Yiheng Lyu

Mr. Yiheng Lyu

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
ETEdward Tai Truong
Edward Tai Truong
YLYiheng Lyu
Yiheng Lyu
AIAbdul Rahman Ihdayhid
Abdul Rahman Ihdayhid
NLNick S. R. Lan
Nick S. R. Lan
GDGirish Dwivedi
Girish Dwivedi
Atrial fibrillation (AF) is the most common type of cardiac arrhythmia, with catheter ablation being a key alternative to medical treatment for restoring normal sinus rhythm. Despite advances in understanding AF pathogenesis, approximately 35% of patients experience AF recurrence at 12 months after catheter ablation. Therefore, accurate prediction of AF recurrence occurring after catheter ablation is important for patient selection and management. Conventional methods for predicting post-catheter ablation AF recurrence, which involve the use of univariate predictors and scoring systems, have played a supportive role in clinical decision-making. In an ever-changing landscape where technology is becoming ubiquitous within medicine, cardiac imaging and artificial intelligence (AI) could prove pivotal in enhancing AF recurrence predictions by providing data with independent predictive power and identifying key relationships in the data. This review comprehensively explores the existing methods for predicting the recurrence of AF following catheter ablation from different perspectives, including conventional predictors and scoring systems, cardiac imaging-based methods, and AI-based methods developed using a combination of demographic and imaging variables. By summarising state-of-the-art technologies, this review serves as a roadmap for developing future prediction models with enhanced accuracy, generalisability, and explainability, potentially contributing to improved care for patients with AF.

5 September 2023 in Life
Verified
Journal Article
Open access
PDF file
YLYiheng Lyu
Yiheng Lyu
Mohammed BennamounMohammed Bennamoun
Mohammed Bennamoun
NSNaeha Sharif
Naeha Sharif
Gregory LipGregory Lip
Gregory Lip
GDGirish Dwivedi
Girish Dwivedi
Atrial fibrillation arises mainly due to abnormalities in the cardiac conduction system and is associated with anatomical remodeling of the atria and the pulmonary veins. Cardiovascular imaging techniques, such as echocardiography, computed tomography, and magnetic resonance imaging, are crucial in the management of atrial fibrillation, as they not only provide anatomical context to evaluate structural alterations but also help in determining treatment strategies. However, interpreting these images requires significant human expertise. The potential of artificial intelligence in analyzing these images has been repeatedly suggested due to its ability to automate the process with precision comparable to human experts. This review summarizes the benefits of artificial intelligence in enhancing the clinical care of patients with atrial fibrillation through cardiovascular image analysis. It provides a detailed overview of the two most critical steps in image-guided AF management, namely, segmentation and classification. For segmentation, the state-of-the-art artificial intelligence methodologies and the factors influencing the segmentation performance are discussed. For classification, the applications of artificial intelligence in the diagnosis and prognosis of atrial fibrillation are provided. Finally, this review also scrutinizes the current challenges hindering the clinical applicability of these methods, with the aim of guiding future research toward more effective integration into clinical practice.

8 April 2026 in Journal of Bio-optics
Verified
Journal Article
Open access
PDF file
PGParmida Ghorbanian
Parmida Ghorbanian
HAHadi Afsharan
Hadi Afsharan
FNFarzan Navaeipour
Farzan Navaeipour
NFNajmeh Fayyazifar
Najmeh Fayyazifar
YLYiheng Lyu
Yiheng Lyu
GDGirish Dwivedi
Girish Dwivedi
Recent advances in artificial intelligence (AI) and deep learning (DL) are reshaping ophthalmology, particularly in the domains of image analysis and image synthesis. Optical coherence tomography (OCT) has become indispensable for diagnosing and monitoring retinal diseases, and the application of generative models such as generative adversarial networks (GANs) now enables the creation of realistic synthetic OCT data. In this systematic review, we evaluate the current state of OCT image generation using DL techniques, with emphasis on retinal applications including common pathologies such as age-related macular degeneration, diabetic retinopathy, glaucoma, diabetic retinopathy and other retinal pathologies. We provide an overview of commonly employed architectures, including GAN variants, variational autoencoders, and emerging diffusion models, and highlight how they have been applied for data augmentation, cross-modality translation, noise reduction, and rare pathology synthesis. We discuss validation strategies, performance metrics, and limitations across existing studies, and emphasize the clinical opportunities these technologies present in improving diagnostic accuracy, education, and accessibility of advanced imaging. Finally, we identify gaps in dataset diversity, external validation, and regulatory considerations, and outline future directions to ensure responsible translation of synthetic OCT imaging into clinical practice.

11 December 2025 in arXiv
Verified
Preprint
Open access
PDF file
YLYiheng Lyu
Yiheng Lyu
LXLian Xu
Lian Xu
Mohammed BennamounMohammed Bennamoun
Mohammed Bennamoun
FBFarid Boussaid
Farid Boussaid
CACoen Arrow
Coen Arrow
GDGirish Dwivedi
Girish Dwivedi
Weakly supervised semantic segmentation offers a label-efficient solution to train segmentation models for volumetric medical imaging. However, existing approaches often rely on 2D encoders that neglect the inherent volumetric nature of the data. We propose TranSamba, a hybrid Transformer-Mamba architecture designed to capture 3D context for weakly supervised volumetric medical segmentation. TranSamba augments a standard Vision Transformer backbone with Cross-Plane Mamba blocks, which leverage the linear complexity of state space models for efficient information exchange across neighboring slices. The information exchange enhances the pairwise self-attention within slices computed by the Transformer blocks, directly contributing to the attention maps for object localization. TranSamba achieves effective volumetric modeling with time complexity that scales linearly with the input volume depth and maintains constant memory usage for batch processing. Extensive experiments on three datasets demonstrate that TranSamba establishes new state-of-the-art performance, consistently outperforming existing methods across diverse modalities and pathologies. Our source code and trained models are openly accessible at: https://github.com/YihengLyu/TranSamba.

26 September 2026
Verified
Book Chapter
Closed access
PDF file
YLYiheng Lyu
Yiheng Lyu
LXLian Xu
Lian Xu
CACoen Arrow
Coen Arrow
Mohammed BennamounMohammed Bennamoun
Mohammed Bennamoun
FBFarid Boussaid
Farid Boussaid
GDGirish Dwivedi
Girish Dwivedi