Abstract 332P
Background
Neoadjuvant chemotherapy (NAC) has been a standard treatment for locally advanced breast cancer (BC). However, the high heterogeneity of BC results in various tumor response. Therefore, there is a growing need for early assessment of tumor response, particularly for insensitive BC, to guide personalized treatment. We aim to develop a longitudinal radiomics multitask model to accurately predict RCB score in the early stage of NAC for breast cancer.
Methods
A total of 1048 patients with breast cancer receiving NAC across four institutions were retrospectively enrolled. We collected longitudinal MRI sequences at the pre-NAC and mid-NAC timepoints, and extracted 21804 radiomics features per patient. We used a multitask learning strategy to predict RCB score (RCB 0-I, II and III). The Mann-Whitney U-test, Spearman analysis, the least absolute shrinkage and selection operator regression and Boruta method were used to perform feature selection. We developed various base machine learning models, followed by an ensemble stacking method to integrate the base model outputs. The multitask learning model was subsequently verified in three independent external validation cohorts.
Results
Of the total patients, 442 (42.18%) reached RCB 0-I, 462 (44.08%) reached RCB II and 144 (13.74%) reached RCB III. 17 and 19 significant features were selected for two independent tasks. For identifying RCB 0-I and RCB II-III, the multitask model reached an area under the curve (AUC) of 0.932 in primary cohort, and AUCs of 0.890, 0.919 and 0.911 in the external validation cohorts. It also identified RCB II and RCB III with an AUC of 0.916 in primary cohort, and AUCs of 0.870, 0.899 and 0.871 in external validation cohorts.
Conclusions
The longitudinal radiomics multitask learning model is a noninvasive tool to predict RCB score for breast cancer, and help clinical decision-making in the early stage of NAC.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
263P - Efficacy and safety of neoadjuvant chemotherapy combination with pembrolizumab in triple-negative breast cancer: Real-world data
Presenter: Layal Rached
Session: Poster session 02
264P - Tumor-infiltrating lymphocytes (TILs) for prediction of response to platinum-based neoadjuvant chemotherapy (NACT) in triple-negative breast cancer (TNBC): Final analysis
Presenter: Sheyda Abdullaeva
Session: Poster session 02
265P - Effect of HER2-low-positive status on neoadjuvant chemotherapy and survival outcome of breast cancer: A 10-year dual-center retrospective study
Presenter: Yijun Li
Session: Poster session 02
266P - Discontinuation rate and serious adverse events of chemoimmunotherapy as neoadjuvant treatment for triple-negative breast cancer: A systematic review and meta-analysis
Presenter: Francesca Schipilliti
Session: Poster session 02
267P - Pathological complete response after neoadjuvant chemotherapy plus pertuzumab and trastuzumab for HER2+ early breast cancer: Real-world data from NeoPowER study
Presenter: Fabio Canino
Session: Poster session 02
268P - Evaluating the efficacy of adjuvant capecitabine in triple-negative breast cancer patients with residual disease: A real-world evidence study
Presenter: Min Jeong Kim
Session: Poster session 02
269P - Achieving treatment goals in elderly breast cancer patients with neoadjuvant chemotherapy: A remarkable insight
Presenter: Eda Caliskan Yildirim
Session: Poster session 02
270P - Influence of neoadjuvant chemotherapy-induced short-term amenorrhea on pathologic response and treatment outcome in ER+HER2- breast cancer
Presenter: Seung Eun Lee
Session: Poster session 02
271P - First clinical demonstration of the predictive value of tissue nanomechanical signature in breast cancer patients in neoadjuvant therapy setting
Presenter: Sara Nizzero
Session: Poster session 02