Survival-relevant high-risk subregion identification for glioblastoma patients: the MRI-based multiple instance learning approach

• Published in: European radiology 2020-10, Vol.30 (10), p.5602-5610
• Main Authors: Zhang, Xi, Lu, Di, Gao, Peng, Tian, Qiang, Lu, Hongbing, Xu, Xiaopan, He, Xiaowei, Liu, Yang
• Format: Article
• Language: English
• Subjects: Adult; Aged; Algorithms; Brain cancer; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - mortality; Cluster Analysis; Clustering; Diagnostic Radiology; Female; Glioblastoma; Glioblastoma - diagnostic imaging; Glioblastoma - mortality; Glioma; Glioma - diagnostic imaging; Glioma - mortality; Heterogeneity; Humans; Image Processing, Computer-Assisted; Imaging; Internal Medicine; Interventional Radiology; Learning; Machine Learning; Magnetic Resonance Imaging; Male; Medical prognosis; Medicine; Medicine & Public Health; Middle Aged; Motion; Neuro; Neuroradiology; Prognosis; Radiology; Radiomics; Reproducibility of Results; Retrospective Studies; Risk; Survival; Survival Analysis; Treatment Outcome; Ultrasound; Vector quantization
• ISSN: 0938-7994; 1432-1084
• DOI: 10.1007/s00330-020-06912-8

Objectives Given the glioblastoma (GBM) heterogeneity, survival-relevant high-risk subregions may exist and facilitate prognosis. The study aimed to identify the high-risk subregions on MRI, and to evaluate their survival stratification performance. Methods The gross tumor regions (GTRs) were delineated on the normalized MRI of 104 GBM patients. The signal intensity of voxels from 104 GTRs was pooled as global intensity vector, and K-means clustering was performed on it to find the optimal global clusters. Subregions were generated by assigning back voxels that belonged to each global cluster. Finally, a multiple instance learning (MIL) model was built and validated using radiomics features from each subregion. In this process, subregions predicted as positive would be treated as high-risk subregions, and patients with high-risk subregions inside the GTR would be predicted as having short-term survival. Results After K-means clustering, three global clusters were fixed and 294 subregions of 104 patients were generated. Then, the subregion-level MIL model was trained and tested by 200 (71 patients) and 94 subregions (33 patients). The accuracy, sensitivity, and specificity for survival stratification were 87.88%, 85.71%, and 89.47%. Furthermore, 41 high-risk subregions were correctly predicted from patients with short-term survival, in which the median overlap rate of non-enhancing component was 60%. Conclusion The stratification performance of high-risk subregions identified by the MIL model was higher than the GTR. The non-enhancing area on MRI was the most important component in high-risk subregions. The MIL approach provides a new perspective on the clinical challenges of glioma with coarse-grained labeling. Key Points • The performance of high-risk subregions was more promising than the GTR for OS stratification. • The non-enhancing component was the most important in the high-risk subregions.