An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas

Abstract

Preoperative MRI is one of the most important clinical results for the diagnosis and treatment of glioma patients. The objective of this study was to construct a stable and validatable preoperative T2-weighted MRI-based radiomics model for predicting the survival of gliomas. A total of 652 glioma patients across three independent cohorts were covered in this study including their preoperative T2-weighted MRI images, RNA-seq and clinical data. Radiomic features (1731) were extracted from preoperative T2-weighted MRI images of 167 gliomas (discovery cohort) collected from Beijing Tiantan Hospital and then used to develop a radiomics prediction model through a machine learning-based method. The performance of the radiomics prediction model was validated in two independent cohorts including 261 gliomas from the The Cancer Genomae Atlas database (external validation cohort) and 224 gliomas collected in the prospective study from Beijing Tiantan Hospital (prospective validation cohort). RNA-seq data of gliomas from discovery and external validation cohorts were applied to establish the relationship between biological function and the key radiomics features, which were further validated by single-cell sequencing and immunohistochemical staining. The 14 radiomic features-based prediction model was constructed from preoperative T2-weighted MRI images in the discovery cohort, and showed highly robust predictive power for overall survival of gliomas in external and prospective validation cohorts. The radiomic features in the prediction model were associated with immune response, especially tumour macrophage infiltration. The preoperative T2-weighted MRI radiomics prediction model can stably predict the survival of glioma patients and assist in preoperatively assessing the extent of macrophage infiltration in glioma tumours.

M7G-related LncRNAs: A comprehensive analysis of the prognosis and immunity in glioma

“…For example, CD8 + T-cell infiltration is associated with poor prognosis in patients with BC ( Hou et al, 2020 ; Liu et al, 2020 ). High infiltration of tumour-associated macrophages was associated with low-grade glioma and thyroid cancer ( Ryder et al, 2008 ; Li et al, 2022 ). The number of mast cells was positively linked to poor prognosis in patients with prostate cancer ( Zhang et al, 2020 ).…”

A Survey of Radiomics in Precision Diagnosis and Treatment of Adult Gliomas

“…Therefore, the use of radiomics-based methods to predict the survival of patients with gliomas has become a clinical concern. The study of Li et al [95] indicated that the model based on radiomics features extracted from preoperative T2WI images of patients with gliomas can stably predict the survival of the patients, and radiomics features in predictive models were found to correlate with immune responses and facilitate the preoperative assessment of the extent of gliomas macrophage infiltration. Han et al [96] combined deep features generated by pre-trained CNN with conventional radiomics features to build a model to predict overall survival in patients with HGGs.…”

Applications of machine learning in tumor-associated macrophages

“…Applications of neural networks and DL in TAMs focus more on classification and medical image segmentation. Li et al developed an MRI radiomics approach to predict survival and tumor-infiltrating macrophages in gliomas (120). They used two neural network models and one long short-term memory DL model to divide patients into long and short-term survival clusters.…”