AUTHOR=Haider Stefan P. , Qureshi Adnan I. , Jain Abhi , Tharmaseelan Hishan , Berson Elisa R. , Zeevi Tal , Werring David J. , Gross Moritz , Mak Adrian , Malhotra Ajay , Sansing Lauren H. , Falcone Guido J. , Sheth Kevin N. , Payabvash Seyedmehdi 

TITLE=Radiomic markers of intracerebral hemorrhage expansion on non-contrast CT: independent validation and comparison with visual markers

JOURNAL=Frontiers in Neuroscience

VOLUME=17

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1225342

DOI=10.3389/fnins.2023.1225342

ISSN=1662-453X

ABSTRACT=<sec><title>Objective</title><p>To devise and validate radiomic signatures of impending hematoma expansion (HE) based on admission non-contrast head computed tomography (CT) of patients with intracerebral hemorrhage (ICH).</p></sec><sec><title>Methods</title><p>Utilizing a large multicentric clinical trial dataset of hypertensive patients with spontaneous supratentorial ICH, we developed signatures predictive of HE in a discovery cohort (<italic>n</italic> = 449) and confirmed their performance in an independent validation cohort (<italic>n</italic> = 448). In addition to <italic>n</italic> = 1,130 radiomic features, <italic>n</italic> = 6 clinical variables associated with HE, <italic>n</italic> = 8 previously defined visual markers of HE, the BAT score, and combinations thereof served as candidate variable sets for signatures. The area under the receiver operating characteristic curve (AUC) quantified signatures’ performance.</p></sec><sec><title>Results</title><p>A signature combining select radiomic features and clinical variables attained the highest AUC (95% confidence interval) of 0.67 (0.61–0.72) and 0.64 (0.59–0.70) in the discovery and independent validation cohort, respectively, significantly outperforming the clinical (<italic>p</italic><sub>discovery</sub> = 0.02, <italic>p</italic><sub>validation</sub> = 0.01) and visual signature (<italic>p</italic><sub>discovery</sub> = 0.03, <italic>p</italic><sub>validation</sub> = 0.01) as well as the BAT score (<italic>p</italic><sub>discovery</sub> &lt; 0.001, <italic>p</italic><sub>validation</sub> &lt; 0.001). Adding visual markers to radiomic features failed to improve prediction performance. All signatures were significantly (<italic>p</italic> &lt; 0.001) correlated with functional outcome at 3-months, underlining their prognostic relevance.</p></sec><sec><title>Conclusion</title><p>Radiomic features of ICH on admission non-contrast head CT can predict impending HE with stable generalizability; and combining radiomic with clinical predictors yielded the highest predictive value. By enabling selective anti-expansion treatment of patients at elevated risk of HE in future clinical trials, the proposed markers may increase therapeutic efficacy, and ultimately improve outcomes.</p></sec>