Objective To report a case of vaginal colonization due to Trichosporon inkin. Methods A 34-year-old female presented with increased vaginal discharge accompanied by abnormal odor for 2 months. Clinical laboratory examination was carried out. Cultures of vaginal discharge yielded yeast-like colony. Subsequently, the isolate underwent the following mycological examinations: purification, slide micro-culture, temperature test, urea enzyme test, biochemistry identification, antifungal susceptibility test, and gene sequencing. Results Gynecological examination revealed white homogeneous secretions attached to mucous membrane of the vagina. Nugent scores of vaginal discharge amounted to 5-6. Two rounds of culture of vaginal discharge resulted in stramineous, reductus and yeast-like colony. The isolate could grow in 42 ℃. Appressorium on the top of hypha and typical sarcinae formed in slide microculture of corn agar, and yeast malt agar was the optimal growth medium for it. Urea enzyme test was positive. API 20C AUX biochemical test and gene sequencing revealed that the isolate was consistent with Trichosporon inkin. The isolate was sensitive to amphotericin B and azoles such as clotrimazole and fluconazole, but resistant to flucytosine and caspofungin. Conclusions It is the first report of vaginal colonization due to T. Inkin in China. The accu-rate identification of T. Inkin relies on synthetic analysis of phenotype characteristics, biochemistry test and molecular sequencing.

Focus on the inconsistency of the shape, location and size of brain glioma, a dual-channel 3-dimensional (3D) densely connected network is proposed to automatically segment brain glioma tumor on magnetic resonance images. Our method is based on a 3D convolutional neural network frame, and two convolution kernel sizes are adopted in each channel to extract multi-scale features in different scales of receptive fields. Then we construct two densely connected blocks in each pathway for feature learning and transmission. Finally, the concatenation of two pathway features was sent to classification layer to classify central region voxels to segment brain tumor automatically. We train and test our model on open brain tumor segmentation challenge dataset, and we also compared our results with other models. Experimental results show that our algorithm can segment different tumor lesions more accurately. It has important application value in the clinical diagnosis and treatment of brain tumor diseases.
Brain Neoplasms ; diagnostic imaging ; Glioma ; diagnostic imaging ; Humans ; Image Processing, Computer-Assisted ; Magnetic Resonance Imaging ; Neural Networks (Computer)