Journal
JOURNAL OF TRANSLATIONAL MEDICINE
Volume 20, Issue 1, Pages -Publisher
BMC
DOI: 10.1186/s12967-022-03688-x
Keywords
Radiomics; Tumor-infiltrating lymphocytes (TILs); Triple-negative breast cancer (TNBC); Tumor microenvironment (TME); Magnetic resonance imaging (MRI)
Categories
Funding
- National Natural Science Foundation of China [81901703, 82071878, 82271957, 91959207, 92159301]
- Shanghai Science and Technology Innovation Program [22Y11912700]
- Youth Medical Talents-Clinical Imaging Practitioner Program [SHWRS (2020) 087]
- Clinical Research Plan of SHDC [SHDC2020CR2008A, SHDC12021103]
- SHDC Municipal Project for Developing Emerging and Frontier Technology in Shanghai Hospitals [SHDC12021103]
Ask authors/readers for more resources
This study demonstrated the feasibility of a radiomics model in predicting TILs status and provided a method to interpret the features, which could pave the way for precision medicine in TNBC.
Background Tumor-infiltrating lymphocytes (TILs) have become a promising biomarker for assessing tumor immune microenvironment and predicting immunotherapy response. However, the assessment of TILs relies on invasive pathological slides. Methods We retrospectively extracted radiomics features from magnetic resonance imaging (MRI) to develop a radiomic cohort of triple-negative breast cancer (TNBC) (n = 139), among which 116 patients underwent transcriptomic sequencing. This radiomic cohort was randomly divided into the training cohort (n = 98) and validation cohort (n = 41) to develop radiomic signatures to predict the level of TILs through a non-invasive method. Pathologically evaluated TILs in the H&E sections were set as the gold standard. Elastic net and logistic regression were utilized to perform radiomics feature selection and model training, respectively. Transcriptomics was utilized to infer the detailed composition of the tumor microenvironment and to validate the radiomic signatures. Results We selected three radiomics features to develop a TILs-predicting radiomics model, which performed well in the validation cohort (AUC 0.790, 95% confidence interval (CI) 0.638-0.943). Further investigation with transcriptomics verified that tumors with high TILs predicted by radiomics (Rad-TILs) presented activated immune-related pathways, such as antigen processing and presentation, and immune checkpoints pathways. In addition, a hot immune microenvironment, including upregulated T cell infiltration gene signatures, cytokines, costimulators and major histocompatibility complexes (MHCs), as well as more CD8(+) T cells, follicular helper T cells and memory B cells, was found in high Rad-TILs tumors. Conclusions Our study demonstrated the feasibility of radiomics model in predicting TILs status and provided a method to make the features interpretable, which will pave the way toward precision medicine for TNBC.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available