Wei Xu
Wei Xu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Baoxin Liu
Tongji Univ, Shanghai Peoples Hosp 10, Dept Cardiol, Sch Med, Shanghai, Peoples R China
1 shared publicationBeibei Shi
Tongji Univ, Shanghai Peoples Hosp 10, Dept Cardiol, Sch Med, Shanghai, Peoples R China
1 shared publicationChuanzhen Hao
Tongji Univ, Shanghai Peoples Hosp 10, Dept Cardiol, Sch Med, Shanghai, Peoples R China
1 shared publicationChufan Hu
University of Sydney,School of Engineering,Sydney,New South Wales,Australia,2006
1 shared publicationJiachen Luo
Tongji Univ, Shanghai Peoples Hosp 10, Dept Cardiol, Sch Med, Shanghai, Peoples R China
1 shared publication- Junfeng Yuan
School of Physical Education, Guizhou Normal University, University Town, Siya Road, Huaxi District, Guiyang, 550025, China, 86 86751983
1 shared publication
Latest Publications
- 29 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1049-1055
Solving the point cloud registration based on deep learning
Point cloud registration is used to create a complete environment map with multiple pieces of scans. It is used mostly to guide autonomous robots when the surrounding is complicated. However, the problem is hard to solve so deep learning networks are often utilized. Most neural networks proposed need manual annotation and selection of patches which is time-consuming and makes the model only work for one particular scenario. In this work, a new method is studied in which a self-supervised learning technique is incorporated into the network. The input to this network is one raw point cloud without any labels or annotations, and as a result, the need for annotating or selecting patches is removed. A key point sampling process is also implemented in this network, which filters non-relevant points and further improves the performance. Based on our experiments, this self-supervised model has the capability of performing better than those requiring manual processing of the input.
- 29 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1049-1055
Solving the point cloud registration based on deep learning
Point cloud registration is used to create a complete environment map with multiple pieces of scans. It is used mostly to guide autonomous robots when the surrounding is complicated. However, the problem is hard to solve so deep learning networks are often utilized. Most neural networks proposed need manual annotation and selection of patches which is time-consuming and makes the model only work for one particular scenario. In this work, a new method is studied in which a self-supervised learning technique is incorporated into the network. The input to this network is one raw point cloud without any labels or annotations, and as a result, the need for annotating or selecting patches is removed. A key point sampling process is also implemented in this network, which filters non-relevant points and further improves the performance. Based on our experiments, this self-supervised model has the capability of performing better than those requiring manual processing of the input.
- Open Access
- 1 April 2022
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 17, 479-493
Prognostic Significance of New-Onset Atrial Fibrillation in Heart Failure with Preserved, Mid-Range, and Reduced Ejection Fraction Following Acute Myocardial Infarction: Data from the NOAFCAMI-SH Registry
Purpose: The prognostic impact of new-onset atrial fibrillation (NOAF) among different heart failure (HF) subtypes including HF with preserved (HFpEF, ejection fraction [EF] ≥ 50%), mid-range (HFmrEF, EF 40%∼ 49%), and reduced (HFrEF, EF < 40%) EF following acute myocardial infarction (AMI) remains unclear. We aimed to investigate the incidence and prognostic implication of post-MI NOAF across HF subtypes. Patients and Methods: We included 1413 patients with post-MI HF (743 with HFpEF, 342 with HFmrEF and 328 with HFrEF) between February 2014 and March 2018. NOAF was considered as patients without a preexisting AF who developed AF during the AMI hospitalization. The primary endpoint was all-cause mortality. Results: Of 1413 patients (mean age 66.8 ± 12.6 years, 72.9% men) analyzed, 200 (14.2%) developed post-MI NOAF. Patients with HFrEF were more likely to experience NOAF compared to those with HFmrEF or HFrEF (18.9%, 13.7% and 12.2% in HFrEF, HFmrEF and HFpEF, respectively; p for trend = 0.006). During a median follow-up of 28.5 months, 192 patients died (70 with HFrEF, 35 with HFmrEF and 87 with HFpEF) and 195 patients experienced HF rehospitalization (79 with HFrEF, 37 with HFmrEF and 79 with HFpEF). After multivariable adjustment, NOAF was independently associated with all-cause mortality (hazard ratio [HR]: 1.79, 95% confidence interval [CI]: 1.03– 3.12) only in the HFrEF group compared to sinus rhythm (SR), whereas an increased risk of HF rehospitalization was found in all HF subtypes, particularly in HFmrEF (HR: 5.08, 95% CI: 2.29– 11.25) and HFpEF (HR: 2.83 95% CI: 1.64– 4.90). Conclusion: In patients with post-MI HF, NOAF carried a worse prognosis for all-cause death in the HFrEF group and for HF rehospitalization in all HF subtypes.
- 1 April 2022
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 17, 479-493
Open AccessPrognostic Significance of New-Onset Atrial Fibrillation in Heart Failure with Preserved, Mid-Range, and Reduced Ejection Fraction Following Acute Myocardial Infarction: Data from the NOAFCAMI-SH Registry
Purpose: The prognostic impact of new-onset atrial fibrillation (NOAF) among different heart failure (HF) subtypes including HF with preserved (HFpEF, ejection fraction [EF] ≥ 50%), mid-range (HFmrEF, EF 40%∼ 49%), and reduced (HFrEF, EF < 40%) EF following acute myocardial infarction (AMI) remains unclear. We aimed to investigate the incidence and prognostic implication of post-MI NOAF across HF subtypes. Patients and Methods: We included 1413 patients with post-MI HF (743 with HFpEF, 342 with HFmrEF and 328 with HFrEF) between February 2014 and March 2018. NOAF was considered as patients without a preexisting AF who developed AF during the AMI hospitalization. The primary endpoint was all-cause mortality. Results: Of 1413 patients (mean age 66.8 ± 12.6 years, 72.9% men) analyzed, 200 (14.2%) developed post-MI NOAF. Patients with HFrEF were more likely to experience NOAF compared to those with HFmrEF or HFrEF (18.9%, 13.7% and 12.2% in HFrEF, HFmrEF and HFpEF, respectively; p for trend = 0.006). During a median follow-up of 28.5 months, 192 patients died (70 with HFrEF, 35 with HFmrEF and 87 with HFpEF) and 195 patients experienced HF rehospitalization (79 with HFrEF, 37 with HFmrEF and 79 with HFpEF). After multivariable adjustment, NOAF was independently associated with all-cause mortality (hazard ratio [HR]: 1.79, 95% confidence interval [CI]: 1.03– 3.12) only in the HFrEF group compared to sinus rhythm (SR), whereas an increased risk of HF rehospitalization was found in all HF subtypes, particularly in HFmrEF (HR: 5.08, 95% CI: 2.29– 11.25) and HFpEF (HR: 2.83 95% CI: 1.64– 4.90). Conclusion: In patients with post-MI HF, NOAF carried a worse prognosis for all-cause death in the HFrEF group and for HF rehospitalization in all HF subtypes.