Prediction of the therapeutic efficacy of epirubicin combined with ifosfamide in patients with lung metastases from soft tissue sarcoma based on contrast-enhanced CT radiomics features.

OBJECTIVE: To investigate the value of contrast-enhanced computed tomography (CECT) radiomics features in predicting the efficacy of epirubicin combined with ifosfamide in patients with pulmonary metastases from soft tissue sarcoma. METHODS: A retrospective analysis of 51 patients with pulmonary metastases from soft tissue sarcoma who received the chemotherapy regimen of epirubicin combined with ifosfamide was performed, and efficacy was evaluated by Recist1.1. ROIs (1 or 2) were selected for each patient. Lung metastases were used as target lesions (86 target lesions total), and the patients were divided into a progression group (n = 29) and a non-progressive group (n = 57); the latter included a stable group (n = 34) and a partial response group (n = 23). Information on lung metastases was extracted from CECT images before chemotherapy, and all lesions were delineated by ITK-SNAP software manually or semiautomatically. The decision tree classifier had a better performance in all radiomics models. A receiver operating characteristic curve was plotted to evaluate the predictive performance of the radiomics model. RESULTS: In total, 851 CECT radiomics features were extracted for each target lesion and finally reduced to 2 radiomics features, which were then used to construct a radiomics model. Areas under the curves of the model for predicting lesion progression were 0.917 and 0.856 in training and testing groups, respectively. CONCLUSION: The model established based on the radiomics features of CECT before treatment has certain predictive value for assessing the efficacy of chemotherapy for patients with soft tissue sarcoma lung metastases.

Prognostic factors of primary neuroendocrine breast cancer: A population-based study.

BACKGROUND: Primary neuroendocrine breast carcinomas (NEBCs) are an extremely rare and underrecognized subtype of mammalian carcinoma. The prognostic factors for NEBCs remain controversial. METHODS: In this multicenter retrospective study, the prognostic factors for patients with primary NEBCs who underwent surgery and had a pathologically confirmed diagnosis of neuroendocrine carcinoma in China and the United States were examined. The endpoints were disease-free survival (DFS) and overall survival (OS). RESULTS: A total of 51 Chinese patients and 98 US patients were included. In the Chinese cohort, tumor grade and Ki-67 levels were prognostic factors for DFS in univariate analysis (hazard ratio [HR] = 5.11 [1.67-15.60], p = 0.004; HR = 57.70 [6.36-523.40], p < 0.001, respectively) and multivariate analysis (HR = 100.52 [1.33-7570.21], p = 0.037; HR = 31.47 [1.05-945.82], p = 0.047, respectively). In the US cohort, age was an important prognostic factor for OS in univariate analysis (HR = 1.09 [1.04-1.15], p = 0.001). The random effects model for the combined cohorts revealed age and positive expression of estrogen receptor (ER) as potential prognostic factors for OS (HR = 1.08 [1.01-1.14], p = 0.015; HR = 0.10 [0.02-0.44], p = 0.003, respectively). CONCLUSIONS: Tumor grade and Ki-67 levels are important prognostic factors for DFS of patients with primary NEBCs. Age and ER status are important prognostic factors for OS of patients with primary NEBCs.