Random projection forest initialization for graph convolutional networks.

Graph convolutional networks (GCNs) were a great step towards extending deep learning to graphs. GCN uses the graph G and the feature matrix X as inputs. However, in most cases the graph G is missing and we are only provided with the feature matrix X. To solve this problem, classical graphs such as k-nearest neighbor (k-nn) are usually used to construct the graph G and initialize the GCN. Although it is computationally efficient to construct k-nn graphs, the constructed graph might not be very useful for learning. In a k-nn graph, points are restricted to have a fixed number of edges, and all edges in the graph have equal weights. Our contribution is Initializing GCN using a graph with varying weights on edges, which provides better performance compared to k-nn initialization. Our proposed method is based on random projection forest (rpForest). rpForest enables us to assign varying weights on edges indicating varying importance, which enhanced the learning. The number of trees is a hyperparameter in rpForest. We performed spectral analysis to help us setting this parameter in the right range. In the experiments, initializing the GCN using rpForest provides better results compared to k-nn initialization.•Constructing the graph G using rpForest sets varying weights on edges, which represents the similarity between a pair of samples.Unlike k-nearest neighbor graph where all weights are equal.•Using rpForest graph to initialize GCN provides better results compared to k-nn initialization. The varying weights in rpForest graph quantify the similarity between samples, which guided the GCN training to deliver better results.•The rpForest graph involves the tuning of the hyperparameter (number of trees T). We provided an informative way to set this hyperparameter through spectral analysis.

A Phase II trial of the combination of vinorelbine and capecitabine as second-line treatment in metastatic breast cancer previously treated with taxanes and/or anthracyclines.

PURPOSE: Survival time for metastatic breast cancer (MBC) can be substantially improved by combination chemotherapy in the adjuvant setting. Capecitabine and vinorelbine have shown considerable efficacy and favourable toxicity as single agents. The aim of this study is to evaluate the response to the combination of capecitabine and vinorelbine as second-line treatment in patients previously treated with taxanes and/or anthracyclines. PATIENTS AND METHODS: Thirty-nine patients with MBC, who received a combination of vinorelbine and capecitabine were included in the study. RESULTS: Overall response rate was 53.9% and disease progression rate was 28.2% for patients who received six cycles of therapy, rates significantly higher than the three-cycle group. The treatment was generally well tolerated and toxicity was mild. CONCLUSIONS: The combination of capecitabine and vinorelbine as salvage therapy in anthracycline- and/or taxane-pre-treated patients with MBC seems to be effective and safe, even more so as the number of treatment cycles increases.

Systemic sclerosis associated with rectal cancer. Case report and a brief review of the literature.

Autoimmune diseases may appear as paraneoplastic syndromes during the course of a neoplastic disease, the most common being dermatomyositis/ polymyositis. The association of systemic sclerosis and cancer is not clear. The case of a 56-year-old male with rectal cancer and systemic sclerosis where the coexistence of the two diseases was closely related, so that scleroderma was considered a paraneoplastic syndrome rather than a concomitant morbid condition, is presented.