Restricted accessResearch articleFirst published online 2025-2
Automated segmentation of ventricular volumes and subarachnoid hemorrhage from computed tomography images: Evaluation of a rule-based pipeline approach
Changes in ventricular size, related to brain edema and hydrocephalus, as well as the extent of hemorrhage are associated with adverse outcomes in patients with subarachnoid hemorrhage (SAH). Frequently, these are measured manually using consecutive non-contrast computed tomography scans. Here, we developed a rule-based approach which incorporates both intensity and spatial normalization and utilizes user-defined thresholds and anatomical templates to segment both lateral ventricle (LV) and SAH blood volumes automatically from CT images. The algorithmic segmentations were evaluated against two expert neuroradiologists on representative slices from 20 admission scans from aneurysmal SAH patients. Previous methods have been developed to automate this time-consuming task, but they lack user feedback and are hard to implement due to large-scale data and complex design processes. Our results using automatic ventricular segmentation aligned well with expert reviewers with a median Dice coefficient of 0.81, AUC of 0.91, sensitivity of 81%, and precision of 84%. Automatic segmentation of SAH blood was most reliable near the base of the brain with a median Dice coefficient of 0.51, an AUC of 0.75, precision of 68%, and sensitivity of 50%. Ultimately, we developed a rule-based method that is easily adaptable through user feedback, generates spatially normalized segmentations that are comparable regardless of brain morphology or acquisition conditions, and automatically segments LV with good overall reliability and basal SAH blood with good precision. Our approach could benefit longitudinal studies in patients with SAH by streamlining assessment of edema and hydrocephalus progression, as well as blood resorption.
GijnJHijdraAWijdicksEFM, et al.Acute hydrocephalus after aneurysmal subarachnoid hemorrhage. J Neurosurg1985; 63: 355–362.
2.
HijdraAGijnJVStefankoS, et al.Delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage: clinicoanatomic correlations. Neurology1986; 36: 329.
3.
BrilstraEHRinkelGJEAlgraA, et al.Rebleeding, secondary ischemia, and timing of operation in patients with subarachnoid hemorrhage. Neurology2000; 55: 1656–1660.
4.
SteenWEZijlstraIAVerbaanD, et al.Association of quantified location-specific blood volumes with delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage. Am J Neuroradiol2018; 39: 1059–1064.
5.
YuanJYChenYJayaramanK, et al.Automated quantification of compartmental blood volumes enables prediction of delayed cerebral ischemia and outcomes after aneurysmal subarachnoid hemorrhage. World Neurosurgery2023; 170: e214–e222.
6.
DaouBJKhalsaSSSAnandSK, et al. Volumetric quantification of aneurysmal subarachnoid hemorrhage independently predicts hydrocephalus and seizures. Journal of Neurosurgery JNS. 2021; 135(4): 1155–1163.
7.
AvrahamiEKatzRRabinA, et al.CT diagnosis of non-traumatic subarachnoid haemorrhage in patients with brain edema. Eur J Radiol1998; 28: 222–225.
8.
DupontSRabinsteinAA. CT evaluation of lateral ventricular dilatation after subarachnoid hemorrhage: baseline bicaudate index balues. Neurol Res2013; 35: 103–106.
9.
GooHW. Hydrocephalus: ventricular volume quantification using three-dimensional brain CT data and semiautomatic three-dimensional threshold-based segmentation approach. Korean J Radiol2021; 22: 435–441.
10.
Talbot-StetskoHKRaueKDAaronBL, et al. Ventricular volume change as a predictor of shunt-dependent hydrocephalus in aneurysmal subarachnoid hemorrhage. World Neurosurgery. 2021; 157: e57–e65. doi:10.1016/j.wneu.2021.09.085.
11.
Talbot-StetskoHKHollonTCMaherCO, et al.A comparison of ventricular volume and linear indices in predicting shunt dependence in aneurysmal subarachnoid hemorrhage. World Neurosurgery: X2023; 19: 100181.
12.
LiY-HZhangLHuQ-M, et al.Automatic subarachnoid space segmentation and hemorrhage detection in clinical head CT scans. Int J CARS2012; 7: 507–516.
13.
LiYWuJLiH, et al.Automatic detection of the existence of subarachnoid hemorrhage from clinical CT images. J Med Syst2012; 36: 1259–1270.
14.
BoersAMZijlstraIAGathierCS, et al.Automatic quantification of subarachnoid hemorrhage on noncontrast CT. Am J Neuroradiol2014; 35: 2279.
15.
BarrosRSvan der SteenWEBoersAMM, et al.Automated segmentation of subarachnoid hemorrhages with convolutional neural networks. Inform Med Unlocked2020; 19: 100321.
16.
HuPZhouHYanT, et al. Deep learning-assisted identification and quantification of aneurysmal subarachnoid hemorrhage in non-contrast CT scans: development and external validation of Hybrid 2D/3D UNet. Neuroimage. 2023; 279.
17.
ThanellasAPeuraHLavintoM, et al. Development and external validation of a deep learning algorithm to identify and localize subarachnoid hemorrhage on CT scans. Neurology. 2023; 100(12): e1257–e1266. doi:10.1212/WNL.0000000000201710.
18.
ThomsonBRGürlekFBuzziRM, et al.Clinical potential of automated convolutional neural network-based hematoma volumetry after aneurysmal subarachnoid hemorrhage. J Stroke Cerebrovasc Dis2023; 32: 107357.
19.
RuttimannUEJoyceEMRioDE, et al.Fully automated segmentation of cerebrospinal fluid in computed tomography. Psychiatr Res Neuroimaging1993; 50: 101–119.
20.
ChenWSmithRJiS-Y, et al.Automated segmentation of lateral ventricles in brain CT images. In: 2008 IEEE International Conference on Bioinformatics and Biomeidcine Workshops, 2008, pp. 48–55.
21.
LiuJHuangSIharV, et al.Automatic model-guided segmentation of the human brain ventricular system from CT images. Acad Radiol2010; 17: 718–726.
22.
PohLEGuptaVJohnsonA, et al.Automatic segmentation of ventricular cerebrospinal fluid from ischemic stroke CT images. Neuroinform2012; 10: 159–172.
23.
FerdianEBoersAMBeenenLF, et al.Automated ventricular system segmentation in CT images of deformed brains due to ischemic and subarachnoid hemorrhagic stroke. In: CardosoMJArbelTGaoF (eds). Molecular Imaging, Reconstruction and Analysis of Moving Body Organs, and Stroke Imaging and Treatment. Cham: Springer International Publishing, 2017, pp. 149–157.
24.
HuffTJLudwigPESalazarD, et al.Fully automated intracranial ventricle segmentation on CT with 2D regional convolutional neural network to estimate ventricular volume. Int J CARS2019; 14: 1923–1932.
25.
KlimontMFliegerMRzeszutekJ, et al.Automated ventricular system segmentation in paediatric patients treated for hydrocephalus using deep learning methods. BioMed Res Int2019; 2019: e3059170.
26.
YuanJYChenYKumarA, et al.Automated quantification of reduced sulcal volume identifies early brain injury after aneurysmal subarachnoid hemorrhage. Stroke2021; 52: 1380–1389.
27.
GerkenAWalluscheckSKohlmannP, et al.Deep learning-based segmentation of brain parenchyma and ventricular system in CT scans in the presence of anomalies. Frontiers in Neuroimaging2023; 2, https://www.frontiersin.org/articles/10.3389/fnimg.2023.1228255 (accessed 19 September 2023).
28.
LiXLuoGWangK, et al.The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: the INSTANCE challenge. 2023. DOI: 10.48550/arXiv.2301.03281.
29.
MaharathiBWongJGeraghtyJR, et al.Multi-modal data integration platform combining clinical and preclinical models of post subarachnoid hemorrhage epilepsy. In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. EMBC, pp. 3459–3463.
30.
The MathWorks Inc.MATLAB. version 9.5.0.1265761 (R2018b). Natick, Massachusetts: The MathWorks Inc., 2018.
31.
MuschelliJPublicly AvailableAResolutionH. Unbiased CT Brain Template and Information Processing and Management of Uncertainty. Knowl Base Syst2020; 1239: 358–366.
32.
EvansACCollinsDLMillsSR, et al.3D statistical neuroanatomical models from 305 MRI volumes. 1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference1993; 3: 1813–1817.
33.
FedorovABeichelRKalpathy-CramerJ, et al.3D slicer as an image computing platform for the quantitative imaging network. Magn Reson Imag2012; 30: 1323–1341.
34.
Slicer Community. 3D slicer image computing software. 3D Slicer, 2022. https://www.slicer.org/.
35.
RordenCBonilhaLFridrikssonJ, et al.Age-specific CT and MRI templates for spatial normalization. Neuroimage2012; 61: 957–965.
36.
MuschelliJUllmanNLMouldWA, et al.Validated automatic brain extraction of head CT images. Neuroimage2015; 114: 379–385.
37.
LiXMorganPSAshburnerJ, et al.The first step for neuroimaging data analysis: DICOM to NIfTI conversion. J Neurosci Methods2016; 264: 47–56.
ImKLeeJ-MLytteltonO, et al.Brain size and cortical structure in the adult human brain. Cerebr Cortex2008; 18: 2181–2191.
44.
KimKYNowrangiRMcGeheeA, et al.Assessment of germinal matrix hemorrhage on head ultrasound with deep learning algorithms. Pediatr Radiol2022; 52: 533–538.
45.
KleinSStaringMMurphyK, et al.Elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med Imag2010; 29: 196–205.
ShattuckDWMirzaMAdisetiyoV, et al.Construction of a 3D probabilistic atlas of human cortical structures. Neuroimage2008; 39: 1064–1080.
48.
YushkevichPAPivenJHazlettHC, et al.User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage2006; 31: 1116–1128.
49.
MüllerDSoto-ReyIKramerF. Towards a guideline for evaluation metrics in medical image segmentation. BMC Res Notes2022; 15: 210.
50.
KooTKLiMY. A guideline of selecting and reporting intraclass correlation coefficients for reliability Research. J Chiropr Med2016; 15: 155–163.
51.
AndradeNFariaFACappabiancoFAM. A practical review on medical image registration: from rigid to deep learning based approaches. In: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2018, pp. 463–470.
52.
MuschelliJGhermanAFortinJ-P, et al.Neuroconductor: an R platform for medical imaging analysis. Biostatistics2019; 20: 218–239.
53.
MontiSPaganelliCBuizzaG, et al.A novel framework for spatial normalization of dose distributions in voxel-based analyses of brain irradiation outcomes. Phys Med2020; 69: 164–169.
54.
LiuXFaesLKaleAU, et al.A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. The Lancet Digital Health2019; 1: e271–e297.
55.
GijnJDongenKJVermeulenM, et al.Perimesencephalic hemorrhage: a nonaneurysmal and benign form of subarachnoid hemorrhage. Neurology1985; 35: 493.
56.
ChieregatoAMDFainardiEMDMorselli-LabateAM, et al.Factors associated with neurological outcome and lesion progression in traumatic subarachnoid hemorrhage patients. Neurosurgery2005; 56: 671–680.
57.
MarderCPNarlaVFinkJR, et al.Subarachnoid hemorrhage: beyond aneurysms. Am J Roentgenol2014; 202: 25–37.
58.
CapionTLilja-CyronAOlsenMH, et al.Predictors of shunt insertion in patients with aneurysmal subarachnoid haemorrhage—a single-centre retrospective analysis. Acta Neurochir2024; 166: 24.
59.
AhnS-HSavarrajJPPervezM, et al.The subarachnoid hemorrhage early brain edema score predicts delayed cerebral ischemia and clinical outcomes. Neurosurgery2018; 83: 137–145.
60.
ReillyCAmideiCTolentinoJ, et al.Clot volume and clearance rate as independent predictors of vasospasm after aneurysmal subarachnoid hemorrhage. J Neurosurg2004; 101: 255–261.
61.
LuoG-GRamchurnAChenY-F, et al.Early predictors of hematoma resorption rate in medically treated patients with spontaneous supratentorial hemorrhage. J Neurol Sci2013; 327: 55–60.
62.
KoS-BChoiHAHelbokR, et al.Quantitative analysis of hemorrhage clearance and delayed cerebral ischemia after subarachnoid hemorrhage. J Neurointerventional Surg2016; 8: 923–926.
63.
RitzenthalerTGobertFBouchierB, et al.Amount of blood during the subacute phase and clot clearance rate as prognostic factors for delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage. J Clin Neurosci2021; 87: 74–79.
64.
ZeineddineHADivitoAMcBrideDW, et al. Subarachnoid blood clearance and aneurysmal subarachnoid hemorrhage outcomes: a retrospective review. Neurocritical Care. 2023; 39(1): 172–179. doi:10.1007/s12028-023-01729-x.
65.
HuttunenJKurkiMIFraunbergM, et al.Epilepsy after aneurysmal subarachnoid hemorrhage: a population-based, long-term follow-up study. Neurology2015; 84: 2229–2237.
66.
ZanatyMNakagawaDStarkeRM, et al.Intraventricular extension of an aneurysmal subarachnoid hemorrhage is an independent predictor of a worse functional outcome. Clin Neurol Neurosurg2018; 170: 67–72.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
