Prediction of pathological complete response to neoadjuvant chemotherapy in locally advanced breast cancer by using a deep learning model with 18F-FDG PET/CT

Abstract

Objectives: The aim of the study is 18F-FDG PET/CT imaging by using deep learning method are predictive for pathological complete response pCR after Neoadjuvant chemotherapy (NAC) in locally advanced breast cancer (LABC).

Introduction: NAC is the standard treatment for locally advanced breast cancer (LABC). Pathological complete response (pCR) after NAC is considered a good predictor of disease-free survival (DFS) and overall survival (OS).Therefore, there is a need to develop methods that can predict the pCR at the time of diagnosis.

Methods: This article was designed as a retrospective chart study.For the convolutional neural network model, a total of 355 PET/CT images of 31 patients were used. All patients had primary breast surgery after completing NAC.

Results: Pathological complete response was obtained in a total of 9 patients. The study results show that our proposed deep convolutional neural networks model achieved a remarkable success with an accuracy of 84.79% to predict pathological complete response.

Conclusion: It was concluded that deep learning methods can predict breast cancer treatment.

Fig 1. [Deep convolutional neural networks model]: Diagram of image cropping for the residual deep convolutional neural networks algorithm.

The cubic shaped region-of-interest was selected at the largest cross-sectional area of the lesion and resized to 224 × 224 pixels. (a) pCR: 0 (b) pCR: 1.

Fig 2. Residual learning block.

Fig 3. The basic architecture of ResNet-152.

Fig 4. [Area under the curve)] The classification performance using AUC (area under the curve) and accuracy analysis for each group.

Fig 5. [Receiver operating characteristic curves] Receiver operating characteristic (ROC) curves of ResNet-152 on ¹⁸F-FDG PET/CT images for each cross-validation group.