kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A novel framework for video-informed reconstructions of sports accidents: A case study correlating brain injury pattern from multimodal neuroimaging with finite element analysis
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Neuronic Engineering.ORCID iD: 0009-0008-8497-0122
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Neuronic Engineering.ORCID iD: 0000-0001-8522-4705
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Neuronic Engineering.ORCID iD: 0000-0002-3910-0418
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Neuronic Engineering.ORCID iD: 0000-0003-0125-0784
2024 (English)In: Brain Multiphysics, E-ISSN 2666-5220, Vol. 6, article id 100085Article in journal (Refereed) Published
Abstract [en]

Ski racing is a high-risk sport for traumatic brain injury. A better understanding of the injury mechanism and the development of effective protective equipment remains central to resolving this urgency. Finite element (FE) models are useful tools for studying biomechanical responses of the brain, especially in real-world ski accidents. However, real-world accidents are often captured by handheld monocular cameras; the videos are shaky and lack depth information, making it difficult to estimate reliable impact velocities and posture which are critical for injury prediction. Introducing novel computer vision and deep learning algorithms offers an opportunity to tackle this challenge. This study proposes a novel framework for estimating impact kinematics from handheld, shaky monocular videos of accidents to inform personalized impact simulations. The utility of this framework is demonstrated by reconstructing a ski accident, in which the extracted kinematics are input to a neuroimaging-informed, personalized FE model. The FE-derived responses are compared with imaging-identified brain injury sites of the victim. The results suggest that maximum principal strain may be a useful metric for brain injury. This study demonstrates the potential of video-informed accident reconstructions combined with personalized FE modeling to evaluate individual brain injury. Statement of significance: Reconstructing real-world sports accidents combined with finite element (FE) models presents a unique opportunity to study brain injuries, as it enables simulating complex loading conditions experienced in reality. However, a significant challenge lies in accurately obtaining kinematics from the often shaky, handheld video footage of such accidents. We propose a novel framework that bridges the gap between real-world accidents and video-informed injury predictions. By integrating video analysis, 3D kinematics estimation, and personalized FE simulation, we extract accurate impact kinematics of a ski accident captured from handheld shaky monocular videos to inform personalized impact simulations, predicting the injury pathology identified by multimodal neuroimaging. This study provides important guidance on how best to estimate impact conditions from video-recorded accidents, opening new opportunities to better inform the biomechanical study of head trauma with improved boundary conditions.

Place, publisher, year, edition, pages
Elsevier BV , 2024. Vol. 6, article id 100085
Keywords [en]
Computer vision, Kinematics estimation, Personalized finite element model, Sports accidents, Traumatic brain injury
National Category
Other Medical Engineering
Identifiers
URN: urn:nbn:se:kth:diva-341761DOI: 10.1016/j.brain.2023.100085Scopus ID: 2-s2.0-85179804551OAI: oai:DiVA.org:kth-341761DiVA, id: diva2:1823431
Note

QC 20240102

Available from: 2024-01-02 Created: 2024-01-02 Last updated: 2024-01-02Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Yuan, QiantailangLi, XiaogaiZhou, ZhouKleiven, Svein

Search in DiVA

By author/editor
Yuan, QiantailangLi, XiaogaiZhou, ZhouKleiven, Svein
By organisation
Neuronic Engineering
Other Medical Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 59 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf