Author name cluster

Lin Pan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

JBHI Journal 2026 Journal Article

A Self-Supervised Diffusion Model With Edge Prior for Unpaired LDCT Denoising

Zhen Zhang
Huizhen Zhang
Shaohua Zheng
Lin Pan
Mingjing Yang
Liqin Huang
Qiang Wu
Zhiyong Zhang

Low-dose computed tomography (LDCT) reduces health risks from radiation exposure but introduces imaging noise and artifacts. While numerous studies have employed deep learning for LDCT image denoising, the field continues to face significant challenges. Recent advancements have seen diffusion models applied to overcome issues of over-smoothness and unstable training inherent in prior deep learning approaches. However, the diffusion models face challenges in direct practical applications due to the extensive sampling steps, significant inference time required, and the need for hard-to-obtain paired data during training. To address these difficulties, this paper introduces a self-supervised diffusion model with edge prior for unpaired LDCT denoising. This method enables denoising within a lower-dimensional space, reducing computational complexity. Our proposed approach enhances denoised image clarity by applying prior edge constraints to compressed encodings; it employs a noise-conditioned encoding strategy to facilitate self-supervised image training, enabling the method to be applicable to unpaired CT data; and it utilizes compressed LDCT encoding as intermediate sampling results during the inference process, thereby accelerating sampling and reducing the time required for inference, making the method more real-time capable. Extensive validation across multiple datasets demonstrates that our method achieves competitive performance against state-of-the-art approaches in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and perceptual quality (LPIPS), while maintaining a practically acceptable inference time.

Details DOI

EAAI Journal 2025 Journal Article

Dual-phase airway segmentation: Enhancing distal bronchial identification with anatomical prior guidance

Zhen Zhang
Wen Zhang
Liqin Huang
Lin Pan
Shaohua Zheng
Zheng Liu
Weisheng Chen
Penggang Bai

Airway segmentation and reconstruction are critical for preoperative lesion localization and surgical planning in pulmonary interventions. However, this task remains challenging due to the intrinsically complex tree structure of the airway and the imbalance in branch sizes. While current deep learning methods focus on model architecture optimization, they underutilize anatomical priors such as the spatial correlation between pulmonary arteries and bronchi beyond geometric grading level III. To address this limitation, we propose a dual-decoding segmentation network (DDS-Net) integrated with a pulmonary-bronchial extension generative adversarial network (PBE-GAN), which explicitly embeds artery-bronchus adjacency priors to enhance distal bronchial identification. Experimental results demonstrate state-of-the-art performance, achieving a Dice Similarity Coefficient (DSC) of 88. 46%, Branch Detection Rate (BD) of 88. 31%, and Tree Length Detection Rate (TD) of 84. 93%, with significant improvements in detecting peripheral bronchi near pulmonary arteries. This study confirms that incorporating anatomical relationships substantially improves segmentation accuracy, particularly for fine structures. Future work should prioritize clinical validation through multi-center trials and explore integration with real-time surgical navigation systems, while extending similar anatomical synergy principles to other organ-specific segmentation tasks.

Details DOI

IJCAI Conference 2025 Conference Paper

Modular Deep Reinforcement Learning for Multi-Workload Offloading in Edge Networks

Hongchang Ke
Yan Ding
Lin Pan
Yang Chen
Jia Zhao

Dynamic edge networks revolutionize mobile edge computing by enabling real-time applications in intelligent transportation, augmented reality, and industrial Internet of Things (IoT). Efficient workload offloading in dynamic edge networks is crucial for addressing the increasing demands of time-varying workloads while contending with limited computational and communication resources. Existing deep reinforcement learning (DRL)-based offloading decision-making schemes are inadequate for managing scenarios involving multiple workloads and edge servers, particularly when faced with time-varying workload arrivals and fluctuating channel states. To this end, we propose a flexible module weighted fusion DRL framework (DRL-MWF) for scalable and robust multi-workload offloading in edge environments. Unlike traditional monolithic networks, DRL-MWF employs a weighted fusion modular architecture that adapts flexibly to diverse workload distributions. Specifically, DRL-MWF introduces a state representation and normalization strategy to model state and workload characteristics, enabling precise and adaptive decision-making. Furthermore, we design two key mechanisms: a weighted policy correction method to stabilize learning and a prioritized experience replay with weighted importance sampling to accelerate convergence by emphasizing critical transitions. Extensive evaluations on real-world datasets demonstrate that DRL-MWF consistently outperforms state-of-the-art baselines. These results reveal DRL-MWF's potential to transform workload offloading in next-generation edge computing systems, ensuring high performance in dynamic scenarios.

PDF Details DOI

JBHI Journal 2025 Journal Article

ZSG-Net: A Zero-Shot Super-Resolution Guided Network for Ultrasound Image Segmentation and Classification

Xingtao Lin
Xiahai Zhuang
Lin Pan
Mingjing Yang
Liqin Huang
Shun Chen
Lei Li

Automated ultrasound (US) image analysis is hindered by challenges stemming from low resolution, noise, and non-uniform grayscale distribution, which compromise image quality. While many existing studies address these issues using super-resolution (SR) techniques, they often focus exclusively on SR without considering downstream tasks or tailoring to the unique characteristics of US images. In this work, we propose ZSG-Net, a zero-shot super-resolution-guided network, designed to bridge the gap between US image quality enhancement and its benefits in segmentation and classification. First, we introduce a zero-shot self-supervised cycle generative adversarial network (ZSCycle-GAN), tailored to the unique characteristics of US images, to perform SR while preserving critical structural details. Unlike conventional SR methods that focus solely on image enhancement, ZSCycle-GAN is designed to optimize downstream tasks. Second, we adopt a zero-shot self-supervised learning strategy, eliminating the reliance on labeled data and addressing the scarcity of annotated medical imaging datasets. Third, we incorporate a random image degradation (RID) strategy to expand the degradation space for clinical US images, enabling robust learning of diverse quality variations. Extensive experiments on three US image datasets validate the effectiveness of the proposed model. Results demonstrate superior performance in segmentation and classification tasks compared to existing approaches, underscoring the potential of our method to improve US image analysis in clinical settings.

Details DOI

AAAI Conference 2022 Conference Paper

Improved Text Classification via Contrastive Adversarial Training

Lin Pan
Chung-Wei Hang
Avirup Sil
Saloni Potdar

We propose a simple and general method to regularize the fine-tuning of Transformer-based encoders for text classification tasks. Specifically, during fine-tuning we generate adversarial examples by perturbing the word embedding matrix of the model and perform contrastive learning on clean and adversarial examples in order to teach the model to learn noiseinvariant representations. By training on both clean and adversarial examples along with the additional contrastive objective, we observe consistent improvement over standard fine-tuning on clean examples. On several GLUE benchmark tasks, our fine-tuned BERTLarge model outperforms BERTLarge baseline by 1. 7% on average, and our fine-tuned RoBERTaLarge improves over RoBERTaLarge baseline by 1. 3%. We additionally validate our method in different domains using three intent classification datasets, where our fine-tuned RoBERTaLarge outperforms RoBERTaLarge baseline by 1–2% on average. For the challenging low-resource scenario, we train our system using half of the training data (per intent) in each of the three intent classification datasets, and achieve similar performance compared to the baseline trained with full training data.

PDF Details

AAAI Conference 2021 Conference Paper

Multilingual Transfer Learning for QA using Translation as Data Augmentation

Mihaela Bornea
Lin Pan
Sara Rosenthal
Radu Florian
Avirup Sil

Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages. In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. Our first strategy augments the original English training data with machine translation-generated data. This results in a corpus of multilingual silver-labeled QA pairs that is 14 times larger than the original training set. In addition, we propose two novel strategies, language adversarial training and language arbitration framework, which significantly improve the (zero-resource) cross-lingual transfer performance and result in LM embeddings that are less language-variant. Empirically, we show that the proposed models outperform the previous zero-shot baseline on the recently introduced multilingual MLQA and TYDI QA datasets.

PDF Details