(1) Background: Cell proliferation (Ki-67) has important clinical value in the treatment and prognosis of non-small cell lung cancer (NSCLC). However, current detection methods for Ki-67 are invasive and can lead to incorrect results. This study aimed to explore a deep learning classification model for the prediction of Ki-67 and the prognosis of NSCLC based on FDG-PET/CT images. (2) Methods: The FDG-PET/CT scan results of 159 patients with NSCLC confirmed via pathology were analyzed retrospectively, and the prediction models for the Ki-67 expression level based on PET images, CT images and PET/CT combined images were constructed using Densenet201. Based on a Ki-67 high expression score (HES) obtained from the prediction model, the survival rate of patients with NSCLC was analyzed using Kaplan–Meier and univariate Cox regression. (3) Results: The statistical analysis showed that Ki-67 expression was significantly correlated with clinical features of NSCLC, including age, gender, differentiation state and histopathological type. After a comparison of the three models (i.e., the PET model, the CT model, and the FDG-PET/CT combined model), the combined model was found to have the greatest advantage in Ki-67 prediction in terms of AUC (0.891), accuracy (0.822), precision (0.776) and specificity (0.902). Meanwhile, our results indicated that HES was a risk factor for prognosis and could be used for the survival prediction of NSCLC patients. (4) Conclusions: The deep-learning-based FDG-PET/CT radiomics classifier provided a novel non-invasive strategy with which to evaluate the malignancy and prognosis of NSCLC.

Early integration of palliative care (PC) for patients with advanced cancer has been recommended to improve quality of care. This study aims to describe prevalence, temporal trend and predictors of PC use in metastatic breast cancer (mBCa) patients receiving critical care therapies (CCT; included invasive mechanic ventilation, percutaneous endoscopic gastrostomy tube, total parenteral nutrition, tracheostomy and dialysis). The National Inpatient Sample was queried for mBCa patients receiving CCT between 2005 and 2014. Annual percent changes (APC) were calculated for PC prevalence in the overall cohort and subgroups. Multivariable logistic analysis was used to explore predictors of PC use. Of 5833 mBCa patients receiving CCT, 880 (15.09%) received PC. Rate of PC use increased significantly from 2.53% in 2005 to 25.96% in 2014 (APC: 35.75%; p < 0.0001). Higher increase in PC use was observed in South (from 0.65% to 27.11%; APC: 59.42%; p < 0.0001), medium bedsize hospitals (from 3.75% to 26.05%; APC: 38.16%; p = 0.0006) and urban teaching hospitals (from 4.13% to 29.86%; APC: 37.33%; p = 0.0005). Multivariable analysis revealed that year interval, urban teaching hospitals, and invasive mechanical ventilation were associated with increased PC use, while primary diagnosis of gastrointestinal disorders, fractures, metastatic sites from lymph nodes and tracheostomy were associated with lower PC use. PC use in mBCa patients receiving CCT increases significantly over the period. However, it still remains low. Efforts to illustrate disparities in PC use are needed to improve quality of care for mBCa patients receiving CCT, especially for those hospitalized in rural and nonteaching hospitals.