Overexpression of a novel candidate oncogene KIF14 correlates with tumor progression and poor prognosis in prostate cancer Overexpression of a novel candidate oncogene KIF14 correlates with tumor progression and poor prognosis in prostate cancer

Background: Laryngeal squamous cell carcinoma (LSCC) is one of the most common tumors of the respiratory tract. Currently, the diagnosis of LSCC is mainly based on a laryngoscopy analysis and pathological findings. Deep-learning algorithms have been shown to provide accurate clinical diagnoses. Methods: We developed a deep convolutional neural network (CNN) model, and evaluated its application to narrow-band imaging (NBI) endoscopy and pathological diagnoses of LSCC at several hospitals. A total of 4,591 patients’ laryngeal NBI scans (1,927 benign and 2,664 LSCC) were used to test and validate the model. Additionally, 3,458 pathological images (752 benign and 2,706 LSCC) of 1,228 patients’ hematoxylin and eosin staining slides (318 benign and 910 LSCC) were used for the pathological diagnosis training and validation. The images were randomly divided into training, validation and testing images at the ratio of 70:15:15. An independent test cohort of LSCC NBI scans and pathological images from other institutions were also used. Results: In the NBI group, the areas under the curve of the validation, test, and independent test data sets were 0.966, 0.964, and 0.873, respectively, and those of the pathology group were 0.994, 0.981, and 0.982, respectively. Our method was highly accurate at diagnosing LSCC. Conclusions: In this study, the CNN model performed well in the NBI and pathological diagnosis of LSCC. More accurate and faster diagnoses could be achieved with the assistance of this algorithm.

OSR1 is a novel epigenetic silenced tumor suppressor regulating invasion and proliferation in renal cell carcinoma OSR1 is a novel epigenetic silenced tumor suppressor regulating invasion and proliferation in renal cell carcinoma

Head and neck squamous cell carcinoma (HNSCC) is the sixth most common cancer worldwide. The five-year survival rate of HNSCC has not improved even with major technological advancements in surgery and chemotherapy. Currently, docetaxel, cisplatin, and 5-fluoruracil (TPF) treatment has been the most popular chemotherapy method for HNSCC; but only a small percentage of HNSCC patients exhibit a good response to TPF treatment. Unfortunately, at present, no reasonably effective prediction model exists to assist clinicians with patient treatment. For this reason, patients have no other alternative but to risk neoadjuvant chemotherapy in order to determine their response to TPF. In this study, we analyzed the gene expression profile in TPF-sensitive and non-sensitive patient samples. We identified a gene expression signature between these two groups. We further chose 10 genes and trained a support vector machine (SVM) model. This model has 88.3% sensitivity and 88.9% specificity to predict the response to TPF treatment in our patients. In addition, four more TPF responsive and four more TPF non-sensitive patient samples were used for further validation. This SVM model has been proven to achieve approximately 75.0% sensitivity and 100% specificity to predict TPF response in new patients. This suggests that our 10-genes SVM prediction model has the potential to assist clinicians to personalize treatment for HNSCC patients.