Breast Cancer Subtype Prediction Model Employing Artificial Neural Network and 18F-Fluorodeoxyglucose Positron Emission Tomography/ Computed Tomography

Abstract

Introduction: Although positron emission tomography/computed tomography (PET/CT) is a common tool for measuring breast cancer (BC), subtypes are not automatically classified by it. Therefore, the purpose of this research is to use an artificial neural network (ANN) to evaluate the clinical subtypes of BC based on the value of the tumor marker.

Materials and methods: In our nuclear medical facility, 122 BC patients (training and testing) had ¹⁸F-fluoro-D-glucose (¹⁸F-FDG) PET/CT to identify the various subtypes of the disease. ¹⁸F-FDG-18 injections were administered to the patients before the scanning process. We carried out the scan according to protocol. Based on the tumor marker value, the ANN's output layer uses the Softmax function with cross-entropy loss to detect different subtypes of BC.

Results: With an accuracy of 95.77%, the result illustrates the ANN model for K-fold cross-validation. The mean values of specificity and sensitivity were 0.955 and 0.958, respectively. The area under the curve on average was 0.985.

Conclusion: Subtypes of BC may be categorized using the suggested approach. The PET/CT may be updated to diagnose BC subtypes using the appropriate tumor maker value when the suggested model is clinically implemented.

Keywords: 18F-fluoro-D-glucose positron emission tomography/computed tomography; artificial neural network; breast cancer; histological subtypes; prediction model.

Figure 1

The illustration for estimating histological subtypes for breast cancer using an artificial neural network based on the value of the tumor maker. ¹⁸F-FDG: ¹⁸F-fluoro-D-glucose, PET/CT: Positron emission tomography/computed tomography, ANN: Artificial neural network

Figure 2

¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography for breast cancer. (a) PET/CT fusion image (axial section). The blue arrow indicates breast cancer (upper left). (b) CT image in Axial section (Upper Right). (c) PET image in Axial Section (lower left). (d) PET image in coronal section (Lower Right)

Figure 3

Artificial neural networks for obtaining subtypes (invasive ductal cancer, invasive lobular cancer, and others) used the sigmoid function as a hidden layer and output layer with the Softmax function. ILC: Invasive lobular cancer, IDC: Invasive ductal cancer

Figure 4

(a) The expression for the value of attributes for invasive ductal cancer, (b) The expression for the value of attributes for invasive lobular cancer, and (c) The expression for the value of attributes for other subtypes. The significance (P < 0.05) is indicated by the asterisk. ILC: Invasive lobular cancer, IDC: Invasive ductal cancer

Figure 5

The receiver operating characteristic curve for invasive ductal cancer, invasive lobular cancer, and other subtypes of breast cancer. AUC: Area under the curve, ILC: Invasive lobular cancer, IDC: Invasive ductal cancer