Automated age estimation of young individuals based on 3D knee MRI using deep learning

Artificial intelligence in the practice of forensic medicine: a scoping review

Forensic medicine is a thriving application field for artificial intelligence (AI). Indeed, AI applications intended to forensic pathologists or forensic physicians have emerged since the last decade. For example, AI models were developed to help estimate the biological age of migrants or human remains. However, the uses of AI applications by forensic pathologists or physicians and their levels of integration in medicolegal practices are not well described yet. Therefore, a scoping review was conducted on PubMed, ScienceDirect, and Scopus databases. This review included articles that mention any AI application used by forensic pathologists or physicians in practice or any AI model applied in one expertise field of the forensic pathologist or physician. Articles in other languages than English or French or dealing mainly with complementary analyses handled by experts who are not forensic pathologists or physicians or with AI to analyze data for research purposes in forensic medicine were excluded from this review. All the relevant information was retrieved in each article from a grid analysis derived and adapted from the TRIPOD checklist. This review included 35 articles and revealed that AI applications are developed in thanatology and in clinical forensic medicine. However, those applications seem to mainly remain in research and development stages. Indeed, the use of AI applications by forensic pathologists or physicians is not actual due to issues discussed in this article. Finally, the integration of AI in daily medicolegal practice involves not only forensic pathologists or physicians but also legal professionals.

Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics

Bone age assessment (BAA) is a crucial task in clinical, forensic, and athletic fields. Since traditional age estimation methods are suffered from potential radiation damage, this study aimed to develop and evaluate a deep learning radiomics method based on multiparametric knee MRI for noninvasive and automatic BAA. This retrospective study enrolled 598 patients (age range,10.00-29.99 years) who underwent MR examinations of the knee joint (T1/T2*/PD-weighted imaging). Three-dimensional convolutional neural networks (3D CNNs) were trained to extract and fuse multimodal and multiscale MRI radiomic features for age estimation and compared to traditional machine learning models based on hand-crafted features. The age estimation error was greater in individuals aged 25-30 years; thus, this method may not be suitable for individuals over 25 years old. In the test set aged 10-25 years (n = 95), the 3D CNN (a fusion of T1WI, T2*WI, and PDWI) demonstrated the lowest mean absolute error of 1.32 ± 1.01 years, which is higher than that of other MRI modalities and the hand-crafted models. In the classification for 12-, 14-, 16-, and 18- year thresholds, accuracies and the areas under the ROC curves were all over 0.91 and 0.96, which is similar to the manual methods. Visualization of important features showed that 3D CNN estimated age by focusing on the epiphyseal plates. The deep learning radiomics method enables non-invasive and automated BAA from multimodal knee MR images. The use of 3D CNN and MRI-based radiomics has the potential to assist radiologists or medicolegists in age estimation.

Age Estimation Using Machine Learning Algorithms with Parameters Obtained from X-ray Images of the Calcaneus

BACKGROUND

Determination of bone age is a critical issue for forensics, surgery, and basic sciences.

AIM

This study aims to estimate age with high accuracy and precision using Machine Learning (ML) algorithms with parameters obtained from calcaneus x-ray images of healthy individuals.

METHOD

The study was carried out by retrospectively examining the foot X-ray images of 341 people aged 18-65 years. Maximum width of the calcaneus (MW), body width (BW), maximum length (MAXL), minimum length (MINL), facies articularis cuboidea height (FACH), maximum height (MAXH), and tuber calcanei width (TKW) parameters were measured from the images. The measurements were then grouped as 20-45 years of age, 46-64 years of age, 65 and older, and age estimation was made by using these at the input of ML models.

RESULTS

As a result of the ML input of the measurements obtained, a 0.85 Accuracy (Acc) rate was obtained with the Extra Tree Classifier algorithm. The accuracy rate of other algorithms was found to vary between 0.78 and 0.82. The contribution of parameters to the overall result was evaluated by using the shapley additive explanations (SHAP) analyzer of Random Forest algorithm and the MAXH parameter was found to have the highest contribution in age estimation.

CONCLUSIONS

As a result of our study, calcaneus bone was found to have high accuracy and precision in age estimations.

Radiological age assessment based on clavicle ossification in CT: enhanced accuracy through deep learning

BACKGROUND

Radiological age assessment using reference studies is inherently limited in accuracy due to a finite number of assignable skeletal maturation stages. To overcome this limitation, we present a deep learning approach for continuous age assessment based on clavicle ossification in computed tomography (CT).

METHODS

Thoracic CT scans were retrospectively collected from the picture archiving and communication system. Individuals aged 15.0 to 30.0 years examined in routine clinical practice were included. All scans were automatically cropped around the medial clavicular epiphyseal cartilages. A deep learning model was trained to predict a person's chronological age based on these scans. Performance was evaluated using mean absolute error (MAE). Model performance was compared to an optimistic human reader performance estimate for an established reference study method.

RESULTS

The deep learning model was trained on 4,400 scans of 1,935 patients (training set: mean age = 24.2 years ± 4.0, 1132 female) and evaluated on 300 scans of 300 patients with a balanced age and sex distribution (test set: mean age = 22.5 years ± 4.4, 150 female). Model MAE was 1.65 years, and the highest absolute error was 6.40 years for females and 7.32 years for males. However, performance could be attributed to norm-variants or pathologic disorders. Human reader estimate MAE was 1.84 years and the highest absolute error was 3.40 years for females and 3.78 years for males.

CONCLUSIONS

We present a deep learning approach for continuous age predictions using CT volumes highlighting the medial clavicular epiphyseal cartilage with performance comparable to the human reader estimate.

Brain structure ages-A new biomarker for multi-disease classification

Age is an important variable to describe the expected brain's anatomy status across the normal aging trajectory. The deviation from that normative aging trajectory may provide some insights into neurological diseases. In neuroimaging, predicted brain age is widely used to analyze different diseases. However, using only the brain age gap information (i.e., the difference between the chronological age and the estimated age) can be not enough informative for disease classification problems. In this paper, we propose to extend the notion of global brain age by estimating brain structure ages using structural magnetic resonance imaging. To this end, an ensemble of deep learning models is first used to estimate a 3D aging map (i.e., voxel-wise age estimation). Then, a 3D segmentation mask is used to obtain the final brain structure ages. This biomarker can be used in several situations. First, it enables to accurately estimate the brain age for the purpose of anomaly detection at the population level. In this situation, our approach outperforms several state-of-the-art methods. Second, brain structure ages can be used to compute the deviation from the normal aging process of each brain structure. This feature can be used in a multi-disease classification task for an accurate differential diagnosis at the subject level. Finally, the brain structure age deviations of individuals can be visualized, providing some insights about brain abnormality and helping clinicians in real medical contexts.

Third Molar Eruption in Dental Panoramic Radiographs as a Feature for Forensic Age Assessment-Presentation of a New Non-Staging Method Based on Measurements

The evaluation of third molar eruption in dental panoramic radiographs (DPRs) constitutes an evidence-based approach for forensic age assessment in living individuals. Existing methodologies involve staging morphological radiographic findings and comparing them to reference populations. Conversely, the existing literature presents an alternative method where the distance between third molars and the occlusal plane is measured on dental plaster models. The aim of this study was to adapt this measurement principle for DPRs and to determine correlation between eruption and chronological age. A total of 423 DPRs, encompassing 220 females and 203 males aged 15 to 25 years, were examined, including teeth 38 [FDI] and 48. Two independent examiners conducted the measurements, with one examiner providing dual assessments. Ultimately, a quotient was derived by comparing orthogonal distances from the mesial cementoenamel junctions of the second and third molars to a simplified radiological occlusal plane. This quotient was subsequently correlated with the individual's age. We estimated correlations between age and quotients, as well as inter- and intra-rater reliability. Correlation coefficients (Spearman's rho) between measurements and individuals' ages ranged from 0.555 to 0.597, conditional on sex and tooth. Intra-rater agreement (Krippendorf's alpha) ranged from 0.932 to 0.991, varying according to the tooth and sex. Inter-rater agreement ranged from 0.984 to 0.992, with distinctions drawn for different teeth and sex. Notably, all observer agreement values fell within the "very good" range. In summary, assessing the distance of third molars from a simplified occlusal plane in DPRs emerges as a new and promising method for evaluating eruption status in forensic age assessment. Subsequent reference studies should validate these findings.

Management of anterior cruciate ligament tears in Tanner stage 1 and 2 children: a narrative review and treatment algorithm guided by ACL tear location

The incidence of anterior cruciate ligament (ACL) tears in skeletally immature patients has acutely increased over the last 20 years, yet there is no consensus on a single "best treatment." Selection of an optimal treatment is critical and based on individual circumstances; consequently, we propose a treatment-selection algorithm based on skeletal development, ACL tear location, type, and quality, as well as parental perspective in order to facilitate the decision-making process. We combined our surgical group's extensive case histories of ACL tear management in Tanner Stage 1 and 2 patients with those in the literature to form a consolidated data base. For each case the diagnostic phase, communication with patient and parents, treatment choice(s), selected surgical techniques and rehabilitation schedule were critically analyzed and compared for patient outcomes. MRI-imaging and intraoperative tissue quality assessment were preeminent in importance for selection of the optimal treatment strategy. Considerations for selecting an optimal treatment included: associated lesions, the child/patient and parent(s)' well-informed and counseled consent, biological potential, and the potential for successful ACL preservative surgery. Complete ACL tears were evaluated according to tear-location. In type I and II ACL tears with remaining good tissue quality, we propose primary ACL repair. In type III and IV ACL tears we propose physeal-sparing reconstruction with an iliotibial band graft. Finally, in the case of a type V ACL tear, we propose that the best treatment be based on the Meyers-McKeever classification. We present a facile decision-making algorithm for ACL management in pediatric patients based on specific elements of tissue damage and status.

Magnetic resonance imaging of the knee for chronological age estimation-a systematic review

INTRODUCTION

Radiographs of the hand and teeth are frequently used for medical age assessment, as skeletal and dental maturation correlates with chronological age. These methods have been criticized for their lack of precision, and magnetic resonance imaging (MRI) of the knee has been proposed as a more accurate method. The aim of this systematic review is to explore the scientific and statistical evidence for medical age estimation based on skeletal maturation as assessed by MRI of the knee.

MATERIALS AND METHODS

A systematic review was conducted that included studies published before April 2021 on living individuals between 8 and 30 years old, with presumptively healthy knees for whom the ossification stages had been evaluated using MRI. The correlation between "mature knee" and chronological age and the risk of misclassifying a child as an adult and vice versa was calculated.

RESULTS

We found a considerable heterogeneity in the published studies -in terms of study population, MRI protocols, and grading systems used. There is a wide variation in the correlation between maturation stage and chronological age.

CONCLUSION

Data from published literature is deemed too heterogenous to support the use of MRI of the knee for chronological age determination. Further, it is not possible to assess the sensitivity, specificity, negative predictive value, or positive predictive value for the ability of MRI to determine whether a person is over or under 18 years old.

KEY POINTS

• There is an insufficient scientific basis for the use of magnetic resonance imaging of the knee in age determination by skeleton. • It is not possible to assess the predictive value of MRI of the knee to determine whether a person is over or under 18 years of age.

DiatomNet v1.0: A novel approach for automatic diatom testing for drowning diagnosis in forensically biomedical application

BACKGROUND AND OBJECTIVE

Diatom testing is supportive for drowning diagnosis in forensic medicine. However, it is very time-consuming and labor-intensive for technicians to identify microscopically a handful of diatoms in sample smears, especially under complex observable backgrounds. Recently, we successfully developed a software, named DiatomNet v1.0 intended to automatically identify diatom frustules in a whole slide under a clear background. Here, we introduced this new software and performed a validation study to elucidate how DiatomNet v1.0 improved its performance with the influence of visible impurities.

METHODS

DiatomNet v1.0 has an intuitive, user-friendly and easy-to-learn graphical user interface (GUI) built in the Drupal and its core architecture for slide analysis including a convolutional neural network (CNN) is written in Python language. The build-in CNN model was evaluated for diatom identification under very complex observable backgrounds with mixtures of common impurities, including carbon pigments and sand sediments. Compared to the original model, the enhanced model following optimization with limited new datasets was evaluated systematically by independent testing and random control trials (RCTs).

RESULTS

In independent testing, the original DiatomNet v1.0 was moderately affected, especially when higher densities of impurities existed, and achieved a low recall of 0.817 and F1 score of 0.858 but good precision of 0.905. Following transfer learning with limited new datasets, the enhanced version had better results, with recall and F1 score values of 0.968. A comparative study on real slides showed that the upgraded DiatomNet v1.0 obtained F1 scores of 0.86 and 0.84 for carbon pigment and sand sediment, respectively, slightly worse than manual identification (carbon pigment: 0.91; sand sediment: 0.86), but much less time was needed.

CONCLUSIONS

The study verified that forensic diatom testing with aid of DiatomNet v1.0 is much more efficient than traditionally manual identification even under complex observable backgrounds. In terms of forensic diatom testing, we proposed a suggested standard on build-in model optimization and evaluation to strengthen the software's generalization in potentially complex conditions.

Applications of artificial intelligence in forensic sciences: Current potential benefits, limitations and perspectives

In recent years, new studies based on artificial intelligence (AI) have been conducted in the forensic field, posing new challenges and demonstrating the advantages and disadvantages of using AI methodologies to solve forensic well-known problems. Specifically, AI technology has tried to overcome the human subjective bias limitations of the traditional approach of the forensic sciences, which include sex prediction and age estimation from morphometric measurements in forensic anthropology or evaluating the third molar stage of development in forensic odontology. Likewise, AI has been studied as an assisting tool in forensic pathology for a quick and easy identification of the taxonomy of diatoms. The present systematic review follows the PRISMA 2020 statements and aims to explore an emerging topic that has been poorly analyzed in the forensic literature. Benefits, limitations, and forensic implications concerning AI are therefore highlighted, by providing an extensive critical review of its current applications on forensic sciences as well as its future directions. Results are divided into 5 subsections which included forensic anthropology, forensic odontology, forensic pathology, forensic genetics, and other forensic branches. The discussion offers a useful instrument to investigate the potential benefits of AI in the forensic fields as well as to point out the existing open questions and issues concerning its application on real-life scenarios. Procedural notes and technical aspects are also provided to the readers.

[Age assessment using CT of knee joint and neural network technologies]

Age assessment of living persons plays an important role in clinical and sports medicine, as well as in law practice. Traditional methods have a number of problems: age restrictions, technical difficulties of visualization, low reproducibility and subjectivity of estimation. The proposed approach, which implies the use of multispiral computed tomography (MSCT) and database mining, will eliminate these drawbacks and improve the estimation of age. The aim of the study was to investigate the use of deep learning algorithms to classify the age groups (with a threshold level of 18 years) for CT images of knee joint. The study included 455 MSCT images of the knee joint of male and female subjects aged from 13 to 24. The method included score assessment of the distal femur's epiphyseal synostosis stages, tibia and fibula proximal epiphyses and a preliminary statistical analysis of correlations between age and stages of synostosis. The challenge of binary classification of target age groups with the use of convolutional neural networks was implemented at the second phase of the trial. Various architectures of convolutional neural networks and their ensembles were tested. The result of the study showed that the total score of epiphyseal synostosis has the highest correlation with the age (r=0.88). The proposed method of chronological age assessment on the basis of the knee area CT images research using deep learning algorithms demonstrated a good result. The classification accuracy (threshold level of 18 years) was 0.86.

Ageing and degeneration analysis using ageing-related dynamic attention on lateral cephalometric radiographs

With the increase of the ageing in the world’s population, the ageing and degeneration studies of physiological characteristics in human skin, bones, and muscles become important topics. Research on the ageing of bones, especially the skull, are paid much attention in recent years. In this study, a novel deep learning method representing the ageing-related dynamic attention (ARDA) is proposed. The proposed method can quantitatively display the ageing salience of the bones and their change patterns with age on lateral cephalometric radiographs images (LCR) images containing the craniofacial and cervical spine. An age estimation-based deep learning model based on 14142 LCR images from 4 to 40 years old individuals is trained to extract ageing-related features, and based on these features the ageing salience maps are generated by the Grad-CAM method. All ageing salience maps with the same age are merged as an ARDA map corresponding to that age. Ageing salience maps show that ARDA is mainly concentrated in three regions in LCR images: the teeth, craniofacial, and cervical spine regions. Furthermore, the dynamic distribution of ARDA at different ages and instances in LCR images is quantitatively analyzed. The experimental results on 3014 cases show that ARDA can accurately reflect the development and degeneration patterns in LCR images.

Application of medical imaging methods and artificial intelligence in tissue engineering and organ-on-a-chip

Organ-on-a-chip (OOC) is a new type of biochip technology. Various types of OOC systems have been developed rapidly in the past decade and found important applications in drug screening and precision medicine. However, due to the complexity in the structure of both the chip-body itself and the engineered-tissue inside, the imaging and analysis of OOC have still been a big challenge for biomedical researchers. Considering that medical imaging is moving towards higher spatial and temporal resolution and has more applications in tissue engineering, this paper aims to review medical imaging methods, including CT, micro-CT, MRI, small animal MRI, and OCT, and introduces the application of 3D printing in tissue engineering and OOC in which medical imaging plays an important role. The achievements of medical imaging assisted tissue engineering are reviewed, and the potential applications of medical imaging in organoids and OOC are discussed. Moreover, artificial intelligence - especially deep learning - has demonstrated its excellence in the analysis of medical imaging; we will also present the application of artificial intelligence in the image analysis of 3D tissues, especially for organoids developed in novel OOC systems.

Inferring pediatric knee skeletal maturity from MRI using deep learning

PURPOSE

Many children who undergo MR of the knee to evaluate traumatic injury may not undergo a separate dedicated evaluation of their skeletal maturity, and we wished to investigate how accurately skeletal maturity could be automatically inferred from knee MRI using deep learning to offer this additional information to clinicians.

MATERIALS AND METHODS

Retrospective data from 894 studies from 783 patients were obtained (mean age 13.1 years, 47% female). Coronal and sagittal sequences that were T1/PD-weighted were included and resized to 224 × 224 pixels. Data were divided into train (n = 673), tune (n = 48), and test (n = 173) sets, and children were separated across sets. The chronologic age was predicted using deep learning approaches based on a long short-term memory (LSTM) model, which took as input DenseNet-121-extracted features from all T1/PD coronal and sagittal slices. Each test case was manually assigned a bone age by two radiology residents using a reference atlas provided by Pennock and Bomar. The patient's age served as ground truth.

RESULTS

The error of the model's predictions for chronological age was not significantly different from that of radiology residents (model M.S.E. 1.30 vs. resident 0.99, paired t-test = 1.47, p = 0.14). Pearson correlation between model and resident prediction of chronologic age was 0.96 (p < 0.001).

CONCLUSION

A deep learning-based approach demonstrated ability to infer skeletal maturity from knee MR sequences that was not significantly different from resident performance and did so in less than 2% of the time required by a human expert. This may offer a method for automatically evaluating lower extremity skeletal maturity automatically as part of every MR examination.

Deep Learning-Based Intelligent Robot in Sentencing

This work aims to explore the application of deep learning-based artificial intelligence technology in sentencing, to promote the reform and innovation of the judicial system. First, the concept and the principles of sentencing are introduced, and the deep learning model of intelligent robot in trials is proposed. According to related concepts, the issues that need to be solved in artificial intelligence sentencing based on deep learning are introduced. The deep learning model is integrated into the intelligent robot system, to assist in the sentencing of cases. Finally, an example is adopted to illustrate the feasibility of the intelligent robot under deep learning in legal sentencing. The results show that the general final trial periods for cases of traffic accidents, copyright information, trademark infringement, copyright protection, and theft are 1,049, 796, 663, 847, and 201 days, respectively; while the final trial period under artificial intelligence evaluation based on the restricted Boltzmann deep learning model is 458, 387, 376, 438, and 247 days, respectively. The accuracy of trials is above 92%, showing a high application value. It can be observed that expect theft cases, the final trial period for others cases has been effectively reduced. The intelligent robot assistance under the restricted Boltzmann deep learning model can shorten the trial period of cases. The deep learning intelligent robot has a certain auxiliary role in legal sentencing, and this outcome provides a theoretical basis for the research of artificial intelligence technology in legal sentencing.

Enabling Legal Risk Management Model for International Corporation with Deep Learning and Self Data Mining

In uncertain times, risk management is critical in keeping companies from acting rashly and wrongly, allowing them to become more flexible and resilient. International cooperative production project investment and operational risks are different from domestic projects. It has a larger likelihood of occurrence, severe damage ramifications, and greater difficulty in prevention and control. As a result, companies must develop a scientific, logical, and comprehensive risk management system and procedure when "reaching out" to perform international joint production projects. We utilize machine learning (ML) to build a legal risk assessment model for international cooperative production projects, evaluate its validity, divide it into five risk categories, and suggest countermeasures for the risk variables discovered at each risk level in this work. The output of a single classifier is then fused using an SDM (self-organizing data mining) approach at the decision level, resulting in a multiclassifier early-warning model. In the context of the sustainable development goals, this methodology also allows for a sustainability assessment through risk evaluation. The experimental results show that the MCFM-SDM model outperforms a single classifier and other MCFMs in terms of early warning accuracy and stability, confirming the model's use and superiority.

Forensic age prediction and age classification for critical age thresholds via 3.0T magnetic resonance imaging of the knee in the Chinese Han population

OBJECTIVES

To assess the performance of knee MRI for forensic age prediction and classification for 12-, 14-, 16-, and 18-year thresholds.

METHODS

The ossification stages of distal femoral epiphyses and proximal tibial epiphyses were assessed using an integrated staging system by Schmeling et al. and Kellinghaus et al. for knee 3.0T MRI with T1-weighted turbo spin-echo (T1-TSE) in sagittal orientation among 852 Chinese Han individuals (483 males and 369 females) aged 7-30 years. Regression models for age prediction were constructed and their performances were evaluated based on mean absolute deviation (MAD) values. In addition, the performances of age classification were assessed using receiver operating characteristic (ROC) analyses.

RESULTS

The intra- and inter-observer agreement levels were very good (κ > 0.80). The complete fusion of those two types of epiphyses took place before 18.0 years in our study participants. The minimum MAD values were 2.51 years (distal femur) and 2.69 years (proximal tibia) in males, and 2.75 years (distal femur) and 2.87 years (proximal tibia) in females. The specificity values of constructed prediction models were all above 90% for the 12-, 14-, and 16-year thresholds, compared to the 74.8-84.6% for the 18-year threshold. Better performances of age prediction and classification were observed in males by distal femoral epiphyses.

CONCLUSIONS

Ossification stages via 3.0T MRI of the knee with T1-TSE sequence using an integrated staging system could be a reliable noninvasive method for age prediction or for age classification for 12-, 14-, and 16-year thresholds, especially in males by distal femoral epiphyses. However, assessments based on the full bony fusion of the distal femoral epiphysis and proximal tibial epiphysis seemed not reliable for age classification for the 18-year threshold in the Chinese Han population.

Robust Estimation of the Chronological Age of Children and Adolescents Using Tooth Geometry Indicators and POD-GP

Determining the chronological age of children or adolescents is becoming an extremely necessary and important issue. Correct age-assessment methods are especially important in the process of international adoption and in the case of immigrants without valid documents confirming their identity. It is well known that traditional, analog methods widely used in clinical evaluation are burdened with a high error rate and are characterized by low accuracy. On the other hand, new digital approaches appear in medicine more and more often, which allow the increase of the accuracy of these estimates, and thus equip doctors with a tool for reliable estimation of the chronological age of children and adolescents. In this study, the work on a fast and effective metamodel is continued. Metamodels have one great advantage over all other analog and quasidigital methods—if they are well trained, a priori, on a representative set of samples, then in the age-assessment phase, results are obtained in a fraction of a second and with little error (reduced to ±7.5 months). In the here-proposed method, the standard deviation for each estimate is additionally obtained, which allows the assessment of the certainty of each result. In this study, 619 pantomographic photos of 619 patients (296 girls and 323 boys) of different ages were used. In the numerical procedure, on the other hand, a metamodel based on the Proper Orthogonal Decomposition (POD) and Gaussian processes (GP) were utilized. The accuracy of the trained model was up to 95%.

Pediatric age estimation from radiographs of the knee using deep learning

OBJECTIVES

Age estimation, especially in pediatric patients, is regularly used in different contexts ranging from forensic over medicolegal to clinical applications. A deep neural network has been developed to automatically estimate chronological age from knee radiographs in pediatric patients.

METHODS

In this retrospective study, 3816 radiographs of the knee from pediatric patients from a German population (acquired between January 2008 and December 2018) were collected to train a neural network. The network was trained to predict chronological age from the knee radiographs and was evaluated on an independent validation cohort of 423 radiographs (acquired between January 2019 and December 2020) and on an external validation cohort of 197 radiographs.

RESULTS

The model showed a mean absolute error of 0.86 ± 0.72 years and 0.9 ± 0.71 years on the internal and external validation cohorts, respectively. Separating age classes (< 14 years from ≥ 14 years and < 18 years from ≥ 18 years) showed AUCs between 0.94 and 0.98.

CONCLUSIONS

The chronological age of pediatric patients can be estimated with good accuracy from radiographs of the knee using a deep neural network.

KEY POINTS

• Radiographs of the knee can be used for age estimations in pediatric patients using a standard deep neural network. • The network showed a mean absolute error of 0.86 ± 0.72 years in an internal validation cohort and of 0.9 ± 0.71 years in an external validation cohort. • The network can be used to separate the age classes < 14 years from ≥ 14 years with an AUC of 0.97 and < 18 years from ≥ 18 years with an AUC of 0.94.

Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology

Artificial intelligence (AI) is playing an ever-increasing role in radiology (more so in the adult world than in pediatrics), to the extent that there are unfounded fears it will completely take over the role of the radiologist. In relation to musculoskeletal applications of AI in pediatric radiology, we are far from the time when AI will replace radiologists; even for the commonest application (bone age assessment), AI is more often employed in an AI-assist mode rather than an AI-replace or AI-extend mode. AI for bone age assessment has been in clinical use for more than a decade and is the area in which most research has been conducted. Most other potential indications in children (such as appendicular and vertebral fracture detection) remain largely in the research domain. This article reviews the areas in which AI is most prominent in relation to the pediatric musculoskeletal system, briefly summarizing the current literature and highlighting areas for future research. Pediatric radiologists are encouraged to participate as members of the research teams conducting pediatric radiology artificial intelligence research.

A probability model for assessing age relative to the 18-year old threshold based on magnetic resonance imaging of the knee combined with radiography of third molars in the lower jaw

OBJECTIVE

This study aims to generate a statistical model based on magnetic resonance imaging of the knee and radiography of third molars in the lower jaw, for assessing age relative to the 18-year old threshold.

METHODS

In total, 58 studies correlating knee or tooth development to age were assessed, 5 studies for knee and 7 studies for tooth were included in the statistical model. The relation between the development of the anatomical site, based on a binary system, and age were estimated using logistic regression. Separate meta-populations for knee and tooth were generated from the individual based data for men and women. A weighted estimate of probabilities was made by combining the probability densities for knee and tooth. Margin of errors for males and females in different age groups and knee and tooth maturity were calculated within the larger framework of transition analysis using a logit model as a base. Evidentiary values for combinations of knee and tooth maturity were evaluated with likelihood ratios.

RESULTS

For males, the sensitivity for the method was calculated to 0.78 (probability of correctly classifying adults), the specificity 0.90 (probability of correctly classifying minors), the negative predictive value 0.80 (proportion identified minors are minors) and the positive predictive value 0.89 (proportion identified adults are adults) indicating a model better at identifying minors than adults. The point at which half the female population has reached closed knee lies before the 18-year threshold, adding the knee as an indicator lowers specificity and increases sensitivity. The sensitivity when using tooth as an indicator for females is 0.24 and specificity 0.97, signifying few minors misclassified as adults but also a low probability of identifying adults. The negative predictive value for women when using tooth as the sole indicator is 0.56 and positive predictive value 0.88. Probabilities were calculated for males and females assuming a uniform age distribution between 15 and 21years. The calculated margin of error of minors classified as adults in a population between 15 and 21 years with the model was 11% for males and 12% for females. Further, the evidentiary value as well as margin of error vary for different combinations of knee and tooth maturity.

CONCLUSION

The statistical model based on the combination of MRI knee and radiography of mandibular third molars is a valid method to assess age relative to the 18-year old threshold when applied on males and of limited value in females.

Use of Advanced Artificial Intelligence in Forensic Medicine, Forensic Anthropology and Clinical Anatomy

Three-dimensional convolutional neural networks (3D CNN) of artificial intelligence (AI) are potent in image processing and recognition using deep learning to perform generative and descriptive tasks. Compared to its predecessor, the advantage of CNN is that it automatically detects the important features without any human supervision. 3D CNN is used to extract features in three dimensions where input is a 3D volume or a sequence of 2D pictures, e.g., slices in a cone-beam computer tomography scan (CBCT). The main aim was to bridge interdisciplinary cooperation between forensic medical experts and deep learning engineers, emphasizing activating clinical forensic experts in the field with possibly basic knowledge of advanced artificial intelligence techniques with interest in its implementation in their efforts to advance forensic research further. This paper introduces a novel workflow of 3D CNN analysis of full-head CBCT scans. Authors explore the current and design customized 3D CNN application methods for particular forensic research in five perspectives: (1) sex determination, (2) biological age estimation, (3) 3D cephalometric landmark annotation, (4) growth vectors prediction, (5) facial soft-tissue estimation from the skull and vice versa. In conclusion, 3D CNN application can be a watershed moment in forensic medicine, leading to unprecedented improvement of forensic analysis workflows based on 3D neural networks.

Zur Anwendbarkeit der dentalen Methode von Roberts et al. aus dem Jahr 2016 zum Nachweis der Vollendung des 18. Lebensjahres lebender Personen

Es sollte die Methode von Roberts et al. aus dem Jahr 2016 zum Nachweis der Vollendung des 18. Lebensjahres überprüft werden.

Dazu wurden 603 Orthopantomogramme (OPG) von 300 Frauen und 303 Männern im Alter von 16,01 bis 25,99 Jahren von 3 Untersuchern ausgewertet, wobei ein Hauptuntersucher alle OPGs zweimal begutachtet hat. Durch die 3 Untersucher wurde eine konsensuale Bestimmung für die Fälle vorgenommen, bei denen mindestens ein Untersucher ein Stadium zugeordnet hatte.

In 31 Fällen (11 Frauen, 20 Männer) konnte konsensuell ein Stadium bestimmt werden. Hauptursache für die Nichtauswertbarkeit war die nicht abgeschlossene Entwicklung des Zahnes 38 [FDI] (30,18 %), gefolgt von Karies, Restaurationen oder anderen Pathologien (20,56 %) und dem Fehlen des Zahnes 38 (19,57 %). Das Stadium „RCW‑C“ konnte bei den Frauen konsensual nicht, die Stadien „RCW‑B“ und „RCW‑C“ konnten bei den Männern nur 4‑mal (3x „RCW-C“, 1x „RCW-B“) bestimmt werden. Der Cohen’s-Kappa-Wert für die Binnenbeobachterübereinstimmung für die 47 Fälle, in denen der Hauptuntersucher in mindestens einem Durchgang ein Stadium zugeordnet hatte, lag im moderaten bzw. guten Bereich (Frauen: 0,44; Männer: 0,62). Der Fleiss’-Kappa-Wert für die Zwischenbeobachterübereinstimmung der 3 Untersucher für die 69 Fälle, bei denen mindestens ein Untersucher ein Stadium zugeordnet hatte, lag im mangelhaften Bereich (Frauen: 0,07; Männer: 0,11), wobei die 95%-Konfidenzintervalle für den Kappa-Wert auch die „0“ einschlossen.

Alle Personen, bei denen ein Stadium zugeordnet wurde, waren über 18 Jahre alt. Aktuell kann eine Anwendung der Methode nicht empfohlen werden. Es wird die Frage aufgeworfen, ob den Stadien eine allgemeingültige Entwicklungsabfolge zu Grunde zu liegt, da bei 30 Fällen der Befund nicht mit den Stadien in Deckung zu bringen war.

Tooth and Bone Parameters in the Assessment of the Chronological Age of Children and Adolescents Using Neural Modelling Methods

The analog methods used in the clinical assessment of the patient's chronological age are subjective and characterized by low accuracy. When using those methods, there is a noticeable discrepancy between the chronological age and the age estimated based on relevant scientific studies. Innovations in the field of information technology are increasingly used in medicine, with particular emphasis on artificial intelligence methods. The paper presents research aimed at developing a new, effective methodology for the assessment of the chronological age using modern IT methods. In this paper, a study was conducted to determine the features of pantomographic images that support the determination of metric age, and neural models were produced to support the process of identifying the age of children and adolescents. The whole conducted work was a new methodology of metric age assessment. The result of the conducted study is a set of 21 original indicators necessary for the assessment of the chronological age with the use of computer image analysis and neural modelling, as well as three non-linear models of radial basis function networks (RBF), whose accuracy ranges from 96 to 99%. The result of the research are three neural models that determine the chronological age.

Forensic age estimation based on magnetic resonance imaging of the proximal humeral epiphysis in Chinese living individuals

Forensic age estimation in living individuals is mainly based on radiological features, but direct radiography and computed tomography lead to a rise in ethical concerns due to radiation exposure. Thus, the contribution of magnetic resonance imaging (MRI) to age estimation of living individuals is a subject of ongoing research. In the current study, MRIs of shoulder were retrospectively collected from a modern Chinese Han population and data from 835 individuals (599 males and 236 females) in the age group 12 to 30 years were obtained. A staging technique based on (Schmidt et al. Int J Legal Med 121(4):321-324, 2007) and (Kellinghaus et al. Int J Legal Med 124(4):321-325, 2010) was used and all images were evaluated with T1-wieghted turbo spin echo (T1-TSE) sequence and T2-weighed fat suppression (T2-FS) sequence. One-sided images were assessed because data from both sides were considered coincidental, as no significant differences were found (P > 0.05). Two MRI sequences were evaluated separately and subsequently compared. Regression models and supportive vector classification (SVC) models were established accordingly. The intraobserver and interobserver agreement levels were good. Compared with T1-TSE sequence, the R² values of T2-FS sequence were generally higher, while the mean absolute deviation (MAD) values were slightly lower. For T2-FS sequence, the MAD value was 1.49 years in males and 2.19 years in females. With two MRI sequences incorporated, the SVC model obtained with 85.7% correctly classified minors and 96.2% correctly classified adults in males, while 83.3% and 98.0% respectively in females. In conclusion, T2-FS sequence may slightly outperform the T1-TSE sequence in shoulder MRI analysis for age estimation, while shoulder MRIs could be a reliable prediction indicator for the 18-year threshold and two MRI sequences incorporated are encouraged.

Age-dependent decrease in dental pulp cavity volume as a feature for age assessment: a comparative in vitro study using 9.4-T UTE-MRI and CBCT 3D imaging

Evaluation of secondary dentin formation is generally suitable for age assessment. We investigated the potential of modern magnetic resonance imaging (MRI) technology to visualize the dental pulp in direct comparison with cone beam computed tomography (CBCT). To this end, we examined 32 extracted human teeth (teeth 11–48 [FDI]) using 9.4-T ultrashort echo time (UTE)-MRI and CBCT (methods). 3D reconstruction was performed via both manual and semi-automatic segmentation (settings) for both methods in two runs by one examiner. Nine teeth were also examined by a second examiner. We evaluated the agreement between examiners, scan methods, and settings. CBCT was able to determine the pulp volume for all teeth. This was not possible for two teeth on MRI due to MRI artifacts. The mean pulp volume estimated by CBCT was consistently higher (~ 43%) with greater variability. With lower variability in its measurements, evaluation of pulp volume using the MRI method exhibited greater sensitivity to differences between settings (p = 0.016) and between examiners (p = 0.009). The interactions of single-rooted teeth and multi-rooted teeth and method or setting were not found to be significant. For examiner agreement, the mean pulp volumes were similar with overlapping measurements (ICC > 0.995). Suitable for use in age assessment is 9.4-T UTE-MRI with good reliability and lower variation than CBCT. For MRI, manual segmentation is necessary due to a more detailed representation of the interior of the pulp cavity. Since determination of pulp volume is expected to be systematically larger using CBCT, method-specific reference values are indispensable for practical age assessment procedures. The results should be verified under in vivo conditions in the future.

Automated age estimation of young individuals based on 3D knee MRI using deep learning

Age estimation is a crucial element of forensic medicine to assess the chronological age of living individuals without or lacking valid legal documentation. Methods used in practice are labor-intensive, subjective, and frequently comprise radiation exposure. Recently, also non-invasive methods using magnetic resonance imaging (MRI) have evaluated and confirmed a correlation between growth plate ossification in long bones and the chronological age of young subjects. However, automated and user-independent approaches are required to perform reliable assessments on large datasets. The aim of this study was to develop a fully automated and computer-based method for age estimation based on 3D knee MRIs using machine learning. The proposed solution is based on three parts: image-preprocessing, bone segmentation, and age estimation. A total of 185 coronal and 404 sagittal MR volumes from Caucasian male subjects in the age range of 13 and 21 years were available. The best result of the fivefold cross-validation was a mean absolute error of 0.67 ± 0.49 years in age regression and an accuracy of 90.9%, a sensitivity of 88.6%, and a specificity of 94.2% in classification (18-year age limit) using a combination of convolutional neural networks and tree-based machine learning algorithms. The potential of deep learning for age estimation is reflected in the results and can be further improved if it is trained on even larger and more diverse datasets.