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

Natasha Ironside; Hongyu Kan; Kristofor Pas; Mohammad Shifat-E-Rabbi; Benjamin Newman; Shinjini Kundu; Kareem El Naamani; Tanvir Rizvi

cs.CVOct 26, 2026

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

Authors: Natasha Ironside, Hongyu Kan, Kristofor Pas, Mohammad Shifat-E-Rabbi, Benjamin Newman, Shinjini Kundu, Kareem El Naamani, Tanvir Rizvi,

Organizations: Department of Neurological Surgery, University of Illinois Chicago, Chicago, Il · Department of Electrical and Computer Engineering, George Washington University, Washington, DC · Department of Biomedical Engineering, University of Virginia Health System, Charlottesville, VA · Department of Electrical and Computer Engineering, North South University, Dhaka, Bangladesh · Department of Radiology, University of Virginia Health System, Charlottesville, VA · Department of Radiology, Washington University in St. Louis, St. Louis, MO · Department of Neurological Surgery, University of Arizona College of Medicine, Tucson, AZ · Department of Neurological Surgery, University of Louisville, Louisville, KY · Department of Neurological Surgery, Tufts University Medical Center, Boston, MA · Department of Neurological Surgery, University of Virginia Health System, Charlottesville, VA · Department of Biostatistics, University of Virginia, Charlottesville, VA · Department of Neurology and Rehabilitation Medicine, University of Cincinnati, Cincinnati, OH · Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, NC · Department of Neurology, University of Buffalo, Buffalo, NY · Department of Neurology, Westchester Medical Center, Westchester, NY · Department of Neurological Surgery, Vagelos College of Physicians and Surgeons, Columbia University, New York, NY · Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA · VISTA-ICH Steering Committee: DF Hanley (Chair), K Butcher, S Davis, B Gregson, KR Lees, P Lyden, S Mayer, K Muir, and T Steiner

Abstract

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.

Clinical Prediction

Clinical prediction uses patient records, signals, and images to estimate diagnoses, risks, outcomes, and treatment responses for care.

See all 207 papers

HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion
Jun 13, 2026Orhun Utku Aydin, Satoru Tanioka, Tzu I Chuang +7Longitudinal Medical Image Analysis Clinical Prediction
CLAIM – Charité Lab for AI in Medicine, Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany · Department of Neurosurgery, Mie Chuo Medical Center, 2158-5 Myojin-cho,2026 514-1101, Hisai,Tsu, Japan
Forecasting Brain Tracer Distribution from Pre-Contrast MRI: A Comparison of Direct Regression and Flow Matching
Sep 17, 2026Qinghui Liu, Jon André Ottesen, Thu Nguyen +6Brain MRI Longitudinal Medical Image Analysis
Department of Physics and Computational Radiology, Oslo University Hospital, Oslo, Norway · Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Oslo, Norway · K.G. Jebsen Centre for Brain Fluid Research, University of Oslo, Oslo, Norway +4
Ischemic Stroke Segmentation and Net Water Uptake Quantification on Multicenter Non-Contrast CT Using Supervised Target-Domain Adaptation
Sep 17, 2026Linus Britt, Maximilian Nielsen, Susan Klapproth +5Medical Image Segmentation
Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf, Hamburg, Germany · Institute of Computational Neuroscience, University Medical Center Hamburg-Eppendorf, Hamburg, Germany · Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany +4

Jun 13, 2026J/K move · Enter open · S save

HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion

Orhun Utku Aydin, Satoru Tanioka, Tzu I Chuang, Alexander Koch+6

CLAIM – Charité Lab for AI in Medicine, Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany · Department of Neurosurgery, Mie Chuo Medical Center, 2158-5 Myojin-cho,2026 514-1101, Hisai,Tsu, Japan

Longitudinal Medical Image Analysis Clinical Prediction Medical Image Synthesis Conditional Diffusion Models

Open paper AskPDF arXiv

Hematoma expansion (HE) after spontaneous intracerebral hemorrhage (ICH) is a major determinant of acute triage and treatment decisions in neurosurgical care. However, most existing methods provide either a binary expansion risk or a single follow-up volume, limiting uncertainty-aware decisions. We introduce HemExp, a clinically-guided latent diffusion model that generates patient-specific follow-up non-contrast CT images, along with segmentations of intraparenchymal and intraventricular hemorrhage. Generation is conditioned on baseline imaging, clinical variables, and an explicit expansion indicator, enabling controllable simulation of realistic clinical scenarios. HemExp uses a hemorrhage-aware multi-head variational autoencoder and models progression as the difference between baseline and follow-up latent representations with a conditional diffusion model. The model is trained on paired scans from 450 patients across multiple centers and evaluated on 107 patients from a held-out institution. HemExp produces spatial HE probability maps by generating multiple synthetic follow-up images per patient to estimate distributions of plausible follow-up hematoma volumes. Perturbing clinical inputs such as symptom-onset-to-imaging time or anticoagulant status shifts the predicted follow-up volume distribution. HemExp extends binary predictors and demonstrates robust estimation of clinically relevant outcomes in the imaging space, such as hematoma volume, intraventricular involvement, and mass effects. Overall, our results support controllable latent diffusion as a promising direction for uncertainty-aware modeling of early ICH progression.

Abstract

Clinical Prediction

Explore similar work

HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion

Forecasting Brain Tracer Distribution from Pre-Contrast MRI: A Comparison of Direct Regression and Flow Matching

Ischemic Stroke Segmentation and Net Water Uptake Quantification on Multicenter Non-Contrast CT Using Supervised Target-Domain Adaptation