Liulu Zhang

Background: Accurate identification of pCR to neoadjuvant chemotherapy (NAC) is essential for determining appropriate surgery strategy and guiding resection extent in breast cancer. However, a non-invasive tool to predict pCR accurately is lacking. Our study aims to develop ensemble learning models using longitudinal multiparametric MRI to predict pCR in breast cancer. Methods: From July 2015 to December 2021, we collected pre-NAC and post-NAC multiparametric MRI sequences per patient. We then extracted 14,676 radiomics and 4096 deep learning features and calculated additional delta-value features. In the primary cohort (n = 409), the inter-class correlation coefficient test, U-test, Boruta and the least absolute shrinkage and selection operator regression were used to select the most significant features for each subtype of breast cancer. Five machine learning classifiers were then developed to predict pCR accurately for each subtype. The ensemble learning strategy was used to integrate the single-modality models. The diagnostic performances of models were evaluated in the three external cohorts (n = 343, 170 and 340, respectively). Findings: A total of 1262 patients with breast cancer from four centers were enrolled in this study, and pCR rates were 10.6% (52/491), 54.3% (323/595) and 37.5% (66/176) in HR+/HER2-, HER2+ and TNBC subtype, respectively. Finally, 20, 15 and 13 features were selected to construct the machine learning models in HR+/HER2-, HER2+ and TNBC subtypes, respectively. The multi-Layer Perception (MLP) yields the best diagnostic performances in all subtypes. For the three subtypes, the stacking model integrating pre-, post- and delta-models yielded the highest AUCs of 0.959, 0.974 and 0.958 in the primary cohort, and AUCs of 0.882-0.908, 0.896-0.929 and 0.837-0.901 in the external validation cohorts, respectively. The stacking model had accuracies of 85.0%-88.9%, sensitivities of 80.0%-86.3%, and specificities of 87.4%-91.5% in the external validation cohorts. Interpretation: Our study established a novel tool to predict the responses of breast cancer to NAC and achieve excellent performance. The models could help to determine post-NAC surgery strategy for breast cancer. Funding: This study is supported by grants from the National Natural Science Foundation of China (82171898, 82103093), the Deng Feng project of high-level hospital construction (DFJHBF202109), the Guangdong Basic and Applied Basic Research Foundation (grant number, 2020A1515010346, 2022A1515012277), the Science and Technology Planning Project of Guangzhou City (202002030236), the Beijing Medical Award Foundation (YXJL-2020-0941-0758), and the Beijing Science and Technology Innovation Medical Development Foundation (KC2022-ZZ-0091-5). Funding sources were not involved in the study design, data collection, analysis and interpretation, writing of the report, or decision to submit the article for publication.

PURPOSE: The use of oncoplastic reconstruction for breast-conserving surgery (BCS) extends benefits beyond merely minimizing poor cosmetic results. However, the feasibility and oncological safety of oncoplastic surgery (OPS) are controversial. METHODS: This meta-analysis aimed to compare the short-term and long-term oncological outcomes of BCS alone and BCS plus OPS. Relevant studies published before July 2017 in the Embase, the Cochrane Library, PubMed, and Web of Science databases were screened and collected. The meta-analysis was performed using STATA software (Stata Corp.). RESULTS: =0.527) did not differ between the two groups. CONCLUSION: A combination of BCS and OPS is preferred over BCS alone for decreasing re-excisions and provides similar long-term survival as BCS alone in patients with breast cancer.

Abstract Previous studies have shown that the addition of carboplatin to neoadjuvant chemotherapy improved the pathologic complete response (pCR) rate in patients suffering from triple‐negative breast cancer (TNBC) and patients who obtained a pCR could achieve prolonged event‐free survival (EFS) and overall survival (OS). However, no studies have assessed the effects of the combination of docetaxel and carboplatin without anthracycline with taxane‐based and anthracycline‐based regimens. The NeoCART study was designed as a multicenter, randomized controlled, open‐label, phase II trial to assess the efficacy and safety of docetaxel combined with carboplatin in untreated stage II‐III TNBC. All eligible patients were randomly assigned, at a 1:1 ratio, to an experimental docetaxel plus carboplatin (DCb) for six cycles group (DCb group) or an epirubicin plus cyclophosphamide for four cycles followed by docetaxel for four cycles group (EC‐D group). PCR (ypT0/is ypN0) was evaluated as the primary outcome. Between 1 September 2016 and 31 December 2019, 93 patients were randomly assigned and 88 patients were evaluated for the primary endpoint (44 patients in each group). In the primary endpoint analysis, 27 patients in the DCb group (61.4%, 95% CI 47.0‐75.8) and 17 patients in the EC‐D group achieved a pCR (38.6%, 95% CI 24.3‐53.0; odds ratio 2.52, 95% CI 2.4‐43.1; P noninferiority = .004). Noninferiority was met, and the DCb regimen was confirmed to be superior to the EC‐D regimen ( P = .044, superiority margin of 5%). At the end of the 37‐month median follow‐up period, OS and EFS rates were equivalent in both groups.

OBJECTIVE: Invasive lobular carcinoma (ILC) and invasive ductal carcinoma (IDC) account for most breast cancers. However, the overall survival (OS) differences between ILC and IDC remain controversial. This study aimed to compare nonmetastatic ILC to IDC in terms of survival and prognostic factors for ILC. METHODS: This retrospective cohort study used data from the Surveillance, Epidemiology and End Results (SEER) Cancer Database (www.seer.cancer.gov). Women diagnosed with nonmetastatic ILC and IDC between 2006 and 2016 were included. A propensity score matching (PSM) method was used in our analysis to reduce baseline differences in clinicopathological characteristics and survival outcomes. Kaplan-Meier curves and log-rank test were used for survival analysis. RESULTS: Compared to IDC patients, ILC patients were diagnosed later in life with poorly differentiated and larger lesions, as well as increased expression of estrogen receptors (ERs) and/or progesterone receptors (PRs). A lower rate of radiation therapy and chemotherapy was observed in ILC. After PSM, ILC, and IDC patients exhibited similar OS (HR=1.017, p=0.409, 95% CI: 0.967-1.069). In subgroup analysis of HR-negative, AJCC stage III, N2/N3 stage patients, or those who received radiotherapy, ILC patients exhibited worse OS compared to IDC patients. Furthermore, multivariate analysis revealed a 47% survival benefit for IDC compared to ILC in HR-negative patients who received chemotherapy (HR=1.47, p=0.01, 95% CI: 1.09-1.97). CONCLUSIONS: Our results demonstrated that ILC and IDC patients had similar OS after PSM. However, ILC patients with high risk indicators had worse OS compared to IDC patients by subgroup analysis.