Prediction of prognosis in acute ischemic stroke after mechanical thrombectomy based on multimodal MRI radiomics and deep learning

Abstract

Background: Acute ischemic stroke (AIS) is a major global health threat associated with high rates of disability and mortality, highlighting the need for early prognostic assessment to guide treatment. Currently, there are no reliable methods for the early prediction of poor prognosis in AIS, especially after mechanical thrombectomy. This study aimed to explore the value of radiomics and deep learning based on multimodal magnetic resonance imaging (MRI) in predicting poor prognosis in patients with AIS who underwent mechanical thrombectomy. This study aimed to provide a more accurate and comprehensive tool for stroke prognosis.

Methods: This study retrospectively analyzed the clinical data and multimodal MRI images of patients with stroke at admission. Logistic regression was employed to identify the risk factors associated with poor prognosis and to construct a clinical model. Radiomics features of the stroke-affected regions were extracted from the patients' baseline multimodal MRI images, and the optimal radiomics features were selected using a least absolute shrinkage and selection operator regression model combined with five-fold cross-validation. The radiomics score was calculated based on the feature weights, and machine learning techniques were applied using a logistic regression classifier to develop the radiomics model. In addition, a deep learning model was devised using ResNet101 and transfer learning. The clinical, radiomics, and deep learning models were integrated to establish a comprehensive multifactorial logistic regression model, termed the CRD (Clinic-Radiomics-Deep Learning) model. The performance of each model in predicting poor prognosis was assessed using receiver operating characteristic (ROC) curve analysis, with the optimal model visualized as a nomogram. A calibration curve was plotted to evaluate the accuracy of nomogram predictions.

Results: A total of 222 patients with AIS were enrolled in this study in a 7:3 ratio, with 155 patients in the training cohort and 67 in the validation cohort. Statistical analysis of clinical data from the training and validation cohorts identified two independent risk factors for poor prognosis: the National Institutes of Health Stroke Scale score at admission and the occurrence of intracerebral hemorrhage. Of the 1,197 radiomic features, 16 were selected to develop the radiomics model. Area under the ROC curve (AUC) analysis of specific indicators demonstrated varying performances across methods and cohorts. In the training cohort, the clinical, radiomics, deep learning, and integrated CRD models achieved AUC values of 0.762, 0.755, 0.689, and 0.834, respectively. In the validation cohort, the clinical model exhibited an AUC of 0.874, the radiomics model achieved an AUC of 0.805, the deep learning model attained an AUC of 0.757, and the CRD model outperformed all models, with an AUC of 0.908. Calibration curves indicated that the CRD model showed exceptional consistency and accuracy in predicting poor prognosis in patients with AIS. Decision curve analysis revealed that the CRD model offered the highest net benefit compared with the clinical, radiomics, and deep learning models.

Conclusion: The CRD model based on multimodal MRI demonstrated high diagnostic efficacy and reliability in predicting poor prognosis in patients with AIS who underwent mechanical thrombectomy. This model holds considerable potential for assisting clinicians with risk assessment and decision-making for patients experiencing ischemic stroke.

Keywords: acute ischemic stroke; deep learning; multimodal MRI; prognosis; radiomics.

Figure 1

Workflow of the study. (A) Study flowchart of participant selection. (B) Workflow of the radiomics and deep learning analysis of AIS.

Figure 2

Based on the manually delineated regions of interest for patients with stroke, (A–C) represent the T1WI, FLAIR, and DWI sequences, respectively.

Figure 3

Utilization of the LASSO algorithm for feature selection. (A) The LASSO model employs five-fold cross-validation to select and fine-tune the parameters (λ). (B) Each colored line represents the coefficient of a specific feature, resulting in the final selection of 16 radiomic features (C).

Figure 4

(A,B) Receiver operating characteristic curves showing that the CRD model exhibited significantly higher AUC values than the other methods in both cohorts. (C,D) Calibration curves showing that the CRD model exhibited exceptional consistency and calibration in predicting a poor prognosis for patients with AIS.

Figure 5

(A,B) The DeLong test was applied to both the training and validation cohorts to evaluate the statistical significance of the differences between the models. (C,D) DCA curves demonstrating that the CRD model offers the greatest net benefit compared to the clinical, radiomics, and deep learning models. (E) A nomogram was constructed for the CRD model based on the NIHSS score at admission, ICH, radiomics score, and deep learning score.