journal article·2025-08

A high-throughput framework for predicting three-dimensional structural–mechanical relationships of human cranial bones using a deep learning-based method

Weihao Guo, Mohammad Rezasefat, Karyne N. Rabey, Simon Ouellet, Lindsey Westover, James David Hogan

Publisher page

Abstract

Cranial bone injuries significantly impact human health, potentially leading to death or permanent disability, and mechanical responses are crucial predictors of cranial damage. Predicting mechanical responses through medical imaging is an efficient method that streamlines the process by eliminating the need for intermediate steps, such as diagnostic testing and biomedical analysis. Although previous studies have successfully predicted 1D sequences or 2D sectional mechanical attributes from medical imaging, these approaches are limited in their ability to capture the anisotropic characteristics of cranial bone. As a complex osseous material, cranial bone has significant directional dependencies in its microstructural features, which directly influence its macroscopic mechanical responses under loading conditions. In this study, we aim to introduce a deep learning-based high-throughput framework to correlate the three-dimensional mechanical responses and three-dimensional cranial microstructures derived from medical images. First, micro-CT scans of 40 human cranial samples, spanning an average age of 82.5 years, were performed to capture microstructural information. Next, 2000 representative volume element (RVE) units were randomly and automatically extracted from these scans to characterize the cranial microstructures. Following this, 2000 stress and 2000 strain fields were derived from finite element simulations based on these RVE units, and subsequently validated through quasi-static compression experiments. An optimized U-Net-based deep learning network was employed to link the macro-property stress-strain response with the three-dimensional cranial microstructures. The proposed framework demonstrates robust performance in predicting the spatial mechanical behavior based on microstructural inputs, showing high and consistent similarity between the predictions and ground truth. Overall, the high-throughput nature of this framework facilitates the handling of large-scale data, enabling comprehensive and efficient analysis that is crucial for predicting mechanical responses. By elucidating structure-property relationships, this approach can enhance the accuracy of injury diagnosis and aid in the development of tailored treatment plans, effectively bridging the gap between structural morphology and mechanical functionality.
Source: europepmc · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Medical Imaging and Analysis · Forensic Anthropology and Bioarchaeology Studies · Dental Radiography and Imaging

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (66)

Show source-provided references
1. The mechanical characterization and comparison of male and female Calvaria under four-point bending impacts10.1115/1.4056459 ↗
2. Cortical and trabecular morphometric properties of the human calvarium10.1016/j.bone.2021.115931 ↗
3. Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis10.1038/s41746-021-00438-z ↗
4. Multiscale response of the human skull to quasi-static compression10.1016/j.jmbbm.2019.103492 ↗
5. Influence of the mesostructure on the compressive mechanical response of adolescent porcine cranial bone10.1016/j.jmbbm.2019.04.010 ↗
6. Structural analysis of the frontal and parietal bones of the human skull10.1016/j.jmbbm.2018.10.035 ↗
7. Implementation and validation of finite element model of skull deformation and failure response during uniaxial compression10.1016/j.jmbbm.2020.104302 ↗
8. The validation and application of a finite element human head model for frontal skull fracture analysis10.1016/j.jmbbm.2013.02.010 ↗
9. Long-bone fracture detection in digital X-ray images based on digital-geometric techniques10.1016/j.cmpb.2015.09.013 ↗
10. Towards efficient uncertainty quantification in complex and large-scale biomechanical problems based on a Bayesian multi-fidelity scheme10.1007/s10237-014-0618-0 ↗
11. Variation of bone layer thicknesses and trabecular volume fraction in the adult male human calvarium10.1016/j.bone.2015.04.031 ↗
12. On the mathematical properties of the structural similarity index10.1109/TIP.2011.2173206 ↗
13. Comparison of mechanical testing methods for biomaterials: Pipette aspiration, nanoindentation, and macroscale testing10.1016/j.jmbbm.2015.07.022 ↗
14. Segmentation of bone structure in X-ray images using convolutional neural network10.4316/AECE.2013.01015 ↗
15. Choi · 2009
16. The structure and mechanics of bone10.1007/s10853-011-5914-9 ↗
17. Skull fracture prediction through subject-specific finite element modelling is highly sensitive to model parameters10.1016/j.jmbbm.2019.103384 ↗
18. Medical image segmentation based on u-net: A review10.2352/J.ImagingSci.Technol.2020.64.2.020508 ↗
19. State-of-the-art traditional to the machine-and deep-learning-based skull stripping techniques, models, and algorithms10.1007/s10278-020-00367-5 ↗
20. Computational methods for three-dimensional electron microscopy (3DEM)10.1016/j.cmpb.2022.107039 ↗
21. Multi-scale deep reinforcement learning for real-time 3D-landmark detection in CT scans10.1109/TPAMI.2017.2782687 ↗
22. Compressive behaviour of bovine cancellous bone and bone analogous materials, microCT characterisation and FE analysis10.1016/j.jmbbm.2011.05.015 ↗
23. A comprehensive analysis of human cranial morphology: multiscale characterization and statistical analysis
24. Apparent damage accumulation in cancellous bone using neural networks10.1016/j.jmbbm.2011.03.002 ↗
25. Deep learning-based inverse scattering with structural similarity loss functions10.1109/JSEN.2020.3030321 ↗
26. Prediction of biomechanical properties of trabecular bone in MR images with geometric features and support vector regression10.1109/TBME.2011.2119484 ↗
27. Identification and functional annotation of genes related to bone stability in laying hens using random forests10.3390/genes12050702 ↗
28. A survey on deep learning approaches to medical images and a systematic look up into real-time object detection
29. Machine learning and big data provide crucial insight for future biomaterials discovery and research10.1016/j.actbio.2021.05.053 ↗
30. Deep learning virtual indenter maps nanoscale hardness rapidly and non-destructively, revealing mechanism and enhancing bioinspired design10.1016/j.matt.2023.03.031 ↗
31. Medical image analysis using deep learning algorithms
32. Micro-hardness and strain-rate-dependent compressive response of an ultra-light-weight Mg-Li-Al alloy10.1016/j.jallcom.2021.161703 ↗
33. Optimizing memory efficiency for deep convolutional neural networks on GPUs
34. A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis10.1098/rsif.2017.0844 ↗
35. Efficient generation of pretraining samples for developing a deep learning brain injury model via transfer learning
36. Influence of morphological variation on brain impact responses among youth and young adults10.1016/j.jbiomech.2022.111036 ↗
37. Cone-beam X-ray luminescence computed tomography based on MLEM with adaptive FISTA initial image10.1016/j.cmpb.2022.107265 ↗
38. Inverse design of anisotropic bone scaffold based on machine learning and regenerative genetic algorithm10.3389/fbioe.2023.1241151 ↗
39. Predicting the effective compressive modulus of human cancellous bone using the convolutional neural network method10.1080/10255842.2022.2112183 ↗
40. On the limits of finite element models created from (micro) CT datasets and used in studies of bone-implant-related biomechanical problems10.1016/j.jmbbm.2021.104393 ↗
41. The mechanical properties of cranial bone: the effect of loading rate and cranial sampling position10.1016/j.jbiomech.2009.05.030 ↗
42. Enhance-net: An approach to boost the performance of deep learning model based on real-time medical images10.1155/2023/8276738 ↗
43. Machine learning model for fast prediction of the natural frequencies of protein molecules10.1039/C9RA04186A ↗
44. A finite element-convolutional neural network model (FE-CNN) for stress field analysis around arbitrary inclusions
45. Prediction of 4D stress field evolution around additive manufacturing-induced porosity through progressive deep-learning frameworks
46. Mechanical characterization of biomaterials10.1016/B978-0-12-415800-9.00003-6 ↗
47. U-net: Convolutional networks for biomedical image segmentation
48. Multi-fidelity surrogate modeling through hybrid machine learning for biomechanical and finite element analysis of soft tissues10.1016/j.compbiomed.2022.105699 ↗
49. Prediction of fracture callus mechanical properties using micro-CT images and voxel-based finite element analysis10.1016/j.bone.2004.11.007 ↗
50. Deep learning approach to assess damage mechanics of bone tissue10.1016/j.jmbbm.2021.104761 ↗
51. Siddique · 2020
52. Mechanical properties of whole-body soft human tissues: A review10.1088/1748-605X/ac2b7a ↗
53. Analysis of trabecular bone mechanics using machine learning10.1177/1176934318825084 ↗
54. Deep learning based synthetic-CT generation in radiotherapy and PET: a review10.1002/mp.15150 ↗
55. Deep learning for automated skeletal bone age assessment in X-ray images10.1016/j.media.2016.10.010 ↗
56. Evaluation of the head protection effectiveness of cyclist helmets using full-scale computational biomechanics modelling of cycling accidents10.1016/j.jsr.2021.11.005 ↗
57. Application of nanoindentation technology in testing the mechanical properties of skull materials10.1038/s41598-022-11216-6 ↗
58. Deep learning-based cardiovascular image diagnosis: a promising challenge10.1016/j.future.2019.09.047 ↗
59. Computational studies of porous head protection structures for human cranium under impact loading10.1007/s10338-021-00222-2 ↗
60. Theoretical prediction model and failure mechanism map of human skull porous structures with quasi-static bending performance10.1016/j.ijmecsci.2021.106431 ↗
61. Impact response and energy absorption of human skull cellular bones10.1016/j.jmbbm.2018.02.018 ↗
62. Impact behaviors of human skull sandwich cellular bones: Theoretical models and simulation10.1016/j.jmbbm.2020.103669 ↗
63. Real-time dynamic simulation for highly accurate spatiotemporal brain deformation from impact10.1016/j.cma.2022.114913 ↗
64. High-throughput generation of 3D graphene metamaterials and property quantification using machine learning10.1002/smtd.202200537 ↗
65. Standardizing compression testing for measuring the stiffness of human bone10.1302/2046-3758.78.BJR-2018-0025.R1 ↗
66. Zur · 2019