An MRI radiomics approach to discriminate hemorrhage prone intracranial tumors before stereotactic biopsy

Yupeng Zhang; Tingliang Cao; Haoyu Zhu; Yuqi Song; Changxuan Li; Chuhan Jiang; Chao Ma

doi:10.1097/JS9.0000000000001396

An MRI radiomics approach to discriminate hemorrhage prone intracranial tumors before stereotactic biopsy

Int J Surg. 2024 Mar 28. doi: 10.1097/JS9.0000000000001396. Online ahead of print.

Authors

Yupeng Zhang^{1

2}, Tingliang Cao³, Haoyu Zhu^{1

2}, Yuqi Song^{1

2}, Changxuan Li⁴, Chuhan Jiang^{1

2}, Chao Ma⁵

Affiliations

¹ Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
² Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.
³ Department of Neurosurgery, Kaifeng Central Hospital, Henan, China.
⁴ Department of Neurosurgery, The first affiliated hospital of Hainan Medical University, Hainan, China.
⁵ Department of Neurosurgery, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China.

PMID: 38537059
DOI: 10.1097/JS9.0000000000001396

Abstract

Purpose: To explore imaging biomarkers predictive of intratumoral hemorrhage 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. 34 lesions were defined as "hemorrhage-prone tumors" as hemorrhage occurred between initial diagnostic MRI acquisition and the scheduled biopsy procedure. Radiomics features were extracted from the contrast-enhanced T1WI and T2WI images. Features informative of hemorrhage were then selected by the LASSO algorithm and an SVM model was built with selected features. The SVM model was further simplified by discarding features with low importance calculated using a "permutation importance" method. The model's performance was evaluated with confusion matrix-derived metrics and AUC value on the independent test dataset.

Results: Nine radiomics features were selected as hemorrhage related features of intracranial tumors 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 T1WI and T2WI sequences were predictive of future hemorrhage of intracranial tumors with favorable accuracy. This model may assist in the arrangement of biopsy procedures and the selection of target lesions in patients with multiple lesions.