Mengya Xu

Mengya Xu

Auto-generated profile, based on publicly available information

Mengya Xu

The Chinese University of Hong Kong

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications

3 October 2024
Verified
Book Chapter
Closed access
PDF file
YHYiming Huang
Yiming Huang
BCBeilei Cui
Beilei Cui
LBLong Bai
Long Bai
ZGZiqi Guo
Ziqi Guo
MXMengya Xu
Mengya Xu
Hongliang RenHongliang Ren
Hongliang Ren

4 January 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Open access
SSShijian Su
Shijian Su
SYSishen Yuan
Sishen Yuan
MXMengya Xu
Mengya Xu
HGHuxin Gao
Huxin Gao
XYXiaoxiao Yang
Xiaoxiao Yang
Hongliang RenHongliang Ren
Hongliang Ren
Traditional magnetic tracking approaches based on mathematical models and optimization algorithms are computationally intensive, depend on initial guesses, and do not guarantee convergence to a global optimum. Although fully-supervised data-driven deep learning can solve the above issues, the demand for a comprehensive dataset hampers its applicability in magnetic tracking. Thus, we propose an annular magnet pose estimation network (called AMagPoseNet) based on dual-domain few-shot learning from a prior mathematical model, which consists of two sub-networks: PoseNet and CaliNet. PoseNet learns to estimate the magnet pose from the prior mathematical model, and CaliNet is designed to narrow the gap between the mathematical model domain (MMD) and the real-world domain (RWD). Experimental results reveal that AMagPoseNet outperforms the optimization-based method regarding localization accuracy (1.87 $\pm$ 1.14 mm, 1.89 $\pm 0.81^{\circ }$ ), robustness (non-dependence on initial guesses), and computational latency (2.08 $\pm$ 0.02 ms). In addition, the six degrees of freedom (6-DoF) pose of the magnet could be estimated when discriminative magnetic field features are provided. With the assistance of the mathematical model, AMagPoseNet requires only a few real-world samples and has excellent performance, showing great potential for practical biomedical and industrial applications.

24 July 2023 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Open access
AWAn Wang
An Wang
MIMobarakol Islam
Mobarakol Islam
MXMengya Xu
Mengya Xu
Hongliang RenHongliang Ren
Hongliang Ren
Accurate and robust medical image segmentation is fundamental and crucial for enhancing the autonomy of computer-aided diagnosis and intervention systems. Medical data collection normally involves different scanners, protocols, and populations, making domain adaptation (DA) a highly demanding research field to alleviate model degradation in the deployment site. To preserve the model performance across multiple testing domains, this work proposes the Curriculum-based Augmented Fourier Domain Adaptation (Curri-AFDA) for robust medical image segmentation. In particular, our curriculum learning strategy is based on the causal relationship of a model under different levels of data shift in the deployment phase, where the higher the shift is, the harder to recognize the variance. Considering this, we progressively introduce more amplitude information from the target domain to the source domain in the frequency space during the curriculum-style training to smoothly schedule the semantic knowledge transfer in an easier-to-harder manner. Besides, we incorporate the training-time chained augmentation mixing to help expand the data distributions while preserving the domain-invariant semantics, which is beneficial for the acquired model to be more robust and generalize better to unseen domains. Extensive experiments on two segmentation tasks of Retina and Nuclei collected from multiple sites and scanners suggest that our proposed method yields superior adaptation and generalization performance. Meanwhile, our approach proves to be more robust under various corruption types and increasing severity levels. In addition, we show our method is also beneficial in the domain-adaptive classification task with skin lesion datasets. The code is available at https://github.com/lofrienger/Curri-AFDA. Note to Practitioners —Medical image segmentation is key to improving computer-assisted diagnosis and intervention autonomy. However, due to domain gaps between different medical sites, deep learning-based segmentation models frequently encounter performance degradation when deployed in a novel domain. Moreover, model robustness is also highly expected to mitigate the effects of data corruption. Considering all these demanding yet practical needs to automate medical applications and benefit healthcare, we propose the Curriculum-based Fourier Domain Adaptation (Curri-AFDA) for medical image segmentation. Extensive experiments on two segmentation tasks with cross-domain datasets show the consistent superiority of our method regarding adaptation and generalization on multiple testing domains and robustness against synthetic corrupted data. Besides, our approach is independent of image modalities because its efficacy does not rely on modality-specific characteristics. In addition, we demonstrate the benefit of our method for image classification besides segmentation in the ablation study. Therefore, our method can potentially be applied in many medical applications and yield improved performance. Future works may be extended by exploring the integration of curriculum learning regime with Fourier domain amplitude fusion in the testing time rather than in the training time like this work and most other existing domain adaptation works.

7 February 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
LLLing Li
Ling Li
XLXiaojian Li
Xiaojian Li
Shuai DingShuai Ding
Shuai Ding
ZFZhao Fang
Zhao Fang
MXMengya Xu
Mengya Xu
SYShanlin Yang
Shanlin Yang
Surgical interaction recognition (SIR) plays a crucial role in navigation decision support for minimally invasive surgery (MIS) or robot-assisted MIS. Currently, the research in SIR is at a coarse-grained level and barely considers the surgical interaction dependencies unrelated to endoscopic images. This work proposes a fine-grained SIR method named SIRNet aiming at predicting surgical interaction triplets. In the proposed SIRNet, a multi-head self-attention mechanism learns the relations among surgical interaction triplets without defining them before the training process, while a multi-head cross-attention mechanism learns the relationships between the endoscopic images and each triplet. The bipartite matching loss, which considers the permutation and combination of instruments, verbs, and targets, is adopted to make appropriate learning and prediction for each component in the surgical interaction triplet. Moreover, a weight attention module is designed to weigh the importance of each predicted surgical interaction triplet and each component in triplet when predicting final valid surgical interaction triplets. The experimental results show the proposed method improves the performance of fine-grained SIR. In addition, experiments also present the effectiveness of each module. The code is available at https://github.com/cynerelee/SIRNet https://github.com/cynerelee/SIRNet .