Can we skip invasive biopsy of sentinel lymph nodes? A preliminary investigation to predict sentinel lymph node status using PET/CT-based radiomics

  • 0Department of PET/CT, Harbin Medical University Cancer Hospital, Harbin, 150001, China.

|

|

Summary

This summary is machine-generated.

This study shows that 2-deoxy-2-[<sup>18</sup>F]fluoro-d-glucose positron emission tomography/computed tomography (<sup>18</sup>F-FDG-PET/CT) radiomics can accurately predict sentinel lymph node (SLN) metastasis in invasive ductal breast cancer (IDC) patients non-invasively.

Area Of Science

  • Oncology
  • Radiology
  • Medical Imaging

Background

  • Sentinel lymph node biopsy (SLNB) is standard for detecting breast cancer metastasis but is invasive.
  • Complications associated with SLNB necessitate the development of less invasive diagnostic methods.
  • Evaluating non-invasive techniques for SLN metastasis assessment in invasive ductal cancer (IDC) is crucial.

Purpose Of The Study

  • To assess the diagnostic performance of non-invasive radiomics analysis using <sup>18</sup>F-FDG-PET/CT for SLN metastasis in IDC patients.
  • To identify predictors of SLN metastasis through clinical and metabolic parameters.
  • To develop and validate predictive models for SLN status.

Main Methods

  • Retrospective analysis of 132 IDC patients who underwent <sup>18</sup>F-FDG-PET/CT before surgery.
  • Extraction of radiomic features from PET and CT scans.
  • Development of prediction models using Random Forest (RF), Decision Tree (DT), and k-Nearest Neighbors (KNN) classifiers.

Main Results

  • Multivariate analysis identified Ki 67 and tumor-to-liver ratio (TLG) as independent predictors.
  • The RF model achieved the highest AUC of 0.887 in the training cohort and 0.856 in the validation cohort.
  • Radiomic features combined with clinical variables showed high accuracy in predicting SLN metastasis.

Conclusions

  • <sup>18</sup>F-FDG-PET/CT radiomics offers a robust, non-invasive method for predicting SLN status in IDC.
  • This approach can aid in personalized treatment planning for breast cancer patients.
  • Non-invasive radiomics may reduce the need for invasive SLNB procedures.