Identifying Fatal Head Injuries on Postmortem Computed Tomography Using Convolutional Neural Network/Deep Learning: A Feasibility Study.
SAH
autopsy
convoluted neural network
deep learning
forensic radiology
head
injuries
postmortem computed tomography
subarachnoid hemorrhage
traumatic brain injury
Journal
Journal of forensic sciences
ISSN: 1556-4029
Titre abrégé: J Forensic Sci
Pays: United States
ID NLM: 0375370
Informations de publication
Date de publication:
Nov 2020
Nov 2020
Historique:
received:
27
03
2020
revised:
07
06
2020
revised:
23
05
2020
accepted:
15
06
2020
pubmed:
9
7
2020
medline:
4
5
2021
entrez:
9
7
2020
Statut:
ppublish
Résumé
Postmortem computed tomography (PMCT) is a relatively recent advancement in forensic pathology practice that has been increasingly used as an ancillary investigation and screening tool. One area of clinical CT imaging that has garnered a lot of research interest recently is the area of "artificial intelligence" (AI), such as in screening and computer-assisted diagnostics. This feasibility study investigated the application of convolutional neural network, a form of deep learning AI, to PMCT head imaging in differentiating fatal head injury from controls. PMCT images of a transverse section of the head at the level of the frontal sinus from 25 cases of fatal head injury were combined with 25 nonhead-injury controls and divided into training and testing datasets. A convolutional neural network was constructed using Keras and was trained against the training data before being assessed against the testing dataset. The results of this study demonstrated an accuracy of between 70% and 92.5%, with difficulties in recognizing subarachnoid hemorrhage and in distinguishing congested vessels and prominent falx from head injury. These results are promising for potential applications as a screening tool or in computer-assisted diagnostics in the future.
Identifiants
pubmed: 32639630
doi: 10.1111/1556-4029.14502
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2019-2022Informations de copyright
© 2020 American Academy of Forensic Sciences.
Références
Le Blanc-Louvry I, Thureau S, Duval C, Papin-Lefebvre F, Thiebot J, Dacher JN, et al. Post-mortem computed tomography compared to forensic autopsy findings: a French experience. Eur Radiol 2013;23(7):1829-35.
Flach PM, Gascho D, Schweitzer W, Ruder TD, Berger N, Ross SG, et al. Imaging in forensic radiology: an illustrated guide for postmortem computed tomography technique and protocols. Forensic Sci Med Pathol 2014;10(4):583-606.
Thomsen AH, Jurik AG, Uhrenholt L, Vesterby A. An alternative approach to computerized tomography (CT) in forensic pathology. Forensic Sci Int 2009;183(1-3):87-90.
Moskala A, Wozniak K, Kluza P, Romaszko K, Lopatin O. The importance of post-mortem computed tomography (PMCT) in confrontation with conventional forensic autopsy of victims of motorcycle accidents. Leg Med (Tokyo) 2016;18:25-30.
Grabherr S, Egger C, Vilarino R, Campana L, Jotterand M, Dedouit F. Modern post-mortem imaging: an update on recent developments. Forensic Sci Res 2017;2(2):52-64.
Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H. Artificial intelligence in radiology. Nat Rev Cancer 2018;18(8):500-10.
Miller DD, Brown EW. Artificial intelligence in medical practice: the question to the answer? Am J Med 2018;131(2):129-33.
Yasaka K, Abe O. Deep learning and artificial intelligence in radiology: current applications and future directions. PLoS Med 2018;15(11):e1002707.
Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, et al. Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet 2018;392(10162):2388-96.
Chan S, Siegel EL. Will machine learning end the viability of radiology as a thriving medical specialty? Br J Radiol 2019;92(1094):20180416.
Zhu G, Jiang B, Tong L, Xie Y, Zaharchuk G, Wintermark M. Applications of deep learning to neuro-Imaging techniques. Front Neurol 2019;10:869.
Ebert LC, Heimer J, Schweitzer W, Sieberth T, Leipner A, Thali M, et al. Automatic detection of hemorrhagic pericardial effusion on PMCT using deep learning - a feasibility study. Forensic Sci Med Pathol 2017;13(4):426-31.
O'Sullivan S, Holzinger A, Zatloukal K, Saldiva P, Sajid MI, Wichmann D. Machine learning enhanced virtual autopsy. Autops Case Rep 2017;7(4):3-7.
O'Sullivan S, Heinsen H, Grinberg LT, Chimelli L, Amaro E, do Nascimento Saldiva PH, et al. The role of artificial intelligence and machine learning in harmonization of high-resolution post-mortem MRI (virtopsy) with respect to brain microstructure. Brain Informatics 2019;6(1):3.
Lefevre T. Big data in forensic science and medicine. J Forensic Leg Med 2018;57:1-6.
Legrand L, Delabarde T, Souillard-Scemama R, Sec I, Plu I, Laborie JM, et al. Comparison between postmortem computed tomography and autopsy in the detection of traumatic head injuries. J Neuroradiol 2020;47(1):5-12.
Schmitt-Sody M, Kurz S, Reiser M, Kanz KG, Kirchhoff C, Peschel O, et al. Analysis of death in major trauma: value of prompt post mortem computed tomography (pmCT) in comparison to office hour autopsy. Scand J Trauma Resusc Emerg Med 2016;24:38. https://doi.org/10.1186/s13049-016-0231-6.
Keras CF. GitHub repository, 2015. https://keras.io (accessed May 20, 2020).
Prevedello LM, Erdal BS, Ryu JL, Little KJ, Demirer M, Qian S, et al. Automated critical test findings identification and online notification system using artificial intelligence in imaging. Radiology 2017;285(3):923-31.
Shirota G, Gonoi W, Ikemura M, Ishida M, Shintani Y, Abe H, et al. The pseudo-SAH sign: an imaging pitfall in postmortem computed tomography. Int J Legal Med 2017;131(6):1647-53.