琳宣 郑

Mr. 琳宣 郑

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
19 June 2025 in IEEE Access
Verified
Journal Article
Open access
LSLiyan Sun
Liyan Sun
琳郑琳宣 郑
琳宣 郑
ZXZhiguo Xiao
Zhiguo Xiao
XYXin Yi
Xin Yi
LJLinqing Jiang
Linqing Jiang
Brain tumors are among the deadliest malignant neoplasms worldwide, and early detection is critical for improving treatment outcomes and patient prognosis. Magnetic resonance imaging (MRI) plays a central role in the clinical diagnosis of brain tumors due to its exceptional ability to visualize brain structures and detect tumors. However, traditional MRI detection models for brain tumors often struggle to balance high accuracy with a lightweight design. To address this challenge, this study proposes a novel model—STAR-YOLO—based on the optimization of YOLOv8n. The model refines the backbone network and enhances the C2f module within the neck network. It also integrates SimAM, a parameter-free attention mechanism, and utilizes ShapeIoU as the localization loss function. These innovations enable STAR-YOLO to achieve both high accuracy and a lightweight design. Experimental results on the Br35H public dataset show that STAR-YOLO outperforms existing models, achieving outstanding scores of 0.937 in Precision, 0.852 in Recall, and 0.642 in mAP50-95. Additionally, the model contains only 2.01 million parameters and has a computational complexity of 6.1 GFLOPs, significantly lower than other models. STAR-YOLO accomplishes a lightweight design while guaranteeing high detection accuracy, prominently demonstrating its immense potential in the diagnosis of clinical brain tumors, particularly in circumstances with constrained computing resources.

28 September 2025 in Sensors
Verified
Journal Article
Open access
PDF file
LSLiyan Sun
Liyan Sun
琳郑琳宣 郑
琳宣 郑
XYXin Yi
Xin Yi
Brain tumors are highly malignant diseases that severely threaten the nervous system and patients’ lives. MRI is a core technology for brain tumor diagnosis and treatment due to its high resolution and non-invasiveness. However, existing YOLO-based models face challenges in brain tumor MRI image detection and segmentation, such as insufficient multi-scale feature extraction and high computational resource consumption. This paper proposes an improved lightweight brain tumor detection and instance segmentation model named FALS-YOLO, based on YOLOv8n-Seg and integrating three key modules: FLRDown, AdaSimAM, and LSCSHN. FLRDown enhances multi-scale tumor perception, AdaSimAM suppresses noise and improves feature fusion, and LSCSHN achieves high-precision segmentation with reduced parameters and computational burden. Experiments on the tumor-otak dataset show that FALS-YOLO achieves Precision (B) of 0.892, Recall (B) of 0.858, mAP@0.5 (B) of 0.912 in detection, and Precision (M) of 0.899, Recall (M) of 0.863, mAP@0.5 (M) of 0.917 in segmentation, outperforming YOLOv5n-Seg, YOLOv8n-Seg, YOLOv9s-Seg, YOLOv10n-Seg and YOLOv11n-Seg. Compared with YOLOv8n-Seg, FALS-YOLO reduces parameters by 31.95%, computational amount by 20.00%, and model size by 32.31%. It provides an efficient, accurate and practical solution for the automatic detection and instance segmentation of brain tumors in resource-limited environments.

19 September 2025 in Genes
Verified
Journal Article
Open access
PDF file
LSLiyan Sun
Liyan Sun
XYXin Yi
Xin Yi
SQShen Qu
Shen Qu
琳郑琳宣 郑
琳宣 郑
LJLinqing Jiang
Linqing Jiang
Background/Objectives: Detecting high-order epistatic interactions in genome-wide association studies (GWAS) is essential for understanding complex diseases, yet most existing approaches are limited to pairwise interactions. We propose GPBSO (Gene Pool-Based Brain Storm Optimization for Epistasis Detection), a novel stochastic framework that integrates Brain Storm Optimization with a dynamic gene pool to efficiently explore high-order SNP combinations. Methods: Epistasis is evaluated using the k2 Bayesian network scoring criterion and the G-test, with iterative updates to the gene matrix enhancing search diversity. Results: Comparative experiments on simulated datasets generated from five epistatic models demonstrated that GPBSO consistently outperformed a set of well-established methods—DECMDR, SNPHarvester, AntEpiSeeker, HS-MMGKG, and SEE—in terms of F-measure and statistical power, particularly for third-order interactions. Conclusions: GPBSO provides an effective and scalable approach for detecting high-order epistatic interactions, offering methodological advancements for genetic epidemiology and complex disease analysis.