AUTHOR=Liu Yue , Chen Zhihong , Chen Junhao , Shi Zhenwei , Fang Gang 

TITLE=Pathologic complete response prediction in breast cancer lesion segmentation and neoadjuvant therapy

JOURNAL=Frontiers in Medicine

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1188207

DOI=10.3389/fmed.2023.1188207

ISSN=2296-858X

ABSTRACT=Objectives: Predicting whether axillary lymph nodes could achieve pathologic Complete Response (pCR) after breast cancer patient receiving neoadjuvant chemotherapy helps make quick follow-up treatment plan. This paper presents a novel method to achieve this prediction with the most effective medical imaging method, Dynamic Contrast-enhanced Magnetic Resonance Imaging (DCE-MRI). Methods: In order to get accurate prediction, we first propose a two-step lesion segmentation method to extract breast cancer lesion region from DCE-MRI images, and with the segmented breast cancer lesion region, we then use a multi-modal fusion model to predict the probability of axillary lymph nodes reaching pCR. Results: We collect 361 breast cancer samples from two hospitals to train and test the proposed segmentation model and the multi-modal fusion model. Both segmentation and prediction model obtain high accuracy. Conclusions: The results show that our method is effective in both segmentation task and pCR prediction task. It suggests that the presented methods, especially the multi-modal fusion model, can be used for prediction of treatment response in breast cancer given data merely from noninvasive methods.