Search

Your search keyword '"Liu, Yalong"' showing total 262 results
Start Over Author "Liu, Yalong"
262 results on '"Liu, Yalong"'

11. Trident Segmentation CNN: A Spatiotemporal Transformation CNN for Punctate White Matter Lesions Segmentation in Preterm Neonates

Author

Liu, Yalong, Li, Jie, Wang, Miaomiao, Jiao, Zhicheng, Yang, Jian, and Li, Xianjun

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

Accurate segmentation of punctate white matter lesions (PWML) in preterm neonates by an automatic algorithm can better assist doctors in diagnosis. However, the existing algorithms have many limitations, such as low detection accuracy and large resource consumption. In this paper, a novel spatiotemporal transformation deep learning method called Trident Segmentation CNN (TS-CNN) is proposed to segment PWML in MR images. It can convert spatial information into temporal information, which reduces the consumption of computing resources. Furthermore, a new improved training loss called Self-balancing Focal Loss (SBFL) is proposed to balance the loss during the training process. The whole model is evaluated on a dataset of 704 MR images. Overall the method achieves median DSC, sensitivity, specificity, and Hausdorff distance of 0.6355, 0.7126, 0.9998, and 24.5836 mm which outperforms the state-of-the-art algorithm. (The code is now available on https://github.com/YalongLiu/Trident-Segmentation-CNN)

Published
2019

13. Refined-Segmentation R-CNN: A Two-stage Convolutional Neural Network for Punctate White Matter Lesion Segmentation in Preterm Infants

Author

Liu, Yalong, Li, Jie, Wang, Ying, Wang, Miaomiao, Li, Xianjun, Jiao, Zhicheng, Yang, Jian, and Gao, Xingbo

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

Accurate segmentation of punctate white matter lesion (PWML) in infantile brains by an automatic algorithm can reduce the potential risk of postnatal development. How to segment PWML effectively has become one of the active topics in medical image segmentation in recent years. In this paper, we construct an efficient two-stage PWML semantic segmentation network based on the characteristics of the lesion, called refined segmentation R-CNN (RS RCNN). We propose a heuristic RPN (H-RPN) which can utilize surrounding information around the PWMLs for heuristic segmentation. Also, we design a lightweight segmentation network to segment the lesion in a fast way. Densely connected conditional random field (DCRF) is used to optimize the segmentation results. We only use T1w MRIs to segment PWMLs. The result shows that our model can well segment the lesion of ordinary size or even pixel size. The Dice similarity coefficient reaches 0.6616, the sensitivity is 0.7069, the specificity is 0.9997, and the Hausdorff distance is 52.9130. The proposed method outperforms the state-of-the-art algorithm. (The code of this paper is available on https://github.com/YalongLiu/Refined-Segmentation-R-CNN)

Published
2019

33. Reactive Toughening of Urea-Formaldehyde Resin With Polyvinyl alcohol) by Formation of Interpenetrating Networks

Author

Liu, Yalong, Yuan, Junling, Zhao, Xiaowen, and Ye, Lin

Subjects
Epoxy resins -- Mechanical properties -- Production processes, Formaldehyde -- Usage, Polyvinyl alcohol -- Usage, Activation energy, Urea, Polymerization, Engineering and manufacturing industries, Science and technology
Abstract

A series of urea-formaldehyde/poly(vinyl alcohol) (UF/PVA) blends were prepared via in situ polymerization. During the synthesis process, intra- and intermolecular acetalization of PVA occurred, along with the addition and condensation reactions between urea and formaldehyde, resulting in the formation of UF/PVA interpenetrating networks. With the increase of PVA content, the curing temperature shifted to higher temperatures and the activation energy (E) increased, suggesting that it was more difficult for the blends to cure. UF/PVA blends showed high storage modulus and only one broad tan [delta] peak, indicating that the stiffness was enhanced and the phase separation was limited at the chain segmental level. By the introduction of PVA, the elongation at break, impact strength, [K.sub.IC] value, and roughness of the fracture surface increased obviously, while the tensile strength can still maintain at a high level. Due to the forced compatibilization of the two components, homogeneous interpenetrating UF/PVA networks can form and thus the toughness of the blends was enhanced. POLYM. ENG. SCI., 58:2031-2038, 2018., INTRODUCTIONUrea-formaldehyde (UF) resin is one of the most important types of the so-called amino plastic resins, which is based on the manifold reaction of urea and formaldehyde [1]. By using [...]

Published
2018
Full Text
View/download PDF

38. Self-cleaning SiO2–TiO2ceramic membrane for enhanced oil–water separation

Author

Liu, Yalong, Xin, Binjie, Newton, Md All Amin, Li, Lifeng, and Gao, Di

Abstract

An efficient and practical method is proposed for the separation of oil–water mixtures and emulsions in sustainable water ecosystems, facilitating energy recovery. The construction of flexible ceramic fiber membranes with high throughput and self-cleaning capabilities has proven effective but challenging. This study reports a novel approach combining the sol–gel and electrospinning techniques to synthesize flexible silicon dioxide (SiO2)–titanium dioxide (TiO2) nanofiber membranes (STNFMs). These membranes possess nanoscale rough structures, granting them superhydrophilicity and underwater superoleophobicity (155°). Exploiting the photocatalytic properties of titanium dioxide, STNFMs-4 not only demonstrates excellent separation performance but also exhibits remarkable self-cleaning abilities. After 2 h of ultraviolet light irradiation, the membrane flux returns to its original level. STNFMs provide a promising solution for highly efficient separation of oil–water mixtures and emulsions, with the potential to play a significant role in water treatment and resource recovery.

Published
2024
Full Text
View/download PDF

39. Sulfur-doped porous carbon sheets embedded with rich iron sites for 1O2dominated peroxymonosulfate activationElectronic supplementary information (ESI) available. See DOI: https://doi.org/10.1039/d3en00971h

Author

Song, Yadan, Liu, Yalong, Li, Yangju, Hu, Haipeng, Huang, Kexin, Zhang, Zhe, Li, Zhongxian, Cao, Wanning, Jiang, Kai, and Wu, Dapeng

Abstract

The poor anti-interference ability of radical-dominated processes continues to be a hindrance to the effectiveness of purification and the practical use of peroxymonosulfate-based advanced oxidation processes (PMS-AOPs). Herein, iron, nitrogen, and sulfur co-doped porous carbon sheets (Fe–SNC) were successfully synthesized viaa one-step pyrolysis process by adopting Mohr's salt and ZIF-8 sheets as precursors to efficiently activate PMS. Quenching experiments and electron paramagnetic resonance (EPR) characterization indicated that singlet oxygen (1O2) played the most important role in phenol degradation. Based on the variation in the material structure and density functional theory (DFT) calculations, the study revealed the specific mechanism of sulfur embedded in rich Fe3C, Fe4N, and Fe–Nx catalytic sites as an activator of PMS in the degradation of the pollutant of interest. In addition, S-doping sites were shown to shorten the distance between PMS and the catalyst due to electron polarization of the catalyst surface, which facilitated PMS adsorption. According to ultra-high-resolution electrospray time-of-flight mass spectrometry and the predictions of ECOSAR software, the aquatic ecological environment would not be harmed by degradation intermediates. As a consequence, this heterogeneous system possesses admirable anti-interference in pollutant elimination. These conclusions provide instructions for the creation of S-doped porous carbon sheets for effective water treatment.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results