Search

Your search keyword '"Liao, Huai"' showing total 38 results
Start Over Author "Liao, Huai"
38 results on '"Liao, Huai"'

1. Multi-Stage Airway Segmentation in Lung CT Based on Multi-scale Nested Residual UNet

Author

Yang, Bingyu, Liao, Huai, Huang, Xinyan, Tian, Qingyao, Wu, Jinlin, Hu, Jingdi, and Liu, Hongbin

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

Accurate and complete segmentation of airways in chest CT images is essential for the quantitative assessment of lung diseases and the facilitation of pulmonary interventional procedures. Although deep learning has led to significant advancements in medical image segmentation, maintaining airway continuity remains particularly challenging. This difficulty arises primarily from the small and dispersed nature of airway structures, as well as class imbalance in CT scans. To address these challenges, we designed a Multi-scale Nested Residual U-Net (MNR-UNet), incorporating multi-scale inputs and Residual Multi-scale Modules (RMM) into a nested residual framework to enhance information flow, effectively capturing the intricate details of small airways and mitigating gradient vanishing. Building on this, we developed a three-stage segmentation pipeline to optimize the training of the MNR-UNet. The first two stages prioritize high accuracy and sensitivity, while the third stage focuses on repairing airway breakages to balance topological completeness and correctness. To further address class imbalance, we introduced a weighted Breakage-Aware Loss (wBAL) to heighten focus on challenging samples, penalizing breakages and thereby extending the length of the airway tree. Additionally, we proposed a hierarchical evaluation framework to offer more clinically meaningful analysis. Validation on both in-house and public datasets demonstrates that our approach achieves superior performance in detecting more accurate airway voxels and identifying additional branches, significantly improving airway topological completeness. The code will be released publicly following the publication of the paper.

Published
2024

2. EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy Labels

Author

Tian, Qingyao, Chen, Zhen, Liao, Huai, Huang, Xinyan, Li, Lujie, Ourselin, Sebastien, and Liu, Hongbin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Single-image depth estimation is essential for endoscopy tasks such as localization, reconstruction, and augmented reality. Most existing methods in surgical scenes focus on in-domain depth estimation, limiting their real-world applicability. This constraint stems from the scarcity and inferior labeling quality of medical data for training. In this work, we present EndoOmni, the first foundation model for zero-shot cross-domain depth estimation for endoscopy. To harness the potential of diverse training data, we refine the advanced self-learning paradigm that employs a teacher model to generate pseudo-labels, guiding a student model trained on large-scale labeled and unlabeled data. To address training disturbance caused by inherent noise in depth labels, we propose a robust training framework that leverages both depth labels and estimated confidence from the teacher model to jointly guide the student model training. Moreover, we propose a weighted scale-and-shift invariant loss to adaptively adjust learning weights based on label confidence, thus imposing learning bias towards cleaner label pixels while reducing the influence of highly noisy pixels. Experiments on zero-shot relative depth estimation show that our EndoOmni improves state-of-the-art methods in medical imaging for 41\% and existing foundation models for 25\% in terms of absolute relative error on specific dataset. Furthermore, our model provides strong initialization for fine-tuning to metric depth estimation, maintaining superior performance in both in-domain and out-of-domain scenarios. The source code will be publicly available.

Published
2024

3. PANS: Probabilistic Airway Navigation System for Real-time Robust Bronchoscope Localization

Author

Tian, Qingyao, Chen, Zhen, Liao, Huai, Huang, Xinyan, Yang, Bingyu, Li, Lujie, and Liu, Hongbin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Accurate bronchoscope localization is essential for pulmonary interventions, by providing six degrees of freedom (DOF) in airway navigation. However, the robustness of current vision-based methods is often compromised in clinical practice, and they struggle to perform in real-time and to generalize across cases unseen during training. To overcome these challenges, we propose a novel Probabilistic Airway Navigation System (PANS), leveraging Monte-Carlo method with pose hypotheses and likelihoods to achieve robust and real-time bronchoscope localization. Specifically, our PANS incorporates diverse visual representations (\textit{e.g.}, odometry and landmarks) by leveraging two key modules, including the Depth-based Motion Inference (DMI) and the Bronchial Semantic Analysis (BSA). To generate the pose hypotheses of bronchoscope for PANS, we devise the DMI to accurately propagate the estimation of pose hypotheses over time. Moreover, to estimate the accurate pose likelihood, we devise the BSA module by effectively distinguishing between similar bronchial regions in endoscopic images, along with a novel metric to assess the congruence between estimated depth maps and the segmented airway structure. Under this probabilistic formulation, our PANS is capable of achieving the 6-DOF bronchoscope localization with superior accuracy and robustness. Extensive experiments on the collected pulmonary intervention dataset comprising 10 clinical cases confirm the advantage of our PANS over state-of-the-arts, in terms of both robustness and generalization in localizing deeper airway branches and the efficiency of real-time inference. The proposed PANS reveals its potential to be a reliable tool in the operating room, promising to enhance the quality and safety of pulmonary interventions.

Published
2024

4. DD-VNB: A Depth-based Dual-Loop Framework for Real-time Visually Navigated Bronchoscopy

Author

Tian, Qingyao, Liao, Huai, Huang, Xinyan, Chen, Jian, Zhang, Zihui, Yang, Bingyu, Ourselin, Sebastien, and Liu, Hongbin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Real-time 6 DOF localization of bronchoscopes is crucial for enhancing intervention quality. However, current vision-based technologies struggle to balance between generalization to unseen data and computational speed. In this study, we propose a Depth-based Dual-Loop framework for real-time Visually Navigated Bronchoscopy (DD-VNB) that can generalize across patient cases without the need of re-training. The DD-VNB framework integrates two key modules: depth estimation and dual-loop localization. To address the domain gap among patients, we propose a knowledge-embedded depth estimation network that maps endoscope frames to depth, ensuring generalization by eliminating patient-specific textures. The network embeds view synthesis knowledge into a cycle adversarial architecture for scale-constrained monocular depth estimation. For real-time performance, our localization module embeds a fast ego-motion estimation network into the loop of depth registration. The ego-motion inference network estimates the pose change of the bronchoscope in high frequency while depth registration against the pre-operative 3D model provides absolute pose periodically. Specifically, the relative pose changes are fed into the registration process as the initial guess to boost its accuracy and speed. Experiments on phantom and in-vivo data from patients demonstrate the effectiveness of our framework: 1) monocular depth estimation outperforms SOTA, 2) localization achieves an accuracy of Absolute Tracking Error (ATE) of 4.7 $\pm$ 3.17 mm in phantom and 6.49 $\pm$ 3.88 mm in patient data, 3) with a frame-rate approaching video capture speed, 4) without the necessity of case-wise network retraining. The framework's superior speed and accuracy demonstrate its promising clinical potential for real-time bronchoscopic navigation.

Published
2024

5. BronchoTrack: Airway Lumen Tracking for Branch-Level Bronchoscopic Localization

Author

Tian, Qingyao, Liao, Huai, Huang, Xinyan, Yang, Bingyu, Wu, Jinlin, Chen, Jian, Li, Lujie, and Liu, Hongbin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Localizing the bronchoscope in real time is essential for ensuring intervention quality. However, most existing methods struggle to balance between speed and generalization. To address these challenges, we present BronchoTrack, an innovative real-time framework for accurate branch-level localization, encompassing lumen detection, tracking, and airway association.To achieve real-time performance, we employ a benchmark lightweight detector for efficient lumen detection. We are the first to introduce multi-object tracking to bronchoscopic localization, mitigating temporal confusion in lumen identification caused by rapid bronchoscope movement and complex airway structures. To ensure generalization across patient cases, we propose a training-free detection-airway association method based on a semantic airway graph that encodes the hierarchy of bronchial tree structures.Experiments on nine patient datasets demonstrate BronchoTrack's localization accuracy of 85.64 \%, while accessing up to the 4th generation of airways.Furthermore, we tested BronchoTrack in an in-vivo animal study using a porcine model, where it successfully localized the bronchoscope into the 8th generation airway.Experimental evaluation underscores BronchoTrack's real-time performance in both satisfying accuracy and generalization, demonstrating its potential for clinical applications.

Published
2024

7. An NMR Study on Two New β-Dihydroagrofuran Compounds in Celastrus angulatus Maxim

Author

LIAO Huai-yu, HAN Hong-yuan, CHEN Fei, ZHANG Hai-yan, YANG Jing, and ZHAO Tian-zeng

Subjects
nuclear magnetic resonance (nmr), celastrus l., β-dihydroagrofuran, celastrus angulatus maxim, Electricity and magnetism, QC501-766
Abstract

Two new β-dihydroagrofuran compounds, 1β,2β,15-triacetoxy-8α-(α-methyl)-butanoyloy-9β-benzoxy-4α,6α- dihydroxy-β-dihydroagrofuran (compound I) and 1β,15-diacetoxy-8α-(α-methyl)-propionyloxy-2β,9β-dibenzoxy-4α,6α- dihydroxy-β-dihydroagrofuran (compound II), were isolated from Celastrus angulatus Maxim. The chemical shifts of the two new compounds were assigned by one- and two-dimensional nuclear magnetic resonance (NMR) techniques. Their structures were elucidated.

Published
2021
Full Text
View/download PDF

12. Comparison of Gamma Irradiation Effects on Short Circuit Characteristics of SiC MOSFET Power Devices between Planar and Trench Structures.

Author

Shu, Lei, Liao, Huai-Lin, Wu, Zi-Yuan, Li, Yan-Yan, Fang, Xing-Yu, Liang, Shi-Wei, Li, Tong-De, Wang, Liang, Wang, Jun, and Zhao, Yuan-Fu

Subjects
SHORT circuits, METAL oxide semiconductor field-effect transistors, FIELD-effect transistors, TRENCHES, IRRADIATION, SILICON carbide
Abstract

The short circuit withstand energy (SCWE) variations, and short circuit withstand time (SCWT) variations, of planar and trench silicon carbide (SiC) metal-oxide-semiconductor field-effect transistor (MOSFET) power devices are studied after exposure to a total ionizing dose (TID). The results for ON bias are explored. The SCWE and SCWT are studied for planar and trench SiC MOSFET power devices tested for TID with gamma irradiation. A higher degradation phenomenon for the SCWE and SCWT are observed for the planar SiC MOSFET. The physical mechanisms for these variations are analyzed and confirmed by technology computer-aided design (TCAD) simulation. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

20. The application of transbronchial cryobiopsy in interstitial lung disease: a prospective, multicenter, real-world study

Author

Chen, Xiaobo, primary, Li, Jing, additional, Luo, Fengming, additional, Tao, Feng, additional, Zhang, Xiaoju, additional, Wu, Youru, additional, Xu, Ping, additional, Ke, Mingyao, additional, Long, Fa, additional, Liu, Laiyu, additional, Lv, Liping, additional, Liao, Huai, additional, Gu, Ye, additional, Liu, Zhiguang, additional, Tan, Xiaoming, additional, Guo, Shuliang, additional, Hu, Yi, additional, Yang, Huaping, additional, Zhou, Yong, additional, Zhou, Hongmei, additional, Ye, Yongshun, additional, Chen, Difei, additional, and Li, Shiyue, additional

Published
2021
Full Text
View/download PDF

21. Three new sesquiterpene polyol esters from Celastrus angulatus.

Author

Zhao, Wei, Chang, Xia, Yuan, Hang, Han, Hong-Yuan, Chen, Fei, Liao, Huai-Yu, Zhang, Hai-Yan, and Zhao, Tian-Zeng

Subjects
TERPENES, HIGH performance liquid chromatography, INSECTICIDES, NUCLEAR magnetic resonance spectroscopy, PHYTOCHEMICALS, DESCRIPTIVE statistics, PLANT extracts, MOLECULAR structure
Abstract

Three new sesquiterpene polyol ester compounds angulatins S-U, together with three known compounds were isolated from Celastrus angulatus Maxim. According to mainly 1D NMR and 2D NMR analysis, the structures of the new compounds were completely determined as angulatin S (1β-furoyloxy-2β,8α-diisobutanoyloxy-9β-benzoyloxy-15-acetoxy-4α,6α-dihydroxy-β-dihydroagarofuran), angulatin T (1β,2β,6α-triacetoxy-8β,15-diisobutanoyloxy-9α-benzoyloxy-β-dihydroagrofuran), and angulatin U (1β,6α,15-triacetoxy-8β-isobutanoyloxy-9α-benzoyloxy-β-dihydroagarofuran). [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

27. Efficiency of EBUS-TBNA for diagnosing benign and malignant lymphadenopathy.

Author

Liu, Yang-Li, Liu, Xiao-Ran, Li, Hui, Chen, Feng-Jia, Liao, Huai, and Xie, Can-Mao

Subjects
LYMPH nodes, TUBERCULOSIS, LUNG cancer, LYMPHATICS, CHEST diseases
Abstract

Objective: To determine whether endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) can rapidly distinguish among lung cancer, tuberculosis and sarcodosis, and to explore its sensitivity and specificity. Methods: Clinical data of patients with enlarged mediastinal or hilar lymphadenopathy who underwent EBUS-TBNA at our hospital between September 1, 2012 and June 30, 2015 for were retrospectively analyzed. The sensitivity, specificity, positive predictive value, and negative predicted value [including 95% confidence interval (CI)] were calculated.. Results: A total of 299 lymph nodes from 201 patients underwent EBUS-TBNA were selected and no serious complications occurred. EBUS-TBNA showed a sensitivity of 87.9% (124/141) (95% CI: 81%–92%), a specificity of 100.0% (124/124) (95% CI: 97%–100%), and a negative predicted value of 41.3% (95% CI: 23%–61%) in the detection of lung cancer. The sensitivity and specificity of diagnosis of mediastinal tuberculosis lymphadenitis were 72.4% (21/29) (95% CI: 53%–87%) and 100.0% (95% CI: 82%–100%); while sensitivity and specificity of diagnosis of sarcoidosis were 71.4% (5/7) (95% CI: 29%–96%) and 100.0% (95% CI: 91%–100%). Conclusions: The sensitivity and specificity of EBUS-TBNA do not significantly differ for a diagnosis of lung cancer versus tuberculosis or sarcodosis. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

35. SINGLE-CHAIN UROKINASE IN EMPYEMA INDUCED BY PASTURELLA MULTOCIDA.

Author

Idell, Steven, Jun Na, Moon, Liao, Huai, Gazar, A. E., Drake, Wonder, Lane, Kirk B., Koenig, Kathy, Komissarov, Andrey, Tucker, Torry, and Light, Richard W.

Subjects
EMPYEMA, FIBRIN, UROKINASE, FLUID mechanics, FIBRINOLYSIS
Abstract

Intrapleural fibrin deposition and subsequent fibrosis characterize evolving empyema and contribute to the morbidity associated with this condition. Single-chain urokinase (scuPA) is proenzyme form of the urokinase plasminogen activator, which has recently been shown to effectively clear intrapleural loculation in tetracycline-induced pleurodesis in rabbits. The authors therefore hypothesized that scuPA could likewise improve intrapleural injury associated with empyema. The authors used a rabbit model of empyema induced by intrapleural administration of Pasturella multocida to test this hypothesis and determined the effects of intrapleural scuPA on pleural fluids indices of inflammation and intrapleural fibrosis. The authors found that intrapleural administration of scuPA was well tolerated, generated readily detectable fibrinolytic activity in the empyema fluids and did not induce intrapleural or systemic bleeding. Pleural fluid volume, intrapleural protein, and D-dimer concentrations were increased at 24 and 48 hours (P < .01, respectively) after induction of empyema. Intrapleural loculation did not occur in the scuPA- or vehicle control-treated animals and there was no significant change in the pleural empyema or thickening scores. These findings confirm that intrapleural scuPA generates fibrinolysis in empyema fluids but does not alter fibrotic repair at the pleural surface or the intensity of intrapleural inflammation in this empyema model. [ABSTRACT FROM AUTHOR]

Published
2009
Full Text
View/download PDF

36. Three novel sesquiterpene polyol esters from the root bark of Celastrus angulatus Maxim and their nitric oxide inhibitory activity.

Author

Liao HY, Du SW, Yang J, Chen F, Han HY, Liu SY, Wang HF, Zhang HY, and Zhao TZ

Abstract

Three new sesquiterpene polyol ester compounds angulatin V [1 β ,15-diacetoxy-2 β -(α-methyl)-butanoyloxy-4α,6α-dihydroxy-8α-isobutanoyloxy-9 β -benzoxy- β -dihydroagarofuran], angulatin W [1 β ,2 β -diacetoxy-4α,6α-dihydroxy-8-carbonyl-9 β -benzoxy-15-isobutanoyloxy- β -dihydroagarofuran], angulatin X [1 β ,2 β, 8α-triacetoxy-4α, 6α-dihydroxy-9 β -benzoxy-15-nicotinyl- β -dihydroagarofuran] ( 1-3 ), together with one known compound Putterine B ( 4 ), were isolated from the root bark of Celastrus angulatus Maxim. The structures of compounds 1-3 were elucidated by NMR, HRESIMS, IR data, and comparison with the literature data. The anti-inflammatory activity of all compounds was evaluated by measuring nitric oxide production in RAW264.7 macrophages. Compounds 1-4 showed no significant nitric oxide inhibitory activity at 2.5 and 5 μM concentrations.

Published
2024
Full Text
View/download PDF

37. Prognostic value of cancer stem cell marker CD133 expression in esophageal carcinoma: A meta-analysis.

Author

Sui YP, Jian XP, Ma LI, Xu GZ, Liao HW, Liu YP, and Wen HC

Abstract

CD133 has been identified as a putative neoplastic stem cell marker in esophageal carcinoma. However, the prognostic value of CD133 overexpression in patients with esophageal carcinoma remains controversial. A meta-analysis of previous studies was performed, in order to assess the association of CD133 overexpression with the clinicopathological characteristics of esophageal carcinoma patients. A total of 7 studies, including 538 patients, were subjected to the final analysis. Our results indicated that a positive CD133 expression was significantly associated with lymph node metastasis [odds ratio (OR)=3.09, 95% confidence interval (CI): 1.93-4.95; P<0.00001], clinical stage (OR=4.26, 95% CI: 1.55-11.73; P=0.005) and histopathological grade (OR=2.40, 95% CI: 1.16-4.94; P=0.02). There was no statistically significant association of CD133 with depth of invasion (OR=1.89, 95% CI: 0.42-8.43; P=0.41). Based on the results of this study, we concluded that CD133 is an efficient prognostic factor in esophageal carcinoma. Higher CD133 expression is significantly associated with lymph node metastasis, clinical stage and histopathological grade.

Published
2016
Full Text
View/download PDF

38. [Effect of hypertonic medium on expression of aquaporin-1 in pleural mesothelial cells: experiment with rats].

Author

Zhang W, Xie CM, Huang JQ, Liao H, and Ke CX

Subjects
Animals, Aquaporin 1 genetics, Blotting, Western, Cells, Cultured, Epithelial Cells cytology, Epithelial Cells metabolism, Gene Expression drug effects, Male, Pleura cytology, RNA, Messenger genetics, RNA, Messenger metabolism, Random Allocation, Rats, Rats, Wistar, Reverse Transcriptase Polymerase Chain Reaction, Time Factors, Aquaporin 1 biosynthesis, Epithelial Cells drug effects, Saline Solution, Hypertonic pharmacology
Abstract

Objective: To study the expression of aquaporin-1 (AQP-1) in pleural mesothelial cells (PMCs) and the influence of hypertonic medium thereupon., Methods: Rat PMCs were isolated, cultured, and divided into 2 groups: hypertonic group, cultured in hypertonic media with NaCl of different concentrations for 24 h and control group, cultured in D-MEM/F-12 medium. The 100 mmol/L NaCI group was examined at the time points 6, 12, 18, and 24 h respectively. RT-PCR and Western blotting were used to analyze the mRNA and protein expression of AQP-1., Results: The A values of AQP-1 protein expression were 24.0 +/- 1.8, 27.8 +/- 2.4, 31.7 +/- 2.5, 89.7 +/- 6.2, and 107.7 +/- 9.3 respectively in the PMCs treated with hypertonic media with NaCl of the concentrations of 25, 50, 75, 100, and 150 mmol/L, all significantly higher than that in the control group (10.8 +/- 1.5, all P < 0.01). The A values of AQP-1 protein expression were 42.1 +/- 2.6, 78.9 +/- 3.6, 109.6 +/- 7.6, and 123.4 +/- 8.7 in the PMCs treated with hypertonic media with NaCl of the concentration of 100 mmol/L after 6 h, 12 h, 18 h, and 24 h, all significantly higher than that in the control group (12.9 +/- 1.9, P < 0. 01). The a values of AQP-1 mRNA expression were 62.6 +/- 6.4, 75.3 +/- 5.5, 122.3 +/- 11.4, 196.2 +/- 18.1, and 223.0 +/- 19.3 respectively in the PMCs treated with hypertonic media with NaCl of the concentrations of 25, 50, 75, 100, and 150 mmol/L, all significantly higher than that in the control group (23.5 +/- 2.7, all P < 0.01). The A values of AQP-1 protein expression were 83.6 +/- 6.1, 159.3 +/- 6.9, 266.2 +/- 24.1, and 196.2 +/- 15.7 in the PMCs treated with hypertonic media with NaCl of the concentration of 100 mmol/L after 6 h, 12 h, 18 h, and 24 h, all significantly higher than that in the control group (26.5 +/- 2.8, P < 0.01)., Conclusion: Hypertonic medium increases the expression of AQP-1 mRNA and protein. AQP-1 participates in the pleural fluid formation.

Published
2007

Catalog

Books, media, physical & digital resources
See catalog results