ABSTRACT NUMBER: ESOC2026A2161 MONITORING THE LATERAL VENTRICLES AND CHANGES OVER TIME IN THE PRESENCE OF SUBDURAL HEMATOMA

Abstract Background and aims Monitoring brain volumetrics during the acute and chronic stages of an intracranial hemorrhage (ICH) can have bearing on treatment course and recovery. The current study investigates automated subdural hematoma (SDH) segmentation, along with lateral ventricles, as a proof of principle to evaluate radiological progression as assessed from sequential head CT scans. Methods This retrospective study involved head CT scans that were accessed (two-year span) among N=57 adults with SDH and scanned up to 12 times (353 total scans). A previously developed Ventricle and Bleed AI model (VB-AI) was used to automatically segment ICH and the lateral ventricles to measure volumes over time. We investigated changes over time and in relation to the number of scans acquired. Results In the acute period, a patient is scanned every 1.3 days (modal value). Higher maximum bleed volume was correlated with a higher total number of scans (R2=0.23, p=0.0001). The average SDH bleed volume was 32.2 ± 32 mL, and the average lateral ventricle volume was 28.8 ± 34 mL. The sequential volumes enable monitoring a patients’ bleed volume decrease over time with successful treatment, and for corresponding changes of the lateral ventricle volume. Conclusions This study demonstrates it is possible to monitor the ICH over time in relation to the lateral ventricle volumes in an SDH sample. On-going work includes similar analysis in patients with spontaneous ICH stroke. We will also investigate how the ventricle volume changes after accounting for age, sex, and intracranial volume to reflect different head sizes. Conflict of interest Zachary Fishman: nothing to disclose, Clea Oshionowo: nothing to disclose, Ellen Cohen: nothing to disclose, Christine Hawkes: nothing to disclose, Qinghui Liu: Funding for this research was provided by Helse Sør-Øst operating and the Research Council of Norway (Qualification – Research Commercialisation fund), Guocheng Jiang: nothing to disclose, Bradley J MacIntosh: BJM acknowledges grant funding from the Canadian Institutes of Health Research (PJT-165981) and support from the Sandra Black Centre for Brain Resilience and Recovery. Figure 1 - belongs to Conclusions

Authors

Institutions

Publication Details

Journal
European Stroke Journal
Published
2026-05-01
DOI
https://doi.org/10.1093/esj/aakag023.1747
Primary Topic
Intracerebral and Subarachnoid Hemorrhage Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

ABSTRACT NUMBER: ESOC2026A2161 MONITORING THE LATERAL VENTRICLES AND CHANGES OVER TIME IN THE PRESENCE OF SUBDURAL HEMATOMA

Ellen Cohen, Guocheng Jiang, Zachary Fishman, Bradley MacIntosh et al.
European Stroke Journal
Intracerebral and Subarachnoid Hemorrhage Research
article

ABSTRACT NUMBER: ESOC2026A2161 MONITORING THE LATERAL VENTRICLES AND CHANGES OVER TIME IN THE PRESENCE OF SUBDURAL HEMATOMA

Ellen Cohen, Guocheng Jiang, Zachary Fishman, Bradley MacIntosh, Qinghui Liu, Clea Oshinowo, Christine Hawkes
article en

Abstract

Abstract Background and aims Monitoring brain volumetrics during the acute and chronic stages of an intracranial hemorrhage (ICH) can have bearing on treatment course and recovery. The current study investigates automated subdural hematoma (SDH) segmentation, along with lateral ventricles, as a proof of principle to evaluate radiological progression as assessed from sequential head CT scans. Methods This retrospective study involved head CT scans that were accessed (two-year span) among N=57 adults with SDH and scanned up to 12 times (353 total scans). A previously developed Ventricle and Bleed AI model (VB-AI) was used to automatically segment ICH and the lateral ventricles to measure volumes over time. We investigated changes over time and in relation to the number of scans acquired. Results In the acute period, a patient is scanned every 1.3 days (modal value). Higher maximum bleed volume was correlated with a higher total number of scans (R2=0.23, p=0.0001). The average SDH bleed volume was 32.2 ± 32 mL, and the average lateral ventricle volume was 28.8 ± 34 mL. The sequential volumes enable monitoring a patients’ bleed volume decrease over time with successful treatment, and for corresponding changes of the lateral ventricle volume. Conclusions This study demonstrates it is possible to monitor the ICH over time in relation to the lateral ventricle volumes in an SDH sample. On-going work includes similar analysis in patients with spontaneous ICH stroke. We will also investigate how the ventricle volume changes after accounting for age, sex, and intracranial volume to reflect different head sizes. Conflict of interest Zachary Fishman: nothing to disclose, Clea Oshionowo: nothing to disclose, Ellen Cohen: nothing to disclose, Christine Hawkes: nothing to disclose, Qinghui Liu: Funding for this research was provided by Helse Sør-Øst operating and the Research Council of Norway (Qualification – Research Commercialisation fund), Guocheng Jiang: nothing to disclose, Bradley J MacIntosh: BJM acknowledges grant funding from the Canadian Institutes of Health Research (PJT-165981) and support from the Sandra Black Centre for Brain Resilience and Recovery. Figure 1 - belongs to Conclusions

European Stroke JournalVol. 11(Supplement_1)
Oslo University Hospital (NO), University of Toronto (CA), Ontario Brain Institute (CA), Sunnybrook Hospital (CA), Sunnybrook Research Institute
Openalex Percentile: Top 9%
Intracerebral and Subarachnoid Hemorrhage Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.