Prediction of Malignant Acute Middle Cerebral Artery Infarction via Computed Tomography Radiomics.

Xuehua Wen,Xuehua Wen,Xiaodong He,Xiaodong He,Yuyun Xu,Xingfei Hu,Xingfei Hu,Hongyang Jiang,Hongyang Jiang,Xiangyang Gong,Xiangyang Gong,Yumei Li,Yumei Li,Zhenyu Shu,Zhenyu Shu,Junfa Chen,Junfa Chen

doi:10.3389/fnins.2020.00708

Abstract

Malignant middle cerebral artery infarction (mMCAi) is a serious complication of cerebral infarction usually associated with poor patient prognosis. In this retrospective study, we analyzed clinical information as well as non-contrast computed tomography (NCCT) and computed tomography angiography (CTA) data from patients with cerebral infarction in the middle cerebral artery (MCA) territory acquired within 24 h from symptoms onset. Then, we aimed to develop a model based on the radiomics signature to predict the development of mMCAi in cerebral infarction patients. Patients were divided randomly into training (n = 87) and validation (n = 39) sets. A total of 396 texture features were extracted from each NCCT image from the 126 patients. The least absolute shrinkage and selection operator regression analysis was used to reduce the feature dimension and construct an accurate radiomics signature based on the remaining texture features. Subsequently, we developed a model based on the radiomics signature and Alberta Stroke Program Early CT Score (ASPECTS) based on NCCT to predict mMCAi. Our prediction model showed a good predictive performance with an AUC of 0.917 [95% confidence interval (CI), 0.863–0.972] and 0.913 [95% CI, 0.795–1] in the training and validation sets, respectively. Additionally, the decision curve analysis (DCA) validated the clinical efficacy of the combined risk factors of radiomics signature and ASPECTS based on NCCT in the prediction of mMCAi development in patients with acute stroke across a wide range of threshold probabilities. Our research indicates that radiomics signature can be an instrumental tool to predict the risk of mMCAi.

Highlights

Malignant middle cerebral artery infarction is a life-threatening complication that is usually observed in relatively young patients with a large middle cerebral artery (MCA) infarction (Hacke et al, 1996)
Inclusion criteria included: (1) patients with symptoms related to cerebral infarction; (2) patients who underwent baseline non-contrast computed tomography (NCCT) and computed tomography angiography (CTA) prior to treatment as well as within 24 h from symptoms onset and follow-up NCCT; (3) patients with MCA M1 occlusion proved by baseline CTA and acute MCA infarction proved by follow-up NCCT
Exclusion criteria included: (1) the presence of old lesions with diameter >1.5 cm, post-operative changes, acute cerebral hemorrhage, acute cerebral traumatic changes or spaceoccupying mass in the ipsilateral hemisphere as indicated by the baseline or follow-up CT; (2) a modified Rankin Scale score >2 prior to the current stroke; (3) patients who participated in other studies and those receiving experimental drugs or treatments; (4) patients suffering from end-stage diseases and those with expected survival period ≤1 year; (5) NCCT image artifacts or other reasons that hinder image interpretation; (6) follow-up CT indicating simultaneous cerebral infarction in the territory of the anterior or posterior cerebral artery

Summary

Introduction

Malignant middle cerebral artery infarction (mMCAi) is a life-threatening complication that is usually observed in relatively young patients with a large middle cerebral artery (MCA) infarction (Hacke et al, 1996). To the best of our knowledge, there are no standardized parameters that can define mMCAi especially in the early stages. Several clinical and standard visual radiological parameters have been studied as possible predictors for the development of mMCAi (Thomalla et al, 2010). Thomalla et al (2010) defined mMCAi as follows: (1) clinical signs of large MCA territory infarction with a NIHSS score >18 and a level of consciousness of ≥1 on item 1a of the NIHSS either on admission or after secondary deterioration; (2) large space-occupying MCA infarction on follow-up MRI or CT occupying at least twothirds of the MCA territory with compression of ventricles or midline shift; and (3) no other obvious causes for neurological deterioration. Shimoyama et al (2014) defined mMCAi as clinical deterioration, midline shift ≥5 mm, or brain herniation within 48 h of admission

Objectives

Methods

Results

Conclusion