Deep learning with biopsy whole slide images for pretreatment prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer：A multicenter study. (December 2022)

• Record Type: Journal Article
• Authors: Li, Bao; Li, Fengling; Liu, Zhenyu; Xu, FangPing; Ye, Guolin; Li, Wei; Zhang, Yimin; Zhu, Teng; Shao, Lizhi; Chen, Chi; Sun, Caixia; Qiu, Bensheng; Bu, Hong; Wang, Kun; Tian, Jie
• Is Part Of: Breast. Volume 66(2022)
• Page Start: 183
• Page End: 190
• Publication Date: 2022-12
• Subjects: Breast cancer -- Neoadjuvant chemotherapy -- Pathological complete response -- Whole-slide image -- Deep learning; Breast -- Diseases -- Periodicals; Breast -- Tumors -- Periodicals; Breast -- Periodicals; Electronic journals; Periodicals; 616
• DOI: 10.1016/j.breast.2022.10.004
• Languages: English
• ISSNs: 0960-9776

Abstract

Abstract: Introduction: Predicting pathological complete response (pCR) for patients receiving neoadjuvant chemotherapy (NAC) is crucial in establishing individualized treatment. Whole-slide images (WSIs) of tumor tissues reflect the histopathologic information of the tumor, which is important for therapeutic response effectiveness. In this study, we aimed to investigate whether predictive information for pCR could be detected from WSIs. Materials and methods: We retrospectively collected data from four cohorts of 874 patients diagnosed with biopsy-proven breast cancer. A deep learning pathological model (DLPM) was constructed to predict pCR using biopsy WSIs in the primary cohort, and it was then validated in three external cohorts. The DLPM could generate a deep learning pathological score (DLPs) for each patient; stromal tumor-infiltrating lymphocytes (TILs) were selected for comparison with DLPs. Results: The WSI feature-based DLPM showed good predictive performance with the highest area under the curve (AUC) of 0.72 among the cohorts. Alternatively, the combination of the DLPM and clinical characteristics offered a better prediction performance (AUC >0.70) in all cohorts. We also evaluated the performance of DLPM in three different breast subtypes with the best prediction for the triple-negative breast cancer (TNBC) subtype (AUC: 0.73). Moreover, DLPM combined with clinical characteristics and stromal TILs achieved the highest AUC in the primary cohort (AUC: 0.82) and validation cohort 1 (AUC: 0.80). Conclusion: Our study suggested that WSIs integrated with deep learning could potentially predict pCR to NAC in breast cancer. The predictive performance will be improved by combining clinical characteristics. DLPs from DLPM can provide more information compared to stromal TILs for pCR prediction. Highlights: Whole-slide images integrated with deep learning can predict therapeutic response. Predictive performance could be improved by combing clinical characteristics. Deep learning pathological scores could provide more complementary information compare to TILs.