Tianbao Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tianbao Liu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Andrei Ivanets
Institute of General and Inorganic Chemistry of the National Academy of Sciences of Belarus, Surganova St., 9/1, 220072, Minsk, Belarus
1 shared publicationChuanpu Li
Southern Medical University,School of Biomedical Engineering,Guangzhou,China
1 shared publicationJi-Jun Liu
1 shared publication- Jie Chang
The State Key Lab of High Performance Ceramics and Superfine Microstructure
1 shared publication Jing Lu
Geologic Party No.216, CNNC, Urumqi, Xinjiang, 830011, PR China
1 shared publication- Jinhua Zhang
College of Life Science, Shanxi University, Taiyuan 030006, China
1 shared publication
Latest Publications
- Open Access
- 1 June 2026
- Published by KEAI Publishing in Petroleum Science
- Vol. 23 (6) , 3682-3697
TransUNet framework improved computed tomography image segmentation for core pore evolution
- 1 June 2026
- Published by KEAI Publishing in Petroleum Science
- Vol. 23 (6) , 3682-3697
Open AccessTransUNet framework improved computed tomography image segmentation for core pore evolution
- 9 June 2022
- Published by Elsevier in Chemosphere
- Vol. 304, 135303
Fe/C materials prepared by one-step calcination of acidified municipal sludge and their excellent adsorption of Cr(VI)
- 9 June 2022
- Published by Elsevier in Chemosphere
- Vol. 304, 135303
Fe/C materials prepared by one-step calcination of acidified municipal sludge and their excellent adsorption of Cr(VI)
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
SPA-RESUNET: Strip Pooling Attention Resunet for Multi-Class Segmentation of Vertebrae and Intervertebral Discs
Automated multi-class segmentation of vertebrae and intervertebral discs for volumetric magnetic resonance image(MRI) can help the diagnosis and the treatment of many spinal diseases. However, existing methods based on fully convolutional network mostly stacked local convolution and pooling operations, and thus failed to capture the long-range dependencies for spine segmentation. In this paper, we propose a novel and computation-efficient residual U-Net with strip-pooling attention mechanism (SPA-ResUNet) for the multi-class segmentation of vertebrae and intervertebral discs. Due to the effectiveness of skip connections in U-Net, the strip pooling attention module is adopted in the skip connections to learn the long-range dependencies for improving the segmentation performance of the top structures and sacral crest of spine. Our SPA-ResUNet was implemented on the MRSpineSeg Challenge dataset. Experiments show that our SPA-ResUNet achieves impressive performance with mean Dice similarity coefficients of 88.14% and 87.88% in all 19 spinal structures on two test datasets, respectively. The visual segmentation results also show that our method achieves superior segmentation in top structures and sacral crest of spine. The proposed SPA-ResUNet has high potential in aiding the diagnosis and the treatment of spinal diseases.
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
SPA-RESUNET: Strip Pooling Attention Resunet for Multi-Class Segmentation of Vertebrae and Intervertebral Discs
Automated multi-class segmentation of vertebrae and intervertebral discs for volumetric magnetic resonance image(MRI) can help the diagnosis and the treatment of many spinal diseases. However, existing methods based on fully convolutional network mostly stacked local convolution and pooling operations, and thus failed to capture the long-range dependencies for spine segmentation. In this paper, we propose a novel and computation-efficient residual U-Net with strip-pooling attention mechanism (SPA-ResUNet) for the multi-class segmentation of vertebrae and intervertebral discs. Due to the effectiveness of skip connections in U-Net, the strip pooling attention module is adopted in the skip connections to learn the long-range dependencies for improving the segmentation performance of the top structures and sacral crest of spine. Our SPA-ResUNet was implemented on the MRSpineSeg Challenge dataset. Experiments show that our SPA-ResUNet achieves impressive performance with mean Dice similarity coefficients of 88.14% and 87.88% in all 19 spinal structures on two test datasets, respectively. The visual segmentation results also show that our method achieves superior segmentation in top structures and sacral crest of spine. The proposed SPA-ResUNet has high potential in aiding the diagnosis and the treatment of spinal diseases.
- 14 August 2017
- Published by Royal Society of Chemistry (RSC) in New Journal of Chemistry
- Vol. 41 (19) , 10695-10702
Two-step controllable preparation of NiO nanocrystal anchored reduced graphene oxide sheets and their electrochemical performance as supercapacitors
A feasible and expandable two-step strategy for the preparation of reduced graphene oxide (rGO) supported NiO nanocrystals (rGO-NiO) was developed using graphene oxide (GO), nickel sulfate and ammonia as raw materials. The rGO-NiO composites were obtained with the benefit of electrostatic attraction between GO and Ni2+ (or Ni(OH)2) in a mild solution phase precipitation process and a sequent simultaneous thermal decomposition of Ni(OH)2 and reduction of GO in Ar. The influence of calcination temperature on the morphology, structure and electrochemical performance of the composites was investigated. The results show that the calcination temperature has less impact on the morphology of the composites. Homogenous cubic NiO nanocrystals (vs. 422 F g−1 at 1 A g−1 and 600 vs. 360 F g−1 at 20 A g−1), but shows inferior rate capability (57.4% vs. 85.3% from 1 to 20 A g−1) and cycling stability (83% vs. 137% after 2000 cycles).
- 14 August 2017
- Published by Royal Society of Chemistry (RSC) in New Journal of Chemistry
- Vol. 41 (19) , 10695-10702
Two-step controllable preparation of NiO nanocrystal anchored reduced graphene oxide sheets and their electrochemical performance as supercapacitors
A feasible and expandable two-step strategy for the preparation of reduced graphene oxide (rGO) supported NiO nanocrystals (rGO-NiO) was developed using graphene oxide (GO), nickel sulfate and ammonia as raw materials. The rGO-NiO composites were obtained with the benefit of electrostatic attraction between GO and Ni2+ (or Ni(OH)2) in a mild solution phase precipitation process and a sequent simultaneous thermal decomposition of Ni(OH)2 and reduction of GO in Ar. The influence of calcination temperature on the morphology, structure and electrochemical performance of the composites was investigated. The results show that the calcination temperature has less impact on the morphology of the composites. Homogenous cubic NiO nanocrystals (vs. 422 F g−1 at 1 A g−1 and 600 vs. 360 F g−1 at 20 A g−1), but shows inferior rate capability (57.4% vs. 85.3% from 1 to 20 A g−1) and cycling stability (83% vs. 137% after 2000 cycles).