Comprehensive treatment of rare multiple endocrine neoplasia type 1:A case report

BACKGROUND Multiple endocrine neoplasia type 1(MEN1)is a rare hereditary disorder caused by mutations of the MEN1 gene.It is characterized by hyperparathyroidism and involves the pancreas,anterior pituitary,duodenum,and adrenal gland.Here,we report a 40-year-old male patient with MEN1 who first manifested as thymic carcinoid,then primary hyperparathyroidism and prolactinoma,and a decade later pancreatic neuroendocrine tumor.CASE SUMMARY The patient underwent a thymectomy because of the thymic carcinoid 10 years prior and a prolactinoma resection 2 years prior.His sister suffered from prolactinoma.His parents displayed a typical triad of amenorrhea,galactorrhea,and infertility.Computed tomography revealed a strong signal in the upper portion of the left lobes and posterior portion of the right lobes of the thyroid and irregular soft tissue densities of the pancreatic body.Positron emission tomography/computed tomography imaging further showed strong 18Fflurodeoxyglucose uptake in the tail of the pancreatic body and segment IV of the liver.The patient underwent pancreatic body tail resection,pancreatic head mass enucleation,and ultrasound-guided radio-frequency ablation for liver cancer.Pathology results reported neuroendocrine tumor grade 2.Whole exome sequencing revealed a verified pathogenic mutation c.378G>A(p.Trp126*)in the MEN1 gene.The diagnosis of MEN1 was confirmed.At the 1.5-year follow-up,the patient appeared healthy without any sign of reoccurrence.CONCLUSION The present case may add some insight into the diagnosis and treatment of patients with MEN1.

Hidden feature extraction for unstructured agricultural environment based on supervised kernel locally linear embedding modeling

An online hidden feature extraction algorithm is proposed for unknown and unstructured agricultural environments based on a supervised kernel locally linear embedding (SKLLE) algorithm. Firstly, an online obtaining method for scene training samples is given to obtain original feature data. Secondly, Bayesian estimation of the a posteriori probability of a cluster center is performed. Thirdly, nonlinear kernel mapping function construction is employed to map the original feature data to hyper-high dimensional kernel space. Fourthly, the automatic deter mination of hidden feature dimensions is performed using a local manifold learning algorithm. Then, a low-level manifold computation in hidden space is completed. Finally, long-range scene perception is realized using a 1-NN classifier. Experiments are conducted to show the effectiveness and the influence of parameter selection for the proposed algorithm. The kernel principal component analysis (KPCA), locally linear embedding (LLE), and supervised locally linear embedding (SLLE) methods are compared under the same experimental unstructured agricultural environment scene. Test results show that the proposed algorithm is more suitable for unstructured agricultural environments than other existing methods, and that the computational load is significantly reduced.