A Machine Learning Enhanced Mechanistic Simulation Framework for Functional Deficit Prediction in TBI

被引:7
作者
Schroder, Anna [1 ,5 ]
Lawrence, Tim [2 ]
Voets, Natalie [2 ]
Garcia-Gonzalez, Daniel [1 ,6 ]
Jones, Mike [3 ]
Pena, Jose-Maria [4 ]
Jerusalem, Antoine [1 ]
机构
[1] Univ Oxford, Dept Engn Sci, Oxford, England
[2] Univ Oxford, Nuffield Dept Clin Neurosci, Oxford, England
[3] Cardiff Univ, Inst Med Engn & Med Phys, Cardiff, Wales
[4] Lurtis Ltd, Oxford, England
[5] UCL, Dept Med Phys & Biomed Engn, London, England
[6] Univ Carlos III Madrid, Dept Continuum Mech & Struct Anal, Leganes, Spain
基金
英国工程与自然科学研究理事会;
关键词
traumatic brain injury; resting state functional magnetic resonance imaging; default mode network; finite element simulation; machine learning; TRAUMATIC BRAIN-INJURY; DEFAULT-MODE NETWORK; DIFFUSE AXONAL INJURY; FINITE-ELEMENT MODELS; CONNECTIVITY; IMPACT; DYSFUNCTION; DISRUPTION; HEAD;
D O I
10.3389/fbioe.2021.587082
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Resting state functional magnetic resonance imaging (rsfMRI), and the underlying brain networks identified with it, have recently appeared as a promising avenue for the evaluation of functional deficits without the need for active patient participation. We hypothesize here that such alteration can be inferred from tissue damage within the network. From an engineering perspective, the numerical prediction of tissue mechanical damage following an impact remains computationally expensive. To this end, we propose a numerical framework aimed at predicting resting state network disruption for an arbitrary head impact, as described by the head velocity, location and angle of impact, and impactor shape. The proposed method uses a library of precalculated cases leveraged by a machine learning layer for efficient and quick prediction. The accuracy of the machine learning layer is illustrated with a dummy fall case, where the machine learning prediction is shown to closely match the full simulation results. The resulting framework is finally tested against the rsfMRI data of nine TBI patients scanned within 24 h of injury, for which paramedical information was used to reconstruct in silico the accident. While more clinical data are required for full validation, this approach opens the door to (i) on-the-fly prediction of rsfMRI alterations, readily measurable on clinical premises from paramedical data, and (ii) reverse-engineered accident reconstruction through rsfMRI measurements.
引用
收藏
页数:19
相关论文
共 70 条
  • [1] Al-Graitti AJ., 2017, INT J BIOMED BIOL EN, V11, P568
  • [2] Three-dimensional magnetic resonance imaging of fetal head molding and brain shape changes during the second stage of labor
    Ami, Olivier
    Maran, Jean Christophe
    Gabor, Petra
    Whitacre, Eric B.
    Musset, Dominique
    Dubray, Claude
    Mage, Gerard
    Boyer, Louis
    [J]. PLOS ONE, 2019, 14 (05):
  • [3] Mechanistic models versus machine learning, a fight worth fighting for the biological community?
    Baker, Ruth E.
    Pena, Jose-Maria
    Jayamohan, Jayaratnam
    Jerusalem, Antoine
    [J]. BIOLOGY LETTERS, 2018, 14 (05)
  • [4] Default Mode Network Connectivity Predicts Sustained Attention Deficits after Traumatic Brain Injury
    Bonnelle, Valerie
    Leech, Robert
    Kinnunen, Kirsi M.
    Ham, Tim E.
    Beckmann, Cristian F.
    De Boissezon, Xavier
    Greenwood, Richard J.
    Sharp, David J.
    [J]. JOURNAL OF NEUROSCIENCE, 2011, 31 (38) : 13442 - 13451
  • [5] Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
  • [6] Bagging predictors
    Breiman, L
    [J]. MACHINE LEARNING, 1996, 24 (02) : 123 - 140
  • [7] Long-Term Disability and Survival in Traumatic Brain Injury: Results From the National Institute on Disability and Rehabilitation Research Model Systems
    Brooks, Jordan C.
    Strauss, David J.
    Shavelle, Robert M.
    Paculdo, David R.
    Hammond, Flora M.
    Harrison-Felix, Cynthia L.
    [J]. ARCHIVES OF PHYSICAL MEDICINE AND REHABILITATION, 2013, 94 (11): : 2203 - 2209
  • [8] Diffuse axonal injury: detection of changes in anisotropy of water diffusion diffusion-weighted imaging
    Chan, JHM
    Tsui, EYK
    Peh, WCG
    Fong, D
    Fok, KF
    Leung, KM
    Yuen, MK
    Fung, KKL
    [J]. NEURORADIOLOGY, 2003, 45 (01) : 34 - 38
  • [9] NEAREST NEIGHBOR PATTERN CLASSIFICATION
    COVER, TM
    HART, PE
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 1967, 13 (01) : 21 - +
  • [10] Ensemble methods in machine learning
    Dietterich, TG
    [J]. MULTIPLE CLASSIFIER SYSTEMS, 2000, 1857 : 1 - 15