DLDonghang Lyu

Donghang Lyu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Donghang Lyu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    CRUNet-MR-Univ: A Foundation Model for Diverse Cardiac MRI Reconstruction

    by Donghang Lyu, Marius Staring, Hildo Lamb, Mariya Doneva

    In recent years, deep learning has attracted increasing attention in the field of Cardiac MRI (CMR) reconstruction due to its superior performance over traditional methods, particularly in handling higher acceleration factors, highlighting its potential for real-world clinical applications. However, current deep learning methods remain limited in generalizability. CMR scans exhibit wide variability in image contrast, sampling patterns, scanner vendors, anatomical structures, and disease types. Most existing models are designed to handle only a single or narrow subset of these variations, leading to performance degradation when faced with distribution shifts. Therefore, it is beneficial to develop a unified model capable of generalizing across diverse CMR scenarios. To this end, we propose CRUNet-MR-Univ, a foundation model that leverages spatio-temporal correlations and prompt-based priors to effectively handle the full diversity of CMR scans. Our approach consistently outperforms baseline methods across a wide range of settings, highlighting its effectiveness and promise.

  • Open Access

    Convolutional recurrent U‐net for cardiac cine MRI reconstruction via effective spatio‐temporal feature exploitation

    by Donghang Lyu, Marius Staring, Matthias J. P. van Osch, Mariya Doneva, Hildo J. Lamb, Nicola Pezzotti

    Background: Cardiac Cine Magnetic Resonance Imaging (MRI) provides dynamic visualization of the heart's structure and function but is hindered by slow acquisition, requiring repeated breath‐holds that challenge sick patients. Accelerated imaging can mitigate these issues but potentially reduce spatial and temporal resolution. Therefore, innovative approaches are essential to ensure effective performance under high acceleration conditions. Deep learning‐based reconstruction methods show promise in enhancing image quality from highly undersampled data, accelerating scans while maintaining diagnostic accuracy. However, they often fail to effectively exploit the spatio‐temporal features inherent to cine MRI, which are essential for accurate reconstruction, thereby leaving room for further improvement. Purpose: We aim to more effectively exploit the spatio‐temporal features inherent in cine MRI sequences by integrating convolutional recurrent operations with a U‐Net architecture, enhancing the reconstruction performance of cine MRI. Methods: We developed a new deep learning model called CRUNet‐MR that enhances the extraction of spatio‐temporal features by combining convolutional recurrent operations with a U‐Net structure. This design ensures continuous extraction of temporal features while fusing fine‐grained spatial details with high‐level semantic information. Furthermore, dilated convolutions are incorporated to expand the spatial receptive field, and appropriate combinations of dilation factors are explored to further enhance overall performance. Results: Training, validation, and testing were performed on the public CMRxRecon2023 dataset, using two views and four acceleration factors ranging from 4 to 24 with the given Auto‐Calibration Signal (ACS) area. The dataset consists of 120 subjects for training, 60 for validation, and 120 for testing. In general, the proposed CRUNet‐MR shows statistically significant differences with benchmark models and consistently outperforms them, particularly showcasing better reconstruction quality in dynamic regions, highlighting its effective extraction of spatio‐temporal features. Ablation studies further validated the design choices of CRUNet‐MR. The model demonstrated strong reconstruction performance, achieving an average SSIM of 0.986 at an acceleration factor of 4 and 0.971 at a factor of 8 across both views. Furthermore, CRUNet‐MR was validated on a small in‐house LUMC dataset, showing its generalization capability and rapid adaptability through fine‐tuning. Conclusions: The proposed CRUNet‐MR model is well‐suited for cine MRI reconstruction, effectively leveraging spatio‐temporal features to reconstruct high‐quality images, especially in dynamic cardiac regions. This capability highlights its potential to support higher acceleration factors, enabling faster and more patient‐friendly cardiac imaging.


  • Open Access

    KP-INR: A Dual-Branch Implicit Neural Representation Model for Cardiac Cine MRI Reconstruction

    by Donghang Lyu, Marius Staring, Mariya Doneva, Hildo J. Lamb, Nicola Pezzotti

    Cardiac Magnetic Resonance (CMR) imaging is a non-invasive method for assessing cardiac structure, function, and blood flow. Cine MRI extends this by capturing heart motion, providing detailed insights into cardiac mechanics. To reduce scan time and breath-hold discomfort, fast acquisition techniques have been utilized at the cost of lowering image quality. Recently, Implicit Neural Representation (INR) methods have shown promise in unsupervised reconstruction by learning coordinate-to-value mappings from undersampled data, enabling high-quality image recovery. However, current existing INR methods primarily focus on using coordinate-based positional embeddings to learn the mapping, while overlooking the feature representations of the target point and its neighboring context. In this work, we propose KP-INR, a dual-branch INR method operating in k-space for cardiac cine MRI reconstruction: one branch processes the positional embedding of k-space coordinates, while the other learns from local multi-scale k-space feature representations at those coordinates. By enabling cross-branch interaction and approximating the target k-space values from both branches, KP-INR can achieve strong performance on challenging Cartesian k-space data. Experiments on the CMRxRecon2024 dataset confirms its improved performance over baseline models and highlights its potential in this field.

  • Open Access

    MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Day

    by Donghang Lyu, Ruochen Gao, Marius Staring

    Medical image segmentation involves partitioning medical images into meaningful regions, with a focus on identifying anatomical structures and lesions. It has broad applications in healthcare, and deep learning methods have enabled significant advancements in automating this process. Recently, the introduction of the Segmentation Anything Model (SAM), the first foundation model for segmentation task, has prompted researchers to adapt it for the medical domain to improve performance across various tasks. However, SAM’s large model size and high GPU requirements hinder its scalability and development in the medical domain. To address these challenges, research has increasingly focused on lightweight adaptations of SAM to reduce its parameter count, enabling training with limited GPU resources while maintaining competitive segmentation performance. In this work, we propose MCP-MedSAM, a powerful and lightweight medical SAM model designed to be trainable on a single A100 GPU with 40GB of memory within one day while delivering superior segmentation performance. Recognizing the significant internal differences between modalities and the need for direct segmentation target information within bounding boxes, we introduce two kinds of prompts: the modality prompt and the content prompt. After passing through the prompt encoder, their embedding representations can further improve the segmentation performance by incorporating more relevant information without adding significant training overhead. Additionally, we adopt an effective modality-based data sampling strategy to address data imbalance between modalities, ensuring more balanced performance across all modalities. Our method was trained and evaluated using a large-scale challenge dataset, compared to top-ranking methods on the challenge leaderboard, MCP-MedSAM achieved superior performance while requiring only one day of training on a single GPU. The code is publicly available at https://github.com/dong845/MCP-MedSAM


  • UPCMR: A Universal Prompt-Guided Model for Random Sampling Cardiac MRI Reconstruction

    by Donghang Lyu, Chinmay Rao, Marius Staring, Matthias J. P. van Osch, Mariya Doneva, Hildo J. Lamb, Nicola Pezzotti


  • Open Access

    Swin-LiteMedSAM: A Lightweight Box-Based Segment Anything Model for Large-Scale Medical Image Datasets

    by Ruochen Gao, Donghang Lyu, Marius Staring

    Medical imaging is essential for the diagnosis and treatment of diseases, with medical image segmentation as a subtask receiving high attention. However, automatic medical image segmentation models are typically task-specific and struggle to handle multiple scenarios, such as different imaging modalities and regions of interest. With the introduction of the Segment Anything Model (SAM), training a universal model for various clinical scenarios has become feasible. Recently, several Medical SAM (MedSAM) methods have been proposed, but these models often rely on heavy image encoders to achieve high performance, which may not be practical for real-world applications due to their high computational demands and slow inference speed. To address this issue, a lightweight version of the MedSAM (LiteMedSAM) can provide a viable solution, achieving high performance while requiring fewer resources and less time. In this work, we introduce Swin-LiteMedSAM, a new variant of LiteMedSAM. This model integrates the tiny Swin Transformer as the image encoder, incorporates multiple types of prompts, including box-based points and scribble generated from a given bounding box, and establishes skip connections between the image encoder and the mask decoder. In the \textit{Segment Anything in Medical Images on Laptop} challenge (CVPR 2024), our approach strikes a good balance between segmentation performance and speed, demonstrating significantly improved overall results across multiple modalities compared to the LiteMedSAM baseline provided by the challenge organizers. Our proposed model achieved a DSC score of \textbf{0.8678} and an NSD score of \textbf{0.8844} on the validation set. On the final test set, it attained a DSC score of \textbf{0.8193} and an NSD score of \textbf{0.8461}, securing fourth place in the challenge.