BackgroundEwing’s sarcoma (ES) and primitive neuroectodermal tumors (PNET) are closely related tumors. Although soft tissue ES/PNET are common in clinical practice, they are rare in the small intestine. Because of the absence of characteristic clinical symptoms, they are easily misdiagnosed as other benign or malignant diseases.Case presentationHere, we present the case of a 16-year-old female who complained of anemia and interval hematochezia. Her serum test results showed only a slight elevation of CA-125 and a low level of hemoglobin. Computer tomography and magnetic resonance imaging revealed a cystic and solid mass in the lower abdominal quadrant and pelvic region, which prompted suspicion of a malignant gastrointestinal stromal tumor of the small intestine. After resection, the tumor’s histology and immunohistochemistry (positive for CD99, vimentin and synaptophysin) results suggested ES/PNET. Fluorescent in situ hybridization tests proved the breakpoint rearrangement of the EWSR1 gene in chr 22.Ultrastructural analysis revealed neurosecretory and glycogen granules in the tumor cell cytoplasm.ConclusionsTogether, these data supported the diagnosis of a rare case of localized ES/PNET in the small intestine without adjuvant chemo- or radiotherapy. To our knowledge, this is the first report from China of a primary small bowel ES/PNET in the English-language literature. In addition, on the basis of findings from previous publications and the current case, the optimal treatment for localized gastrointestinal ES/PNET is discussed.

No abstract

Principal Component Analysis (PCA) has been widely used in data mining and analysis as it can significantly reduce data dimensionality while maintaining the most useful information carried in data. However, from the perspective of minimizing reconstruction error, each data sample's error is squared, and therefore sensitive to widely existed outliers and noises which increases dramatically as data dimensionality grows. To alleviate the problem, many researchers focus on improving the robustness of PCA by using more robust norm such as 2,p (p < 2) or 1 -norm loss formulation. In this paper we propose a novel optimization framework to systematically solve 2,p and 1 -norm-based PCA problem with rigorous theoretical guarantee, based on which we investigate a very computationally economic updating version. The proposed methods are not only robust to outliers but also easy to implement.