Endless possibilities in academia
Endless possibilities in academia
School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P. R. China.
Address correspondence to: Rongguo Yan, Department of Biomedical Engineering, School of Health Science and Engineering, University of Shanghai for Science and Technology, No. 516 Jungong Road, Yangpu, Shanghai 200093, P. R. China. E-mail: yanrongguo@usst.edu.cn.
DOI: https://doi.org/10.61189/017119gmeubf
Received February 21, 2025; Accepted April 16, 2025; Published December 31, 2025
Highlights
● This paper presents a new method for brain injury detection, which uses eddy current damping technology. This method is more convenient and faster than the traditional detection method.
● This paper simulates the method in COMSOL software and then verifies it through experiments. The feasibility of the method is proved through the combination of simulation and experiments.
Research Article |Published on: 31 December 2025
[Progress in Medical Devices] 2025; 3 (4): 202-210
He Ren*, Yina Zhang*, Yutong Xie*, Anqi Wu, Xianglun Kong, Chenxiao Bai, Miao Yu, Yimeng Wang, Ping Li
Faculty of Medical Instrumentation, Shanghai University of Medicine and Health Sciences, Shanghai 201318, China.
*The authors contribute equally.
Address correspondence to: Ping Li, Faculty of Medical Instrumentation, Shanghai University of Medicine and Health Sciences, No. 279, Zhouzhu Highway, Pudong New Area, Shanghai 201318, China. Tel: +86-13764055848. E-mail: lip@sumhs.edu.cn.
DOI: https://doi.org/10.61189/517419bnpxap
Received July 17, 2025; Accepted September 29, 2025; Published December 31, 2025
Highlights
● Based on 8,110 OAI X-ray images, 18 radiomic features were processed and selected, with SMOTE combined with category weight balancing employed to address data imbalance.
● Among eight machine learning models, the SVM achieved the best performance.
● SHAP and LIME analyses enhanced model interpretability by identifying key radiomic features influencing predictions.
Research Article |Published on: 31 December 2025
[Progress in Medical Devices] 2025; 3 (4): 211-222.
Siqi Wang*, Danhong Li*, Yina Zhang* , Yu Wang, Linrong Yuan, Miao Yu, Jianghui Li, Yimeng Wang, Ping Li
Faculty of Medical Instrumentation, Shanghai University of Medicine and Health Sciences, Shanghai 201318, China.
*These authors are co-first authors.
Address correspondence to: Ping Li, Faculty of Medical Instrumentation, Shanghai University of Medicine and Health Sciences, 279 Zhouzhu Highway, Pudong New Area, Shanghai 201318, China. Tel: +86-13764055848. E-mail: lip@sumhs.edu.cn.
Declaration of ethics: The study was approved by the Ethics Review Committees of the Medical University of Vienna and the University of Queensland.
Declaration of patient consent: The dataset underwent automated screening using neural networks, followed by multiple manual reviews. All EXIF metadata were removed to eliminate any potentially identifiable information. Therefore, the data are considered anonymized to the best of our knowledge.
DOI: https://doi.org/10.61189/446813bjkhvg
Received July 26, 2025; Accepted November 4, 2025; Published December 31, 2025
Highlights
● For the first time, the advantages of two deep learning architectures-SegNet and U-Net-were integrated by averaging their prediction outputs. This ensemble approach overcame the limitations of single models and substantially improved segmentation accuracy.
● The proposed Ensemble Model outperformed both SegNet and U-Net across all major evaluation metrics, including the Intersection over Union (IoU, 93.73%), Dice coefficient (84.85%), precision (93.93%), and loss (0.63), confirming the effectiveness of multi-method fusion.
● Considering the complex morphology and indistinct lesion boundaries characteristic of skin diseases, a standardized preprocessing and data augmentation pipeline was developed to enhance the model' s robustness in handling diverse lesion patterns.
Research Article |Published on: 31 December 2025
[Progress in Medical Devices] 2025; 3 (4): 223-233
Wanwen Yang, Lin Mao, Yadan Yang, Chengli Song
Shanghai Institute for Minimally Invasive Therapy, School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
Address correspondence to: Lin Mao, Shanghai Institute for Minimally Invasive Therapy, School of Health Science and Engineering, University of Shanghai for Science and Technology, No. 516 Jungong Road, Yangpu District, Shanghai 200093, China. Tel: +86-21-55572159. E-mail: linmao@usst.edu.cn.
DOI: https://doi.org/10.61189/925623shkhmp
Received March 5, 2025; Accepted April 10, 2025; Published December 31, 2025
Highlights
● Systematic classification of anastomosis techniques, including manual sutures, robotic assistance, biomedical adhesives, energy welding, and stapling devices.
● Critical analysis of biodegradable materials in addressing foreign body reactions and balancing degradation and mechanical performance.
● Future directions emphasizing intelligent material design, multimodal technology fusion, and specialized device development.
Review Article |Published on: 31 December 2025
[Progress in Medical Devices] 2025; 3 (4): 234-243
Yuxiang Luo, Yong Wang, Jiuzhou Zhao, Xiangzhou Meng, Yanan Hou, Yao Zheng, Yu Zhou
School of Health Sciences and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
Address correspondence to: Yu Zhou, School of Health Sciences and Engineering, University of Shanghai for Science and Technology, No. 516 Jungong Road, Shanghai 200093, China. Tel: +86-18021042556. E-mail: zhouyu@usst.edu.cn.
DOI: https://doi.org/10.61189/880658qzgyhf
Received April 21, 2025; Accepted August 8, 2025; Published December 31, 2025
Highlights
● Comprehensive Technology Review-It systematically compares three major techniques for reducing thermal damage in electrosurgery.
● Balanced Evaluation Framework-Each method is evaluated across multiple dimensions, including effectiveness, applicability, complexity, and cost.
● Forward-Looking Insight-It discusses future trends such as AI integration and the development of advanced materials for smarter surgical systems.
Review Article |Published on: 31 December 2025
[Progress in Medical Devices] 2025; 3 (4): 244-254
Wensong Yan1 , Shiju Yan1 , Yunhua Xu2
1School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China. 2Department of Oncology, Shanghai Chest Hospital, Shanghai 200030, China.
Address correspondence to: Shiju Yan, School of Health Sciences and Engineering, University of Shanghai for Science and Technology, No.580 Jungong Road, Shanghai 200093, China. Tel: +86-18217617984. E-mail: yanshiju@usst.edu.cn.
DOI: https://doi.org/10.61189/828047gamhgw
Received January 13, 2025; Accepted April 15, 2025; Published December 31, 2025
Highlights
● This study introduces a novel method to predict the efficacy of PD1/PD-L1 inhibitors in non-small cell lung can-cer by extracting radiomic features from pre-treatment and post-treatment CT images.
● Integrating biological features and radiomic features enhances predictive performance.
● The newly proposed segmentation model achieved a dice coefficient of 90.09%, enabling accurate lesion seg-mentation.
Research Article |Published on: 31 December 2025
[Progress in Medical Devices] 2025; 3 (4): 255-264
Submit
