Search

Your search keyword '"Gao, Yanhua"' showing total 415 results
Start Over Author "Gao, Yanhua"
415 results on '"Gao, Yanhua"'

4. Preparing data for pathological artificial intelligence with clinical-grade performance

Author

Yang, Yuanqing, Sun, Kai, Gao, Yanhua, Wang, Kuangsong, and Yu, Gang

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

[Purpose] The pathology is decisive for disease diagnosis, but relies heavily on the experienced pathologists. Recently, pathological artificial intelligence (PAI) is thought to improve diagnostic accuracy and efficiency. However, the high performance of PAI based on deep learning in the laboratory generally cannot be reproduced in the clinic. [Methods] Because the data preparation is important for PAI, the paper has reviewed PAI-related studies in the PubMed database published from January 2017 to February 2022, and 118 studies were included. The in-depth analysis of methods for preparing data is performed, including obtaining slides of pathological tissue, cleaning, screening, and then digitizing. Expert review, image annotation, dataset division for model training and validation are also discussed. We further discuss the reasons why the high performance of PAI is not reproducible in the clinical practices and show some effective ways to improve clinical performances of PAI. [Results] The robustness of PAI depend on randomized collection of representative disease slides, including rigorous quality control and screening, correction of digital discrepancies, reasonable annotation, and the amount of data. The digital pathology is fundamental of clinical-grade PAI, and the techniques of data standardization and weakly supervised learning methods based on whole slide image (WSI) are effective ways to overcome obstacles of performance reproduction. [Conclusion] The representative data, the amount of labeling and consistency from multi-centers is the key to performance reproduction. The digital pathology for clinical diagnosis, data standardization and technique of WSI-based weakly supervised learning hopefully build clinical-grade PAI. Keywords: pathological artificial intelligence; data preparation; clinical-grade; deep learning

Published
2022

8. Multi-scale super-resolution generation of low-resolution scanned pathological images

Author

Sun, Kai, Gao, Yanhua, Xie, Ting, Wang, Xun, Yang, Qingqing, Chen, Le, Wang, Kuansong, and Yu, Gang

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Background. Digital pathology has aroused widespread interest in modern pathology. The key of digitalization is to scan the whole slide image (WSI) at high magnification. The lager the magnification is, the richer details WSI will provide, but the scanning time is longer and the file size of obtained is larger. Methods. We design a strategy to scan slides with low resolution (5X) and a super-resolution method is proposed to restore the image details when in diagnosis. The method is based on a multi-scale generative adversarial network, which sequentially generates three high-resolution images such as 10X, 20X and 40X. Results. The peak-signal-to-noise-ratio of 10X to 40X generated images are 24.16, 22.27 and 20.44, and the structural-similarity-index are 0.845, 0.680 and 0.512, which are better than other super-resolution networks. Visual scoring average and standard deviation from three pathologists is 3.63 plus-minus 0.52, 3.70 plus-minus 0.57 and 3.74 plus-minus 0.56 and the p value of analysis of variance is 0.37, indicating that generated images include sufficient information for diagnosis. The average value of Kappa test is 0.99, meaning the diagnosis of generated images is highly consistent with that of the real images. Conclusion. This proposed method can generate high-quality 10X, 20X, 40X images from 5X images at the same time, in which the time and storage costs of digitalization can be effectively reduced up to 1/64 of the previous costs. The proposed method provides a better alternative for low-cost storage, faster image share of digital pathology. Keywords. Digital pathology; Super-resolution; Low resolution scanning; Low cost, Comment: 27 pages,12 figures

Published
2021

21. Purification and characterisation of a homogenised protein from Red Deer (Cervus elaphus) abomasum as a potential hyaluronidase inhibitor.

Author

Yang, Zi, Wali, Ahmidin, Arken, Amina, Dongmulati, Naziermu, Hu, Ailin, Gao, Yanhua, Yili, Abulimiti, and Aisa, HajiAkber

Subjects
ESSENTIAL amino acids, RED deer, HYALURONIDASES, FLUORESCENCE spectroscopy, PROTEIN structure
Abstract

Summary: To improve the utilisation of abomasum and explore the material basis of its antioxidant and hyaluronidase inhibitory activities, a homogeneous protein RDA4‐1 was isolated from the abomasum of cultured red deer by two‐step chromatography process for the first time in this study. It has a molecular weight of 15 kDa and comprises 43.56% essential amino acids. RDA4‐1 scavenged 50.97% of DPPH• and 88.37% of ABTS+· at 1.5 mg mL−1, and inhibited hyaluronidase by 79.23% at 1 mg mL−1. The CD and fluorescence spectroscopy was used to initiate explore the hyaluronidase inhibition reaction process. With an increase in the concentration of RDA4‐1 in the inhibition reaction, the wavelength of the negative peak of CD shifted from 208 to 218 nm, and the absorption of the positive peak of CD increased from 0.5 to 8.3 mdeg. Furthermore, fluorescence absorption at a wavelength of 340 nm rose from 248 to 762 au. These findings suggest that the interaction of RDA4‐1 with hyaluronidase induces alterations in the secondary structure of the protein complex, and RDA4‐1 binds reversibly to the enzyme in a non‐covalent manner. The results of this study indicate that RDA4‐1 could serve as a potential hyaluronidase inhibitor in the development of nutraceuticals. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

28. One-step hydrothermal synthesis of MIL-88A/BiOCl0.1Br0.9(M88/BCB) solid solution Z-scheme heterojunction photocatalysts.

Author

Gao, Yanhua, Liu, Hongya, Zhang, Dongfeng, Chen, Ying, Liang, Yuning, and Ren, Juan

Abstract

In this paper, M88/BCB Z-scheme heterojunction photocatalysts were synthesized by a one-step hydrothermal method. A series of characterization analyses showed that the introduction of iron-based MOF material M88 with mixed valence (Fe2+/Fe3+) increased not only the specific surface area of BCB, which was 2.2 times higher than that of BiOCl0.1Br0.9 solid solution, but also the existence of Fe2+/Fe3+ redox centers promoting the in situ photoFenton-like reaction, which could generate more ˙O2− and ˙OH. In addition, the introduction of M88 further enhances the visible light response capability of BCB and the separation efficiency of photogenerated carriers. Under visible light for 120 min, 10% M88/BCB can degrade 89.74% of TC, which is 2.1 times and 1.6 times higher than that of M88 and BCB, respectively. A possible photocatalytic degradation mechanism of Z-scheme heterojunctions was proposed based on the study of the band structure and the capture experiment of active species. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

29. One-step preparation of direct Z-scheme NH2-UiO-66/BiOCl photocatalyst for antibiotic degradation by electrostatic adsorption.

Author

Gao, Yanhua, Liu, Hongya, Zhang, Dongfeng, Chen, Ying, Liang, Yuning, and Ren, Juan

Subjects
*ANTIBIOTICS, *VISIBLE spectra, *PHOTODEGRADATION, *ELECTRIC fields, *TETRACYCLINES, *PHOTOCATALYSTS
Abstract

In this work, based on the electrostatic adsorption theory, a direct Z-scheme NH2-UiO-66/BiOCl composite photocatalyst was prepared by a one-step solvothermal method with NH2-UiO-66 embedded on the smooth surface of flower-like BiOCl without additional chlorine source to form a close contact interface. The photocatalytic degradation of tetracycline hydrochloride (TCH) of 1.0-NH2-UiO-66/BiOCl(1.0-NUBC) prepared under simulated sunlight was 1.63 times and 78.84 times that of pure BiOCl and pure NH2-UiO-66, respectively. The reason for the enhanced photocatalytic performance may be that electrostatic adsorption promotes the homogeneous and orderly synthesis of heterogeneous structures, significantly increasing the ratio of NH2-UiO-66/BiOCl surface, which not only improves the visible light response range but also promotes the formation of the interface electric field between NH2-UiO-66 and BiOCl interface. The separation and transfer of the photogenerated electron–hole pairs are greatly promoted. Therefore, this study provides an effective way for the synthesis of BiOCl/MOF composites and has a good application prospect. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

46. A User-Mode Scheduling Mechanism for ARINC653 Partitioning in seL4

Author

Kang, Qiao, Yuan, Cangzhou, Wei, Xin, Gao, Yanhua, Wang, Lei, Kacprzyk, Janusz, Series editor, Pal, Nikhil R., Advisory editor, Bello Perez, Rafael, Advisory editor, Corchado, Emilio S., Advisory editor, Hagras, Hani, Advisory editor, Kóczy, László T., Advisory editor, Kreinovich, Vladik, Advisory editor, Lin, Chin-Teng, Advisory editor, Lu, Jie, Advisory editor, Melin, Patricia, Advisory editor, Nedjah, Nadia, Advisory editor, Nguyen, Ngoc Thanh, Advisory editor, Wang, Jun, Advisory editor, Bhatia, Sanjiv K., editor, Mishra, Krishn K., editor, Tiwari, Shailesh, editor, and Singh, Vivek Kumar, editor

Published
2017
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results