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

Age prediction in sub-adults based on MRI segmentation of 3rd molar tissue volumes

PURPOSE

Our aim was to investigate tissue volumes measured by MRI segmentation of the entire 3rd molar for prediction of a sub-adult being older than 18 years.

MATERIAL AND METHOD

We used a 1.5-T MR scanner with a customized high-resolution single T2 sequence acquisition with 0.37 mm iso-voxels. Two dental cotton rolls drawn with water stabilized the bite and delineated teeth from oral air. Segmentation of the different tooth tissue volumes was performed using SliceOmatic (Tomovision^©). Linear regression was used to analyze the association between mathematical transformation outcomes of the tissue volumes, age, and sex. Performance of different transformation outcomes and tooth combinations were assessed based on the p value of the age variable, combined or separated for each sex depending on the selected model. The predictive probability of being older than 18 years was obtained by a Bayesian approach.

RESULTS

We included 67 volunteers (F/M: 45/22), range 14-24 years, median age 18 years. The transformation outcome (pulp + predentine)/total volume for upper 3rd molars had the strongest association with age (p = 3.4 × 10^-9).

CONCLUSION

MRI segmentation of tooth tissue volumes might prove useful in the prediction of age older than 18 years in sub-adults.

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.

Applicability of Magnetic Resonance Imaging for Bone Age Estimation in the Context of Medical Issues

OBJECTIVE

 The determination of bone age is a method for analyzing biological age and structural maturity. Bone age estimation is predominantly used in the context of medical issues, for example in endocrine diseases or growth disturbance. As a rule, conventional X-ray images of the left wrist and hand are used for this purpose. The aim of the present study is to investigate the extent to which MRI can be used as a radiation-free alternative for bone age assessment.

METHODS

 In 50 patients, 19 females and 31 males, in addition to conventional left wrist and hand radiographs, MRI was performed with T1-VIBE (n = 50) and T1-TSE (n = 34). The average age was 11.87 years (5.08 to 17.50 years). Bone age assessment was performed by two experienced investigators blinded for chronological age according to the most widely used standard of Greulich and Pyle. This method relies on a subjective comparison of hand radiographs with gender-specific reference images from Caucasian children and adolescents. In addition to interobserver and intraobserver variability, the correlation between conventional radiographs and MRI was determined using the Pearson correlation coefficient.

RESULTS

 Between the bone age determined from the MRI data and the results of the conventional X-ray images, a very good correlation was found for both T1-VIBE with r = 0.986 and T1-TSE with r = 0.982. Gender differences did not arise. The match for the interobserver variability was very good: r = 0.985 (CR), 0.966 (T1-VIBE) and 0.971 (T1-TSE) as well as the match for the intraobserver variability for investigator A (CR = 0.994, T1-VIBE = 0.995, T1-TSE = 0.998) and for investigator B (CR = 0.994, T1-VIBE = 0.993, T1-TSE = 0.994).

CONCLUSION

 The present study shows that MRI of the left wrist and hand can be used as a possible radiation-free alternative to conventional X-ray imaging for bone age estimation in the context of medical issues.

KEY POINTS

  · MRI and X-ray show a very good correlation for bone age determination in medical issues.. · With short examination times, T1 VIBE shows slight advantages over T1 TSE.. · Both investigators show high intra- and interobserver variability..

CITATION FORMAT

· Diete V, Wabitsch M, Denzer C et al. Applicability of Magnetic Resonance Imaging for Bone Age Estimation in the Context of Medical Issues. Fortschr Röntgenstr 2021; 193: 692 - 700.

Evaluation of proximal humeral epiphysis ossification in 3.0 T MR images according to the Dedouit staging method: Is it be used for age of majority?

Magnetic resonance imaging (MRI) for forensic age estimation is among the research issues since it does not lead to radiation exposure. In this study, the ossification stage of the proximal humeral epiphysis was determined retrospectively in 178 male and 109 female individuals in the 12 to 30-year age group using 3.0 T MRI. All images were evaluated with the proton density fat saturated turbo spin echo (PD TSE FS) sequence and the T2 TSE FS sequence. A five-stage scoring system was used following the method of Dedouit et al. The relevant statistics were defined as minimum, maximum, mean ± standard deviation, 95% confidence interval of mean and median and the intra- and interobserver agreement levels were very good (κ > 0.80). There were no significant age differences between males and females in any of the stages (all p-values>0.05). According to the present study, stage 5 was initially observed at age 22 years for both genders. According to our results, it is possible to determine the completion of the 18th year of life in either gender on the shoulder joint. Proximal humeral epiphysis ossification may be used as an additional method for forensic age estimation through MRI.

Applicability of 3.0 T MRI images in the estimation of full age based on shoulder joint ossification: Single-centre study

Skeletal maturity is evaluated by many radiological methods for forensic age estimation. Direct radiography and computed tomography lead to a rise in ethical concerns due to radiation exposure. Therefore, magnetic resonance imaging (MRI) has currently been used in recent studies. In this study, the ossification stage of the shoulder joint was determined retrospectively in 178 male and 109 female individuals in the age group 12 to 30 years using 3.0 T MRI. All the images were evaluated with T1-weighted turbo spin echo (T1 TSE) sequence and T1 fast low angle shot two-dimensional sequence (T1 FL2D). The combined staging method, which was defined by Kellinghaus et al. and Schmeling et al., was used. The intra- and inter-observer agreement levels were very good (κ and κ_w). There were no significant age differences between males and females in all stages. In most of the stages, the ossification of the proximal humeral epiphyses occurred earlier in females than in males. Stage 4 did not occur in either of the sexes before the 18th birthday as the youngest patients in this stage was at 19 and 18 years of age in males and females, respectively. We concluded that evaluating the ossification of the proximal humeral epiphysis with MRI imaging for forensic age estimation may be beneficial. Evaluating the same anatomical structure with different MRI sequences may be useful for accurate staging diagnosis.