Radiomics-based prediction of intraoperative blood loss during intracranial meningiomas surgery

Filimonova, E.; Pashkov, A.; Poptsova, A.; Abdilatipov, A.; Barabanov, I.; Uzhakova, E.; Kalinovsky, A.; Rzaev, J.

Авторы: Filimonova Elena, Pashkov Anton, Poptsova Aleksandra, Abdilatipov Abdishukur, Barabanov Ilya, Uzhakova Elena, Kalinovsky Anton, Rzaev Jamil
Журнал: Neurosurgical Review
Номер: 48:681
Год издания: 2025
Издательство: Springer Verlag
Местоположение издательства: Germany
DOI: 10.1007/s10143-025-03802-9
Аннотация: AbstractMeningiomas surgery is frequently accompanied by substantial blood loss, which is associated with an increased incidenceof medical morbidities. Neuroimaging features, such as radiomic characteristics, could provide additional quantitativeinformation on the tumor. Nonetheless, the usefulness of radiomics in predicting intraoperative blood loss has yet to bevalidated. Our objective was to examine the potential of radiomics to predict intraoperative blood loss in patients withintracranial meningiomas. A total of 137 patients with primary diagnosed intracranial meningiomas were evaluated viahigh-resolution brain magnetic resonance imaging (MRI), which included T1-weighted pre- and postcontrast imaging,T2-weighted imaging, diffusion-weighted (with apparent diffusion coefficient) imaging, and arterial spin labeling (ASL).MRI data were processed with subsequent extraction of radiomic features. The most significant predictors were determinedvia random forest regression analysis to model the relationships between selected metrics and the rate of intraoperativebleeding. We created a regression model based on ten radiomic predictors, including first- and second-order radiomicfeatures. The resulting model allowed us to predict intraoperative blood loss in patients with intracranial meningiomaswith a mean absolute error of 135.14 ml and R-squared value of 0.29, which could be considered good prediction quality.Tumor volume, tumor location, histological grade, and surgery duration were found to be less significant predictors thanthe other parameters and did not improve the model. Radiomic features could be useful in predicting intraoperative bloodloss and provide valuable information for the presurgical evaluation of patients with intracranial meningiomas.
Добавил в систему: Абдилатипов Абдишукур Абдилатипович

	ИСТИНА	Войти в систему Регистрация
	ИСТИНА ПсковГУ
	Главная Поиск Статистика О проекте Помощь

ИСТИНА

ИСТИНА ПсковГУ

Radiomics-based prediction of intraoperative blood loss during intracranial meningiomas surgeryстатья