Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging.

IMPORTANCE: Accurate pre-treatment prediction of distant metastasis in patients with Nasopharyngeal Carcinoma (NPC) enables the implementation of appropriate treatment strategies for high-risk individuals. PURPOSE: To develop and assess a Convolutional Neural Network (CNN) model using pre-therapy Magnetic Resonance (MR) imaging to predict distant metastasis in NPC patients. METHODS: We retrospectively reviewed data of 441 pathologically diagnosed NPC patients who underwent complete radiotherapy and chemotherapy at Renmin Hospital of Wuhan University (Hubei, China) between February 2012 and March 2018. Using Adobe Photoshop, an experienced radiologist segmented MR images with rectangular regions of interest. To develop an accurate model according to the primary tumour, Cervical Metastatic Lymph Node (CMLN), the largest area of invasion of the primary tumour, and image segmentation methods, we constructed intratumoural and intra-peritumoural datasets that were used for training and test of the transfer learning models. Each model's precision was assessed according to its receiver operating characteristic curve and accuracy. Generated high-risk-related Grad-Cams demonstrated how the model captured the image features and further verified its reliability. RESULTS: Among the four models, all intra-peritumoural datasets performed better than the corresponding intratumoural datasets, with the CMLN intra-peritumoural dataset exhibiting the best performance (average area under the curves (AUCs) = 0.88). There was no significant difference between average AUCs of the Max and NPC tumour datasets. AUCs of the eight datasets for the four models were higher than those of the Tumour-Node-Metastasis staging system (AUC=0.67). In most datasets, the xception model had higher AUCs than other models. The efficientnet-b0 and xception models efficiently extracted high-risk features. CONCLUSION: The CNN model predicted distant metastasis in NPC patients with high accuracy. Compared to the primary tumour, the CMLN better predicted distant metastasis. In addition to intratumoural data, peritumoural information can facilitate the prediction of distant metastasis. With a larger sample size, datasets of the largest areas of tumour invasion may achieve meaningful accuracy. Among the models, xception had the best overall performance.

[Simultaneous determination of five illegal drugs in weight control foods with solid phase extraction-high performance liquid chromatography].

OBJECTIVE: To develop a method for simultaneous determination of hydrochlorothiazide, furosemide, clopamide, bumetanide and sibutramine hydrochloride in weight control foods with solid phase extraction-high performance liquid chromatography. METHODS: The analytes in the samples were extracted with 2% phosphoric acid-methanol (1:1, V/V) solution ultrasonically and centrifuged. The extracts were clean-up with Osis MCX SPE columns, concentrated under weak N2 stream, and reconstituted with 2% phosphoric acid-methanol (1:1, V/V) solution, vortex mixing and centrifugation at 12,000 r/min. The high performance liquid chromatography was performed with Phenomenex C18 (250 x 4.60 mm, 5 microm) as separation column, 0.02 mol/L acetonitrile potassium dihydrogen phosphate buffer as mobile phase, gradient elution of 1.0 mL/min for the flow rate, and 40 degrees C for the column temperature. The standard curve method was used for the quantitative analysis. RESULTS: A good linear range appeared for the five analytes from 0.25 to 100 microg/mL (r > or = 0.999). The detection limits were 5.2-108 microg/kg. The average recoveries were 86.5%-113.1%, with the relative standard deviations of 1.6%-8.9%. CONCLUSION: The proposed method is a reliable method with high selectivity and high sensitivity for the detection of the five illegal chemicals in the weight control foods.