Related Experiment Video
Updated: Jul 1, 2025
09:32
Multiplexed Immunofluorescence Analysis and Quantification of Intratumoral PD-1+ Tim-3+ CD8+ T Cells
Published on: February 8, 2018
14.6K
Computed Tomography-Based Radiomics to Predict FOXM1 Expression and Overall Survival in Patients with Clear Cell
Jingwei Zhao1, Qi Zhang1, Yan Chen1
1Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.
Academic Radiology
|March 13, 2024
Summary
A radiomics signature (Rad-score) accurately predicts Forkhead box M1 (FOXM1) expression in clear cell renal cell carcinoma (ccRCC). This, combined with clinical factors, offers a superior prognostic prediction model for ccRCC patients.
Area of Science:
- Radiology and Oncology
- Medical Imaging Analysis
- Cancer Biomarkers
Background:
- Forkhead box M1 (FOXM1) is a key regulator in cell proliferation and has been implicated in clear cell renal cell carcinoma (ccRCC) pathogenesis.
- Accurate prediction of FOXM1 expression levels and patient prognosis is crucial for effective ccRCC management.
- Computed tomography (CT)-based radiomics offers a non-invasive method to extract quantitative imaging features for predicting tumor characteristics.
Purpose of the Study:
- To develop a CT-based radiomics model for predicting FOXM1 expression levels in ccRCC.
- To establish a combined prognostic prediction model integrating radiomics and clinical factors for ccRCC patients.
- To evaluate the predictive performance of the radiomics signature (Rad-score) and the combined model against traditional prognostic factors.
Main Methods:
- A cohort of 529 patients with ccRCC was analyzed to assess FOXM1 prognostic significance.
- A radiomics signature (Rad-score) was developed in a training cohort (n=184) using CT images to predict FOXM1 expression.
- Cox regression analyses were used to build clinical and combined models (clinical factors + Rad-score) for prognostic prediction, with performance assessed by concordance index (C-index).
Main Results:
- The Rad-score demonstrated high accuracy in predicting high FOXM1 expression, with an area under the ROC curve of 0.713 in the training cohort.
- The combined model achieved the highest C-index (0.741 in training, 0.745 in validation), significantly outperforming the Rad-score, TNM stage, and clinical model alone.
- The Rad-score was identified as an independent prognostic factor for ccRCC.
Conclusions:
- A CT-based radiomics signature (Rad-score) can accurately predict FOXM1 expression levels in ccRCC.
- The developed Rad-score is an independent prognostic factor for ccRCC.
- A combined model incorporating the Rad-score and clinical factors provides superior prognostic prediction for ccRCC patients.
