Mi Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mi Chen has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
- Albert Markus Kasel
Department of Cardiology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
7 shared publications Felix C. Tanner
5 shared publicationsBarbara E. Stähli
Department of Cardiology, University Heart Center, University Hospital Zurich and the Center for Translational and Experimental Cardiology (CTEC), University of Zurich, Zurich, Switzerland
4 shared publicationsJonathan M. Michel
Department of Cardiology, University Heart Centre, University Hospital Zurich, Zurich, Switzerland
4 shared publicationsJonathan Michel
Department of Cardiology, University Hospital Zurich, University of Zurich , Raemistrasse 100, Zurich 8091
4 shared publications- Barbara Elisabeth Stähli
Department of Cardiology, University Heart Center, Center for Translational and Experimental Cardiology (CTEC), University Hospital Zurich, University of Zurich, Zurich, Switzerland.
3 shared publications
Latest Publications
- Open Access
- 8 July 2026
- Published by Elsevier in JACC: Case Reports
- Vol. 31 (27) , 109091
Reading TTVR Mechanically
- 8 July 2026
- Published by Elsevier in JACC: Case Reports
- Vol. 31 (27) , 109091
Open AccessReading TTVR Mechanically
- Open Access
AutoClip: AI-Guided TEE Semantic Segmentation for TEER A Proof-of-Concept Study
Background: Transcatheter edge-to-edge repair (TEER) is an established treatment for mitral regurgitation but remains highly dependent on operator experience and complex transesophageal echocardiography (TEE)-guided intraprocedural imaging. Artificial intelligence (AI)-based semantic segmentation may improve procedural reproducibility and intraprocedural guidance; however, no TEER-specific segmentation framework has been reported. Objectives: To develop and evaluate AutoClip, a clinician-driven AI-guided TEE semantic segmentation model designed for simultaneous delineation of mitral valve anatomy and in-vivo TEER device components. Methods: A retrospective proof-of-concept study was conducted using 987 intraprocedural TEE frames derived from 10 video clips in 3 patients undergoing MitraClip G4 implantation. Seven semantic labels, including mitral leaflets and device components, were manually annotated using ITK-SNAP. Following standardized preprocessing and region-of-interest extraction, an Attention U-Net architecture was trained frame-wise on bicommissural and corresponding X-plane TEE views. Model performance was assessed using mean intersection-over-union (IoU) and Dice coefficient on an independent test set. Results: The Attention U-Net demonstrated improved sensitivity to small device structures compared with conventional U-Net architectures. Preliminary training performance achieved a mean IoU of approximately 0.93, while independent test performance reached a mean IoU of 0.46 across foreground classes. Qualitative assessment demonstrated feasible simultaneous segmentation of mitral leaflets, clip arms, grippers, and delivery shaft during TEER procedures. Conclusions: AutoClip represents a proof-of-concept TEER-specific TEE semantic segmentation framework initiated through a clinician-oriented workflow without formal computer science expertise. Although preliminary accuracy remains modest due to limited sample size, this study establishes a reproducible pathway for future AI-assisted intraprocedural guidance systems and larger multicenter development efforts in structural heart interventions.
Open AccessAutoClip: AI-Guided TEE Semantic Segmentation for TEER A Proof-of-Concept Study
Background: Transcatheter edge-to-edge repair (TEER) is an established treatment for mitral regurgitation but remains highly dependent on operator experience and complex transesophageal echocardiography (TEE)-guided intraprocedural imaging. Artificial intelligence (AI)-based semantic segmentation may improve procedural reproducibility and intraprocedural guidance; however, no TEER-specific segmentation framework has been reported. Objectives: To develop and evaluate AutoClip, a clinician-driven AI-guided TEE semantic segmentation model designed for simultaneous delineation of mitral valve anatomy and in-vivo TEER device components. Methods: A retrospective proof-of-concept study was conducted using 987 intraprocedural TEE frames derived from 10 video clips in 3 patients undergoing MitraClip G4 implantation. Seven semantic labels, including mitral leaflets and device components, were manually annotated using ITK-SNAP. Following standardized preprocessing and region-of-interest extraction, an Attention U-Net architecture was trained frame-wise on bicommissural and corresponding X-plane TEE views. Model performance was assessed using mean intersection-over-union (IoU) and Dice coefficient on an independent test set. Results: The Attention U-Net demonstrated improved sensitivity to small device structures compared with conventional U-Net architectures. Preliminary training performance achieved a mean IoU of approximately 0.93, while independent test performance reached a mean IoU of 0.46 across foreground classes. Qualitative assessment demonstrated feasible simultaneous segmentation of mitral leaflets, clip arms, grippers, and delivery shaft during TEER procedures. Conclusions: AutoClip represents a proof-of-concept TEER-specific TEE semantic segmentation framework initiated through a clinician-oriented workflow without formal computer science expertise. Although preliminary accuracy remains modest due to limited sample size, this study establishes a reproducible pathway for future AI-assisted intraprocedural guidance systems and larger multicenter development efforts in structural heart interventions.
- Open Access
- 20 November 2025
- Published by Elsevier in Structural Heart
- Vol. 9 (12)
Indirect Annuloplasty for Functional Mitral Regurgitation: CINCH or CLIP?
- 20 November 2025
- Published by Elsevier in Structural Heart
- Vol. 9 (12)
Open AccessIndirect Annuloplasty for Functional Mitral Regurgitation: CINCH or CLIP?
- Open Access
- 9 October 2025
- Published by Elsevier in Structural Heart
- Vol. 9 (12) , 100735
Left Atrial Appendage Occlusion Using the Amplatzer Amulet Device in High-Risk Patients With Atrial Fibrillation Undergoing Transcatheter Aortic Valve Intervention: A Randomized Pilot Study
- 9 October 2025
- Published by Elsevier in Structural Heart
- Vol. 9 (12) , 100735
Open AccessLeft Atrial Appendage Occlusion Using the Amplatzer Amulet Device in High-Risk Patients With Atrial Fibrillation Undergoing Transcatheter Aortic Valve Intervention: A Randomized Pilot Study
- Open Access
- 1 October 2025
- Published by SMW Supporting Association in Swiss Medical Weekly
- Vol. 155 (10) , 4288
Safety and effectiveness of left atrial appendage occlusion in patients with atrial fibrillation and high bleeding risk: a cardinality-matched comparison with direct oral anticoagulation on long-term stroke and bleeding rates
STUDY AIMS: Left atrial appendage occlusion (LAAO) is an accepted alternative stroke prevention strategy for patients with atrial fibrillation (AF) and contraindications to oral anticoagulation despite the lack of randomised data in this population. This study aims to compare the outcomes of LAAO and direct oral anticoagulation (DOAC) therapy in patients with high bleeding risk. METHODS: This cardinality-matched analysis comprised data from the Beat-AF and Swiss-AF cohorts (n = 3960; enrolment from 2010 to 2014 and from 2014 to 2017, respectively), along with the Zurich LAAO Registry (n = 535; patients included between 2010 and 2023). The primary endpoint was a composite of stroke, cardiovascular death or major bleeding. The individual components constituted the secondary endpoints. Time-dependent cumulative incidence curves were constructed and a competing risk analysis was included. RESULTS: After matching, 478 patients with a DOAC score ≥8 and 159 patients with previous major bleeding were compared in a 1:1 and 1:2 ratio, respectively, regarding their stroke prevention strategy (DOAC versus LAAO). After a median follow-up time of 4.9 years (interquartile range [IQR]: 2.2–6.1) in all patients with a DOAC score ≥8 and 4.4 years (IQR: 2.0–6.0) in all patients with previous major bleeding, there were no significant differences in the primary endpoint (hazard ratio [HR]: 0.88, 95% confidence interval [CI]: 0.67–1.14, p = 0.33 and HR: 0.79, 95% CI: 0.50–1.27, p = 0.33) and in the rates of stroke (HR: 0.74, 95% CI: 0.39–1.42, p = 0.36 and HR: 1.09, 95% CI: 0.33–3.62, p = 0.89) and cardiovascular death (HR: 0.97, 95% CI: 0.68–1.38, p = 0.85 and HR: 0.91, 95% CI: 0.50–1.64, p = 0.74). The rate of major bleedings was significantly lower in the LAAO group of both cohorts (HR: 0.55, 95% CI: 0.32–0.94, p = 0.029 and HR: 0.32, 95% CI: 0.13–0.79, p = 0.013). CONCLUSION: In this high bleeding risk population, LAAO was associated with similar effectiveness in preventing atrial fibrillation-related stroke and cardiovascular death and significantly lower rates of major bleeding compared to DOAC therapy. This strengthens the value of LAAO as an alternative stroke prevention strategy for patients at high risk of bleeding.
- 1 October 2025
- Published by SMW Supporting Association in Swiss Medical Weekly
- Vol. 155 (10) , 4288
Open AccessSafety and effectiveness of left atrial appendage occlusion in patients with atrial fibrillation and high bleeding risk: a cardinality-matched comparison with direct oral anticoagulation on long-term stroke and bleeding rates
STUDY AIMS: Left atrial appendage occlusion (LAAO) is an accepted alternative stroke prevention strategy for patients with atrial fibrillation (AF) and contraindications to oral anticoagulation despite the lack of randomised data in this population. This study aims to compare the outcomes of LAAO and direct oral anticoagulation (DOAC) therapy in patients with high bleeding risk. METHODS: This cardinality-matched analysis comprised data from the Beat-AF and Swiss-AF cohorts (n = 3960; enrolment from 2010 to 2014 and from 2014 to 2017, respectively), along with the Zurich LAAO Registry (n = 535; patients included between 2010 and 2023). The primary endpoint was a composite of stroke, cardiovascular death or major bleeding. The individual components constituted the secondary endpoints. Time-dependent cumulative incidence curves were constructed and a competing risk analysis was included. RESULTS: After matching, 478 patients with a DOAC score ≥8 and 159 patients with previous major bleeding were compared in a 1:1 and 1:2 ratio, respectively, regarding their stroke prevention strategy (DOAC versus LAAO). After a median follow-up time of 4.9 years (interquartile range [IQR]: 2.2–6.1) in all patients with a DOAC score ≥8 and 4.4 years (IQR: 2.0–6.0) in all patients with previous major bleeding, there were no significant differences in the primary endpoint (hazard ratio [HR]: 0.88, 95% confidence interval [CI]: 0.67–1.14, p = 0.33 and HR: 0.79, 95% CI: 0.50–1.27, p = 0.33) and in the rates of stroke (HR: 0.74, 95% CI: 0.39–1.42, p = 0.36 and HR: 1.09, 95% CI: 0.33–3.62, p = 0.89) and cardiovascular death (HR: 0.97, 95% CI: 0.68–1.38, p = 0.85 and HR: 0.91, 95% CI: 0.50–1.64, p = 0.74). The rate of major bleedings was significantly lower in the LAAO group of both cohorts (HR: 0.55, 95% CI: 0.32–0.94, p = 0.029 and HR: 0.32, 95% CI: 0.13–0.79, p = 0.013). CONCLUSION: In this high bleeding risk population, LAAO was associated with similar effectiveness in preventing atrial fibrillation-related stroke and cardiovascular death and significantly lower rates of major bleeding compared to DOAC therapy. This strengthens the value of LAAO as an alternative stroke prevention strategy for patients at high risk of bleeding.
- 29 March 2025
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 46 (22) , 2130
26 mm SAPIEN fractured 23 mm SAPIEN and surgical prosthesis: a transcatheter aortic valve-in-valve-in-valve implantation
- 29 March 2025
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 46 (22) , 2130
26 mm SAPIEN fractured 23 mm SAPIEN and surgical prosthesis: a transcatheter aortic valve-in-valve-in-valve implantation
- Open Access
- 5 March 2025
- Published by Elsevier in JACC: Case Reports
- Vol. 30 (5) , 102987
Tricuspid Regurgitation–Patent Foramen Ovale Coupling
- 5 March 2025
- Published by Elsevier in JACC: Case Reports
- Vol. 30 (5) , 102987
Open AccessTricuspid Regurgitation–Patent Foramen Ovale Coupling
- Open Access
- 1 March 2025
- Published by Elsevier in Structural Heart
- Vol. 9 (6)
Novel Technique Employing Transcatheter Balloon-Expandable Valves in Pure Aortic Regurgitation: A Proof-of-Concept Study
- 1 March 2025
- Published by Elsevier in Structural Heart
- Vol. 9 (6)
Open AccessNovel Technique Employing Transcatheter Balloon-Expandable Valves in Pure Aortic Regurgitation: A Proof-of-Concept Study
- Open Access
- 25 June 2024
- Published by Elsevier in Structural Heart
- Vol. 8 (5) , 100331
A Novel Risk Score Facilitates Femoral Artery Access in Transcatheter Aortic Valve Implantation: Passage-Puncture Score
- 25 June 2024
- Published by Elsevier in Structural Heart
- Vol. 8 (5) , 100331
Open AccessA Novel Risk Score Facilitates Femoral Artery Access in Transcatheter Aortic Valve Implantation: Passage-Puncture Score
- 8 April 2024
- Published by Elsevier in JACC: Cardiovascular Interventions
- Vol. 17 (7) , 938-939
Transjugular Mitral Edge-to-Edge Repair
- 8 April 2024
- Published by Elsevier in JACC: Cardiovascular Interventions
- Vol. 17 (7) , 938-939
Transjugular Mitral Edge-to-Edge Repair