Automatic and Efficient Prediction of Hematoma Expansion in Patients with Hypertensive Intracerebral Hemorrhage Using Deep Learning Based on CT Images.
deep learning
end-to-end
hematoma expansion
hypertension
Journal
Journal of personalized medicine
ISSN: 2075-4426
Titre abrégé: J Pers Med
Pays: Switzerland
ID NLM: 101602269
Informations de publication
Date de publication:
12 May 2022
12 May 2022
Historique:
received:
25
04
2022
revised:
09
05
2022
accepted:
10
05
2022
entrez:
28
5
2022
pubmed:
29
5
2022
medline:
29
5
2022
Statut:
epublish
Résumé
Patients with hypertensive intracerebral hemorrhage (ICH) have a high hematoma expansion (HE) incidence. Noninvasive prediction HE helps doctors take effective measures to prevent accidents. This study retrospectively analyzed 253 cases of hypertensive intraparenchymal hematoma. Baseline non-contrast-enhanced CT scans (NECTs) were collected at admission and compared with subsequent CTs to determine the presence of HE. An end-to-end deep learning method based on CT was proposed to automatically segment the hematoma region, region of interest (ROI) feature extraction, and HE prediction. A variety of algorithms were employed for comparison. U-Net with attention performs best in the task of segmenting hematomas, with the mean Intersection overUnion (mIoU) of 0.9025. ResNet-34 achieves the most robust generalization capability in HE prediction, with an area under the receiver operating characteristic curve (AUC) of 0.9267, an accuracy of 0.8827, and an F
Identifiants
pubmed: 35629201
pii: jpm12050779
doi: 10.3390/jpm12050779
pmc: PMC9147936
pii:
doi:
Types de publication
Journal Article
Langues
eng
Subventions
Organisme : Neuro-oncology Project from the Chinese Anti-Cancer Association
ID : CSNO-2016-MSD05
Organisme : the Beijing Municipal Science &Technology Commission
ID : Z171100001017199
Références
Physiol Meas. 2021 Jul 28;42(7):
pubmed: 34198278
JAMA Neurol. 2014 Feb;71(2):158-64
pubmed: 24366060
J Neurol Neurosurg Psychiatry. 2013 Oct;84(10):1150-5
pubmed: 23715913
Stroke. 2015 Aug;46(8):2119-23
pubmed: 26089330
Stroke. 2016 Apr;47(4):958-63
pubmed: 26931155
Front Oncol. 2021 Feb 18;10:614201
pubmed: 33680934
Comput Intell Neurosci. 2021 Aug 31;2021:7552185
pubmed: 34504522
Lancet Neurol. 2003 Jan;2(1):43-53
pubmed: 12849300
Korean J Radiol. 2021 Mar;22(3):415-424
pubmed: 33169546
Stroke. 2017 Jan;48(1):131-135
pubmed: 27879447
Lancet Neurol. 2012 Apr;11(4):307-14
pubmed: 22405630
Nat Methods. 2019 Jan;16(1):67-70
pubmed: 30559429
Neurology. 2012 Jul 24;79(4):314-9
pubmed: 22744655
Med Phys. 2021 Dec;48(12):7864-7876
pubmed: 34716711
N Engl J Med. 2013 Jun 20;368(25):2355-65
pubmed: 23713578
Neurology. 2006 Apr 25;66(8):1175-81
pubmed: 16636233
EBioMedicine. 2019 May;43:454-459
pubmed: 31060901
Appl Intell (Dordr). 2021;51(5):2850-2863
pubmed: 34764568
Front Genet. 2021 Feb 11;12:639930
pubmed: 33679900
Sensors (Basel). 2021 Jun 04;21(11):
pubmed: 34199873
Stroke. 2016 Jul;47(7):1777-81
pubmed: 27174523
Stroke. 2017 Nov;48(11):3019-3025
pubmed: 29018128
Stroke. 1997 Mar;28(3):491-9
pubmed: 9056601
J Neurosurg. 1994 Jan;80(1):51-7
pubmed: 8271022
J Neurol Neurosurg Psychiatry. 2014 Jun;85(6):660-7
pubmed: 24262916
Front Aging Neurosci. 2021 May 26;13:632138
pubmed: 34122038
IEEE/ACM Trans Comput Biol Bioinform. 2021 Jan-Feb;18(1):94-102
pubmed: 32287004
Lancet Neurol. 2012 Jan;11(1):101-18
pubmed: 22172625
N Engl J Med. 2001 May 10;344(19):1450-60
pubmed: 11346811
Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:3205-3208
pubmed: 34891923
AJNR Am J Neuroradiol. 2018 Feb;39(2):232-237
pubmed: 29217744
N Engl J Med. 2016 Sep 15;375(11):1033-43
pubmed: 27276234