Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Automated detection of multi-class urinary sediment particles: An accurate deep learning approach

Lyu He, Xu Fanxin, Jin Tao, Zheng Siyi, Zhou Chenchen, Cao Yang, Luo Bin, Huang Qinzhen, Xiang Wei, Li Dong

Biocybernetics and Biomedical Engineering

2023

Vol. 43, no. 4

672--683

Urine microscopy is an essential diagnostic tool for kidney and urinary tract diseases, with automated analysis of urinary sediment particles improving diagnostic efficiency. However, some urinary sediment particles remain challenging to identify due to individual variations, blurred boundaries, and unbalanced samples. This research aims to mitigate the adverse effects of urine sediment particles while improving multi-class detection performance. We proposed an innovative model based on improved YOLOX for detecting urine sediment particles (YUS-Net). The combination of urine sediment data augmentation and overall pre-trained weights enhances model optimization potential. Furthermore, we incorporate the attention module into the critical feature transfer path and employ a novel loss function, Varifocal loss, to facilitate the extraction of discriminative features, which assists in the identification of densely distributed small objects. Based on the USE dataset, YUS-Net achieves the mean Average Precision (mAP) of 96.07%, 99.35% average precision, and 96.77% average recall, with a latency of 26.13 ms per image. The specific metrics for each category are as follows: cast: 99.66% AP; cryst: 100% AP; epith: 92.31% AP; epithn: 100% AP; eryth: 92.31% AP; leuko: 99.90% AP; mycete: 99.96% AP. With a practical network structure, YUS-Net achieved efficient, accurate, end-to-end urinary sediment particle detection. The model takes native high-resolution images as input without additional steps. Finally, a data augmentation strategy appropriate for the urinary microscopic image domain is established, which provides a novel approach for applying other methods in urine microscopic images.

Gold recovery from refractory gold concentrates by pressure oxidation pre-treatment and thiosulfate leaching

Yu Li, Li Shimei, Liu Quanjun, Deng Jiushuai, Luo Bin, Liang Yuanqin, Zhao Liuchuang, Lai Hao

Physicochemical Problems of Mineral Processing

2019

Vol. 55, iss. 2

537--551

Naturally, refractory gold is enclosed by sulfide minerals such as pyrite and arsenopyrite and a higher content of organic carbon, which results in difficulty in the recovery of gold. In this study, the flotation gold concentrate before and after pressure oxidation (POX) was analyzed. The analysis of the Eh-pH diagram revealed that pyrite/arsenopyrite would be dissolved in higher oxidation potential. Results of SEM-EDS showed that the surface of minerals became very rough and structure of some particles was destroyed after POX. The XRD measurement showed that pyrite was oxidized to jarosite, and gangue minerals such as quartz and organic carbon were hardly changed. The process of thiosulfate leaching of gold was designed and optimized according to Miscellaneous implemented by Response Surface Methodology (RSM). Based on the results of ANOVA, leaching model was significant. In leaching, [S2O32-] played an important role and the interactions between [S2O32-] and [Cu2+] were significant. The effect of [HA] was relatively weak. Optimum process parameters of the initial reagent concentration were 505.00 mM for [S2O32-], 34.77 mM for [Cu2+], and 0.50 mM for [HA]. Under these conditions, the Au extraction value was about 86.21%, which was significantly higher than that obtained with leaching directly.