An MRI radiomics approach to discriminate haemorrhage-prone intracranial tumours before stereotactic biopsy.

PURPOSE: To explore imaging biomarkers predictive of intratumoral haemorrhage for lesions intended for elective stereotactic biopsy. METHOD: This study included a retrospective cohort of 143 patients with 175 intracranial lesions intended for stereotactic biopsy. All the lesions were randomly split into a training dataset ( n =121) and a test dataset ( n =54) at a ratio of 7:3. Thirty-four lesions were defined as "hemorrhage-prone tumors" as haemorrhage occurred between initial diagnostic MRI acquisition and the scheduled biopsy procedure. Radiomics features were extracted from the contrast-enhanced T1 Weighted Imaging and T2 Weighted Imaging images. Features informative of haemorrhage were then selected by the LASSO algorithm, and an Support Vector Machine model was built with selected features. The Support Vector Machine model was further simplified by discarding features with low importance and calculating them using a "permutation importance" method. The model's performance was evaluated with confusion matrix-derived metrics and area under curve (AUC) values on the independent test dataset. RESULTS: Nine radiomics features were selected as haemorrhage-related features of intracranial tumours by the LASSO algorithm. The simplified model's sensitivity, specificity, accuracy, and AUC reached 0.909, 0.930, 0.926, and 0.949 (95% CI: 0.865-1.000) on the test dataset in the discrimination of "hemorrhage-prone tumors". The permutation method rated feature "T2_gradient_firstorder_10Percentile" as the most important, the absence of which decreased the model's accuracy by 10.9%. CONCLUSION: Radiomics features extracted on contrast-enhanced T1 Weighted Imaging and T2 Weighted Imaging sequences were predictive of future haemorrhage of intracranial tumours with favourable accuracy. This model may assist in the arrangement of biopsy procedures and the selection of target lesions in patients with multiple lesions.

Rupture-Related Features of Cerebral Arteriovenous Malformations and Their Utility in Predicting Hemorrhage.

BACKGROUND: Evaluating rupture risk in cerebral arteriovenous malformations currently lacks quantitative hemodynamic and angioarchitectural features necessary for predicting subsequent hemorrhage. We aimed to derive rupture-related hemodynamic and angioarchitectural features of arteriovenous malformations and construct an ensemble model for predicting subsequent hemorrhage. METHODS: This retrospective study included 3 data sets, as follows: training and test data sets comprising consecutive patients with untreated cerebral arteriovenous malformations who were admitted from January 2015 to June 2022 and a validation data set comprising patients with unruptured arteriovenous malformations who received conservative treatment between January 2009 and December 2014. We extracted rupture-related features and developed logistic regression (clinical features), decision tree (hemodynamic features), and support vector machine (angioarchitectural features) models. These 3 models were combined into an ensemble model using a weighted soft-voting strategy. The performance of the models in discriminating ruptured arteriovenous malformations and predicting subsequent hemorrhage was evaluated with confusion matrix-related metrics in the test and validation data sets. RESULTS: A total of 896 patients (mean±SD age, 28±14 years; 404 women) were evaluated, with 632, 158, and 106 patients in the training, test, and validation data sets, respectively. From the training set, 9 clinical, 10 hemodynamic, and 2912 pixel-based angioarchitectural features were extracted. A logistic regression model was built using 4 selected clinical features (age, nidus size, location, and venous aneurysm), whereas a decision-tree model was constructed from 4 hemodynamic features (outflow time, stasis index, cerebral blood flow, and outflow volume ratio). A support vector machine model was designed using 5 pixel-based angioarchitectural features. In the validation data set, the accuracy, sensitivity, specificity, and area under the curve of the ensemble model for predicting subsequent hemorrhages were 0.840, 0.889, 0.823, and 0.911, respectively. CONCLUSIONS: The ensemble model incorporating clinical, hemodynamic, and angioarchitectural features showed favorable performance in predicting subsequent hemorrhage of cerebral arteriovenous malformations.