Prediction of Axillary Lymph Node Metastasis Status in Breast Cancer Based on PET/CT Radiomics

A Study on the Construction of a Comprehensive Predictive Model for Axillary Lymph Node Metastasis in Breast Cancer

Patients with suspected breast cancer undergoing PET/CT at our hospital. The PET/CT center's chief physician and senior attending physician reviewed the films together and disagreement, if any, was resolved by consensus. The lesion was visually identified. A 3D region of interest(ROI) of the lesion was automatically outlined using the 40% threshold method, and PET metabolic parameters were measured . Breast lesions with radionuclide concentrations greater than those in normal breast tissue are considered to be breast cancer lesions, while lymph nodes with radionuclide concentrations greater than those in muscle tissue are considered to be metastatic lymph nodes.

Image segmentation: Image segmentation was performed using ITK-SNAP software (4) (version 3.6.0, http://www.itksnap.org/), Brush Style: circular, Brush Size: 10, Brush Options: 3D. The entire tumor volume was outlined on the PET image as ROI for segmentation.

An open source Python package (PyRadiomics version 3.0.1(5)) was used to extract the radiomics features from the ROI.

Univariate and multivariate binary logistic regressions were used to construct model for predicting lymph node metastasis in breast cancer.

Inclusion Criteria:

• 1) 18F-FDG PET/CT for breast occupancy; 2) adult female patients with pathologically confirmed breast cancer (age ≥18 years); 3) no history of surgery, radiotherapy, or chemotherapy before 18F-FDG PET/CT; and 4) interval between 18F-FDG PET/CT and puncture/surgery ≤2 weeks.

Exclusion Criteria:

• 1) multifocal, bilateral, or occult breast cancer; 2) incomplete clinical or pathological data; 3) poor PET/CT image quality, when metabolic tumor volume(MTV) cannot be automatically segmented; and 4) concomitant malignant tumors.