JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Sub-regional Radiomics Analysis for Predicting Metastasis Risk in Clear Cell Renal Cell Carcinoma: A Multicenter Retrospective Study

  • 0Department of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Shandong Province, China.
Academic Radiology +

|

August 15, 2024

|

August 15, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a non-invasive imaging model to predict clear cell renal cell carcinoma (ccRCC) metastasis risk. The radiomics approach accurately identifies high-risk patients for early intervention and improved survival.

Area Of Science

  • Oncology
  • Radiology
  • Medical Imaging

Background

  • Clear cell renal cell carcinoma (ccRCC) is the most common kidney cancer.
  • Metastatic ccRCC has a poor prognosis, highlighting the need for early detection biomarkers.
  • Understanding ccRCC composition is key to developing sensitive diagnostic tools.

Purpose Of The Study

  • To predict the risk of metastasis in clear cell renal cell carcinoma (ccRCC) using habitat imaging and multimodal data.
  • To enable early intervention and improve patient survival rates through precise risk stratification.
  • To explore the clinical utility of radiomics in assessing ccRCC metastasis risk.

Main Methods

  • Retrospective analysis of 263 ccRCC patients' preoperative CT, ultrasound, and clinical data.
  • Consensus clustering to define tumor sub-regions (habitats) from contrast-enhanced CT images.
  • Radiomic feature extraction and reduction to build predictive models for metastasis risk.

Main Results

  • A risk prediction model integrating CT, ultrasound, and clinical data achieved an AUC of 0.935 in the training set and 0.891 in the testing set.
  • The CT_Habitat3 model demonstrated strong predictive performance with an AUC of 0.934 (training) and 0.903 (testing).
  • Identified distinct tumor subregions with significant discriminative power for metastasis risk assessment.

Conclusions

  • A non-invasive imaging predictor, specifically a sub-regional radiomics model, accurately predicts ccRCC metastasis risk.
  • This predictive tool shows potential for clinical application in refining individualized treatment strategies.
  • The findings support the use of advanced imaging analysis for improved ccRCC patient management.

Keywords: