Regional prediction of hematoma expansion from non-contrast computed tomography in spontaneous intracerebral hemorrhage patients

@misc{ironside2026regional,
  title = {{Regional prediction of hematoma expansion from non-contrast computed tomography in spontaneous intracerebral hemorrhage patients}},
  author = {Natasha Ironside and Hongyu Kan and Kristofor Pas and Mohammad Shifat-E-Rabbi and Benjamin Newman and Shinjini Kundu and Kareem El Naamani and Tanvir Rizvi and Andrea Becerril-Gaitan and Harrison Snyder and Aarathi Manchikalapudi and Sarah Ratcliffe and Stacie L. Demel and Carl D. Langefeld and Daniel Woo and Stephan Mayer and E. Sander Connolly and Gustavo Rohde and for the ERICH Investigators and the VISTA-ICH collaboration},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.34645},
  eprint = {2610.34645},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.34645},
  note = {CC BY-NC-SA 4.0},
}

TY  - UNPB
TI  - Regional prediction of hematoma expansion from non-contrast computed tomography in spontaneous intracerebral hemorrhage patients
AU  - Natasha Ironside
AU  - Hongyu Kan
AU  - Kristofor Pas
AU  - Mohammad Shifat-E-Rabbi
AU  - Benjamin Newman
AU  - Shinjini Kundu
AU  - Kareem El Naamani
AU  - Tanvir Rizvi
AU  - Andrea Becerril-Gaitan
AU  - Harrison Snyder
AU  - Aarathi Manchikalapudi
AU  - Sarah Ratcliffe
AU  - Stacie L. Demel
AU  - Carl D. Langefeld
AU  - Daniel Woo
AU  - Stephan Mayer
AU  - E. Sander Connolly
AU  - Gustavo Rohde
AU  - for the ERICH Investigators
AU  - the VISTA-ICH collaboration
PY  - 2026
DA  - 2026/10/26
PB  - arXiv
DO  - 10.48550/arxiv.2610.34645
UR  - https://arxiv.org/abs/2610.34645
AB  - Background The combination of hematoma location, expansion and final volume influence neurological outcome. The aim of this study was to derive and validate a quantitative and interpretable region-based NCCT image feature model for predicting hematoma expansion. Methods The Ethnic/Racial Variations of Intracerebral Hemorrhage(ERICH) study was used for derivation and the Virtual International Trials in Stroke Archive(VISTA) was used for validation. NCCT images at presentation and 24+/-6hours were pre-processed, segmented and categorized into lobar, basal ganglia or thalamic regions. Hematoma expansion was defined by region and according to its effect on clinical outcome. Transport-based morphometry (TBM) produced a unique transport-based representation from each NCCT hematoma image. Linear classifiers applied to transport representations were used to derive a predictive model. The regional TBM model's performance was compared to alternate methods using AUROC analyses. Results The derivation dataset included 574 patients, comprising 162 lobar, 257 basal ganglia and 155 thalamic hematomas. The validation dataset included 196 patients, comprising 31 lobar, 119 basal ganglia and 46 thalamic hematomas. A combined regional model predicted hematoma expansion in the validation dataset with an AUROC of 0.787. The principal image features which varied by location were size, heterogeneity, eccentricity and density distribution towards the hematoma periphery. The regional TBM model outperformed alternative clinician based and machine-learning methods. Conclusions TBM discriminated and visualized regional features of hematoma expansion from presentation NCCT scans. This provides preliminary evidence for regional radiographic features of hematoma expansion. It has the potential to improve hematoma expansion prediction and understanding of hematoma expansion pathophysiology.
SN  - 2331-8422
ER  -