare the performance of the different input strategies and demonstrate unprecedented results. For estimating biological age, we obtain a mean absolute error of 0.37 ±â€¯0.51 years for the age range of the subjects  ≤  18 years, i.e. where bone ossification has not yet saturated. Finally, we validate our findings by adapting our best performing method to 2D images and applying it to a publicly available dataset of X-ray images, showing that we are in line with the state-of-the-art automatic methods for this task.

Segmenting and tracking cell instances with cosine embeddings and recurrent hourglass networks.

Differently to semantic segmentation, instance segmentation assigns unique labels to each individual instance of the same object class. In this work, we propose a novel recurrent fully convolutional network architecture for tracking such instance segmentations over time, which is highly relevant, e.g., in biomedical applications involving cell growth and migration. Our network architecture incorporates convolutional gated recurrent units (ConvGRU) into a stacked hourglass network to utilize temporal information, e.g., from microscopy videos. Moreover, we train our network with a novel embedding loss based on cosine similarities, such that the network predicts unique embeddings for every instance throughout videos, even in the presence of dynamic structural changes due to mitosis of cells. To create the final tracked instance segmentations, the pixel-wise embeddings are clustered among subsequent video frames by using the mean shift algorithm. After showing the performance of the instance segmentation on a static in-house dataset of muscle fibers from H&E-stained microscopy images, we also evaluate our proposed recurrent stacked hourglass network regarding instance segmentation and tracking performance on six datasets from the ISBI celltracking challenge, where it delivers state-of-the-art results.

Automatic Age Estimation and Majority Age Classification From Multi-Factorial MRI Data.

Age estimation from radiologic data is an important topic both in clinical medicine as well as in forensic applications, where it is used to assess unknown chronological age or to discriminate minors from adults. In this paper, we propose an automatic multi-factorial age estimation method based on MRI data of hand, clavicle, and teeth to extend the maximal age range from up to 19 years, as commonly used for age assessment based on hand bones, to up to 25 years, when combined with clavicle bones and wisdom teeth. Fusing age-relevant information from all three anatomical sites, our method utilizes a deep convolutional neural network that is trained on a dataset of 322 subjects in the age range between 13 and 25 years, to achieve a mean absolute prediction error in regressing chronological age of 1.01±0.74 years. Furthermore, when used for majority age classification, we show that a classifier derived from thresholding our regression-based predictor is better suited than a classifier directly trained with a classification loss, especially when taking into account that those cases of minors being wrongly classified as adults need to be minimized. In conclusion, we overcome the limitations of the multi-factorial methods currently used in forensic practice, i.e., dependence on ionizing radiation, subjectivity in quantifying age-relevant information, and lack of an established approach to fuse this information from individual anatomical sites.

Integrating spatial configuration into heatmap regression based CNNs for landmark localization.

In many medical image analysis applications, only a limited amount of training data is available due to the costs of image acquisition and the large manual annotation effort required from experts. Training recent state-of-the-art machine learning methods like convolutional neural networks (CNNs) from small datasets is a challenging task. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the overall need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) learns this simplification due to multiplying the heatmap predictions of its two components and by training the network in an end-to-end manner. Thus, the SCN dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the spatial configuration of landmarks. In our extensive experimental evaluation, we show that the proposed SCN outperforms related methods in terms of landmark localization error on a variety of size-limited 2D and 3D landmark localization datasets, i.e., hand radiographs, lateral cephalograms, hand MRIs, and spine CTs.

Quantitative CT-derived vessel metrics in idiopathic pulmonary fibrosis: A structure-function study.

BACKGROUND AND OBJECTIVE: This study aimed to investigate whether quantitative lung vessel morphology determined by a new fully automated algorithm is associated with functional indices in idiopathic pulmonary fibrosis (IPF). METHODS: A total of 152 IPF patients had vessel volume, density, tortuosity and heterogeneity quantified from computed tomography (CT) images by a fully automated algorithm. Separate quantitation of vessel metrics in pulmonary arteries and veins was performed in 106 patients. Results were evaluated against readouts from lung function tests. RESULTS: Normalized vessel volume expressed as a percentage of total lung volume was moderately correlated with functional indices on univariable linear regression analysis: forced vital capacity (R2 = 0.27, P < 1 × 10-6 ), diffusion capacity for carbon monoxide (DLCO ; R2 = 0.12, P = 3 × 10-5 ), total lung capacity (TLC; R2 = 0.45, P < 1 × 10-6 ) and composite physiologic index (CPI; R2 = 0.28, P < 1 × 10-6 ). Normalized vessel volume was correlated with vessel density but not with vessel heterogeneity. Quantitatively derived vessel metrics (and artery and vein subdivision scores) were not significantly linked with the transfer factor for carbon monoxide (KCO ), and only weakly with DLCO . On multivariable linear regression analysis, normalized vessel volume and vessel heterogeneity were independently linked with DLCO , TLC and CPI indicating that they capture different aspects of lung damage. Artery-vein separation provided no additional information beyond that captured in the whole vasculature. CONCLUSION: Our study confirms previous observations of links between vessel volume and functional measures of disease severity in IPF using a new vessel quantitation tool. Additionally, the new tool shows independent linkages of normalized vessel volume and vessel heterogeneity with functional indices. Quantitative vessel metrics do not appear to reflect vasculopathic damage in IPF.

Healthy Lung Vessel Morphology Derived From Thoracic Computed Tomography.

Knowledge of the lung vessel morphology in healthy subjects is necessary to improve our understanding about the functional network of the lung and to recognize pathologic deviations beyond the normal inter-subject variation. Established values of normal lung morphology have been derived from necropsy material of only very few subjects. In order to determine morphologic readouts from a large number of healthy subjects, computed tomography pulmonary angiography (CTPA) datasets, negative for pulmonary embolism, and other thoracic pathologies, were analyzed using a fully-automatic, in-house developed artery/vein separation algorithm. The number, volume, and tortuosity of the vessels in a diameter range between 2 and 10 mm were determined. Visual inspection of all datasets was used to exclude subjects with poor image quality or inadequate artery/vein separation from the analysis. Validation of the algorithm was performed manually by a radiologist on randomly selected subjects. In 123 subjects (men/women: 55/68), aged 59 ± 17 years, the median overlap between visual inspection and fully-automatic segmentation was 94.6% (69.2-99.9%). The median number of vessel segments in the ranges of 8-10, 6-8, 4-6, and 2-4 mm diameter was 9, 34, 134, and 797, respectively. Number of vessel segments divided by the subject's lung volume was 206 vessels/L with arteries and veins contributing almost equally. In women this vessel density was about 15% higher than in men. Median arterial and venous volumes were 1.52 and 1.54% of the lung volume, respectively. Tortuosity was best described with the sum-of-angles metric and was 142.1 rad/m (138.3-144.5 rad/m). In conclusion, our fully-automatic artery/vein separation algorithm provided reliable measures of pulmonary arteries and veins with respect to age and gender. There was a large variation between subjects in all readouts. No relevant dependence on age, gender, or vessel type was observed. These data may provide reference values for morphometric analysis of lung vessels.

Integrated computer-aided forensic case analysis, presentation, and documentation based on multimodal 3D data.

Three-dimensional (3D) crime scene documentation using 3D scanners and medical imaging modalities like computed tomography (CT) and magnetic resonance imaging (MRI) are increasingly applied in forensic casework. Together with digital photography, these modalities enable comprehensive and non-invasive recording of forensically relevant information regarding injuries/pathologies inside the body and on its surface. Furthermore, it is possible to capture traces and items at crime scenes. Such digitally secured evidence has the potential to similarly increase case understanding by forensic experts and non-experts in court. Unlike photographs and 3D surface models, images from CT and MRI are not self-explanatory. Their interpretation and understanding requires radiological knowledge. Findings in tomography data must not only be revealed, but should also be jointly studied with all the 2D and 3D data available in order to clarify spatial interrelations and to optimally exploit the data at hand. This is technically challenging due to the heterogeneous data representations including volumetric data, polygonal 3D models, and images. This paper presents a novel computer-aided forensic toolbox providing tools to support the analysis, documentation, annotation, and illustration of forensic cases using heterogeneous digital data. Conjoint visualization of data from different modalities in their native form and efficient tools to visually extract and emphasize findings help experts to reveal unrecognized correlations and thereby enhance their case understanding. Moreover, the 3D case illustrations created for case analysis represent an efficient means to convey the insights gained from case analysis to forensic non-experts involved in court proceedings like jurists and laymen. The capability of the presented approach in the context of case analysis, its potential to speed up legal procedures and to ultimately enhance legal certainty is demonstrated by introducing a number of representative forensic cases.

Reducing acquisition time for MRI-based forensic age estimation.

Radiology-based estimation of a living person's unknown age has recently attracted increasing attention due to large numbers of undocumented immigrants entering Europe. To avoid the application of X-ray-based imaging techniques, magnetic resonance imaging (MRI) has been suggested as an alternative imaging modality. Unfortunately, MRI requires prolonged acquisition times, which potentially represents an additional stressor for young refugees. To eliminate this shortcoming, we investigated the degree of reduction in acquisition time that still led to reliable age estimates. Two radiologists randomly assessed original images and two sets of retrospectively undersampled data of 15 volunteers (N = 45 data sets) applying an established radiological age estimation method to images of the hand and wrist. Additionally, a neural network-based age estimation method analyzed four sets of further undersampled images from the 15 volunteers (N = 105 data sets). Furthermore, we compared retrospectively undersampled and acquired undersampled data for three volunteers. To assess reliability with increasing degree of undersampling, intra-rater and inter-rater agreement were analyzed computing signed differences and intra-class correlation. While our findings have to be confirmed by a larger prospective study, the results from both radiological and automatic age estimation showed that reliable age estimation was still possible for acquisition times of 15 seconds.

Integrating geometric configuration and appearance information into a unified framework for anatomical landmark localization.

In approaches for automatic localization of multiple anatomical landmarks, disambiguation of locally similar structures as obtained by locally accurate candidate generation is often performed by solely including high level knowledge about geometric landmark configuration. In our novel localization approach, we propose to combine both image appearance information and geometric landmark configuration into a unified random forest framework integrated into an optimization procedure that iteratively refines joint landmark predictions by using the coordinate descent algorithm. Depending on how strong multiple landmarks are correlated in a specific localization task, this integration has the benefit that it remains flexible in deciding whether appearance information or the geometric configuration of multiple landmarks is the stronger cue for solving a localization problem both accurately and robustly. Furthermore, no preliminary choice on how to encode a graphical model describing landmark configuration has to be made. In an extensive evaluation on five challenging datasets involving different 2D and 3D imaging modalities, we show that our proposed method is widely applicable and delivers state-of-the-art results when compared to various other related methods.

Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization.

Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN) for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses.

Forensic age estimation by morphometric analysis of the manubrium from 3D MR images.

Forensic age estimation research based on skeletal structures focuses on patterns of growth and development using different bones. In this work, our aim was to study growth-related evolution of the manubrium in living adolescents and young adults using magnetic resonance imaging (MRI), which is an image acquisition modality that does not involve ionizing radiation. In a first step, individual manubrium and subject features were correlated with age, which confirmed a statistically significant change of manubrium volume (Mvol:p<0.01, R2¯=0.50) and surface area (Msur:p<0.01, R2¯=0.53) for the studied age range. Additionally, shapes of the manubria were for the first time investigated using principal component analysis. The decomposition of the data in principal components allowed to analyse the contribution of each component to total shape variation. With 13 principal components, ∼96% of shape variation could be described (Mshp:p<0.01, R2¯=0.60). Multiple linear regression analysis modelled the relationship between the statistically best correlated variables and age. Models including manubrium shape, volume or surface area divided by the height of the subject (Y∼MshpMsur/Sh:p<0.01, R2¯=0.71; Y∼MshpMvol/Sh:p<0.01, R2¯=0.72) presented a standard error of estimate of two years. In order to estimate the accuracy of these two manubrium-based age estimation models, cross validation experiments predicting age on held-out test sets were performed. Median absolute difference of predicted and known chronological age was 1.18 years for the best performing model (Y∼MshpMsur/Sh:p<0.01, Rp2=0.67). In conclusion, despite limitations in determining legal majority age, manubrium morphometry analysis presented statistically significant results for skeletal age estimation, which indicates that this bone structure may be considered as a new candidate in multi-factorial MRI-based age estimation.