Search

Background：Lymph node metastasis of lung cancer plays an important part in lung cancer diagnosis since its close relationship with patients’ prognosis and subsequent treatment, however, diagnosis of lymph node metastases often was tedious and takes too much time for pathologists. Automatized classification with few-shot learning algorithms is required for clinical situations that only unbalanced and small datasets can be collected. We developed a few-shot learning algorithms for automatized classification of lymphatic metastasis of lung carcinoma from Whole Slide Images (WSIs) through a deep convolutional neural network (DCNN).Material and methods: Lymph node slides of patients with lung cancer collected from July to December 2018 were reviewed and used for model development retrospectively. A total of 1701 lymph node slides from 453 lung cancer patients with different histological types were enrolled. Each slide could provide a different number of patches, in which 6, 8, 10, 20, and 30 positive patches and 12, 16, 20, 40, and 60 negative patches for training and validation, respectively. A total of 1577 WSIs were used. The receiver operating characteristic (ROC) analysis of the model was performed for estimating the performance and compared to the traditional deep learning approach Resnet34.Results: Deep learning methods, when trained with very few shots (6 positive/12 negative, 8 positive/16 negative, and 10 positive/20 negative patches), the traditional deep learning approach Resnet34 was outperformed by our Aitrox model. When the dataset was raised to 20 positive/40 negative patches, similar performance was achieved with AUC 0.5895 (95% CI, 0.5833-0.5910) for Resnet34 and 0.6124 (95% CI, 0.6077-0.6147) for our Aitrox model. Resnet34 over-performed our Aitrox model (AUC=0.6450 [95%CI, 0.6397-0.6470]) with an AUC of 0.7481 (95%CI, 0.7120-0.7485) when the training and validation dataset was raised to 30 positive/60 negative patches.Conclusions: This proposed few-shot method may address AI approaches to the diagnosis of lymphatic metastasis of lung carcinoma and other kinds of carcinoma in the future.

This work investigated the corrosion resistance of an acceptable composite coating obtained from catecholate-functionalized zinc complex (CFZ). The ion distribution states of catechol and Zn(II) at different pH values were calculated, and the anticorrosion of coatings on carbon steel by means of neutral salt spray test were specifically monitored. CFZ-steel was fabricated using 30 min electrodeposition of CFZ/Na2SO4 media at pH 9 on carbon steel. Lower corrosion degree of CFZ-steel in salt spray during oxidation process meant slight amount of corrosion attack on the steel surface. Also, the growth tendency of corrosion rate was gradually reduced, indicating a nonlinear relationship between corrosion rate and contact time. This indicated electrodeposition of CFZ was not only appropriate for the practical application of composite coatings to corrosion resistance but also a key step for extending the service life of carbon steel.

This work highlights the results of a program currently underway to improve the voltage delay of aqueous magnesium (Mg) battery through pulse technique. The effect of current pulse on the electrochemical behavior of AZ31B Mg anode in aqueous solution is investigated using a multi-current step method and electrochemical impedance spectroscopy. Results indicate that the optimal pulse signal is 25 mA cm−2-100 ms and the excellent discharge behavior can be well maintained even at the 10 days immersion time. The surface morphology and chemical composition of the Mg anode are analyzed by scanning electron microscopy, Fourier transform infrared spectroscopy, and X-ray photoelectron spectroscopy. The results demonstrate that the elimination of delayed action of the Mg electrode at controlled-pulse condition is to change the surface morphology distribution rather than the chemical composition. Finally, an evolutionary model of the surface film is proposed.