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

Abstract

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.

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

“…Besides reducing the costs it can lower the stress to patients as well, which is particularly useful for young refugees with traumatic backgrounds. First promising applications of the acceleration technique in the area of age estimation have been analyzed in [ 71 , 74 , 75 ]. Other non-invasive techniques such as ultrasound (US) have yet to be evaluated for their suitability for age estimation, especially when used in combination with machine learning.…”

“…A final limitation of the current study is MRI as image modality due to the high cost in comparison to X-ray due to spacious facilities, equipment, medical technical assistants, and examination duration. In [69][70][71][72][73][74][75][76][77][78], a solution is proposed to accelerate acquisition times by reconstructing MRIs using undersampled data in k-space. Besides reducing the costs it can lower the stress to patients as well, which is particularly useful for young refugees with traumatic backgrounds.…”

Dental and Skeletal Imaging in Forensic Age Estimation: Disparities in Current Approaches and the Continuing Search for Optimization

“…69 Using a 3-T MR scanner, Neumayer et al presented a 4-minute approach to study the AGFAD triad of anatomical sites. 70 These results look promising but need to be validated before they can be generally applied.…”

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

“…Erste Studien haben sich bereits mit dem Einsatz von KI-Systemen zur Knochenalterbestimmung basierend auf der MRT der linken Hand oder des Kniegelenks beschäftigt [29][30][31]. Auch die Reduktion der Akquisitionszeiten für die MRT wurde bereits in ersten Studien untersucht [32,33]. Für zukünftige Studien ergeben sich daraus vielversprechende Ansätze.…”