Longxiang Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Longxiang Feng has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Peizhong Liu
College of Engineering, Huaqiao University, Quanzhou, China
3 shared publications - Jiansong Zhang
Shenzhen University
2 shared publications - Yong Diao
School of Medicine, Huaqiao University, Quanzhou 362021, China
2 shared publications Chunxia Chen
1 shared publication- Dagui Zhang
College of Materials Science and Engineering, Huaqiao University, Xiamen 361021, China
1 shared publication Fang Huang
1 shared publication
Latest Publications
- Open Access
Injectable Thermosensitive Composite Hydrogels for Sustained Nanoparticle Delivery and Enhanced Wound Healing
Wound healing is frequently compromised by excessive oxidative stress, prolonged inflammation, and inadequate tissue regenerative capacity. To address these challenges, a thermosensitive and injectable composite hydrogel based on Pluronic F127 (F127), phosphatidylcholine (PC), and L-lysine (Lys) was developed for the sustained delivery of sinomenine–gallic acid nanoparticles (SGNPs) and the acceleration of wound repair. The hydrogel undergoes a rapid sol–gel transition at physiological temperatures through physical interactions, enabling excellent injectability and in situ gelation. The optimized composite hydrogel exhibited improved mechanical properties, enhanced structural stability, and a uniform porous microarchitecture. The F127−Lys−PCF127−Lys−PC@SGNPs hydrogel showed superior overall stability and hemocompatibility while enabling the sustained release of SGNPs for up to 24 h. Benefiting from the incorporation of SGNPs, the composite hydrogel displayed enhanced antioxidant activity, effectively scavenging free radicals and alleviating cellular oxidative stress. In vitro experiments demonstrated that the hydrogel promoted keratinocyte migration and proliferation. Furthermore, in a murine full-thickness skin wound model, treatment with F127−Lys−PCF127−Lys−PC@SGNPs significantly accelerated wound closure and facilitated re-epithelialization, angiogenesis, and collagen deposition. Collectively, this multifunctional thermosensitive hydrogel provides a promising platform for advanced wound dressings that integrate sustained delivery, antioxidant protection, and tissue regeneration.
Open AccessInjectable Thermosensitive Composite Hydrogels for Sustained Nanoparticle Delivery and Enhanced Wound Healing
Wound healing is frequently compromised by excessive oxidative stress, prolonged inflammation, and inadequate tissue regenerative capacity. To address these challenges, a thermosensitive and injectable composite hydrogel based on Pluronic F127 (F127), phosphatidylcholine (PC), and L-lysine (Lys) was developed for the sustained delivery of sinomenine–gallic acid nanoparticles (SGNPs) and the acceleration of wound repair. The hydrogel undergoes a rapid sol–gel transition at physiological temperatures through physical interactions, enabling excellent injectability and in situ gelation. The optimized composite hydrogel exhibited improved mechanical properties, enhanced structural stability, and a uniform porous microarchitecture. The F127−Lys−PCF127−Lys−PC@SGNPs hydrogel showed superior overall stability and hemocompatibility while enabling the sustained release of SGNPs for up to 24 h. Benefiting from the incorporation of SGNPs, the composite hydrogel displayed enhanced antioxidant activity, effectively scavenging free radicals and alleviating cellular oxidative stress. In vitro experiments demonstrated that the hydrogel promoted keratinocyte migration and proliferation. Furthermore, in a murine full-thickness skin wound model, treatment with F127−Lys−PCF127−Lys−PC@SGNPs significantly accelerated wound closure and facilitated re-epithelialization, angiogenesis, and collagen deposition. Collectively, this multifunctional thermosensitive hydrogel provides a promising platform for advanced wound dressings that integrate sustained delivery, antioxidant protection, and tissue regeneration.
- Open Access
Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
This magnetic resonance imaging multimodal fusion study aims to automate the staging of endometrial cancer using deep learning and to compare the diagnostic performance of deep learning with that of radiologists in the staging of endometrial cancer. This study retrospectively investigated 122 patients with pathologically confirmed early EC from January 1, 2025 to December 31, 2021. Of these patients, 68 were in the International Federation of Gynecology and Obstetrics (FIGO) stage IA, and 54 were in FIGO stage IB. Based on the Swin transformer model and its proprietary SW-MSA (shift window multiple self-coherence) module, magnetic resonance imaging (MRI) images in each of the three planes (sagittal, coronal, and transverse) are cropped, enhanced, and classified, and fusion experiments in the three planes are performed simultaneously. Selecting one plane for the experiment, the accuracy of IA and IB classification was 0.988 in the sagittal, 0.96 in the coronal, and 0.94 in the transverse position, and classification accuracy after the fusion of three planes reached 1. Finally, the automatic classification method based on the Swin transformer has an accuracy of 1, a recall of 1, and a specificity of 1 for early EC classification. In this study, the multimodal fusion approach accurately classified early EC. It was comparable to what a radiologist would perform and simpler and more precise than previous methods that required segmenting followed by staging.
Open AccessMultimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
This magnetic resonance imaging multimodal fusion study aims to automate the staging of endometrial cancer using deep learning and to compare the diagnostic performance of deep learning with that of radiologists in the staging of endometrial cancer. This study retrospectively investigated 122 patients with pathologically confirmed early EC from January 1, 2025 to December 31, 2021. Of these patients, 68 were in the International Federation of Gynecology and Obstetrics (FIGO) stage IA, and 54 were in FIGO stage IB. Based on the Swin transformer model and its proprietary SW-MSA (shift window multiple self-coherence) module, magnetic resonance imaging (MRI) images in each of the three planes (sagittal, coronal, and transverse) are cropped, enhanced, and classified, and fusion experiments in the three planes are performed simultaneously. Selecting one plane for the experiment, the accuracy of IA and IB classification was 0.988 in the sagittal, 0.96 in the coronal, and 0.94 in the transverse position, and classification accuracy after the fusion of three planes reached 1. Finally, the automatic classification method based on the Swin transformer has an accuracy of 1, a recall of 1, and a specificity of 1 for early EC classification. In this study, the multimodal fusion approach accurately classified early EC. It was comparable to what a radiologist would perform and simpler and more precise than previous methods that required segmenting followed by staging.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (12) , 9119-9130
Benchmarking Supervised and Self-Supervised Learning Methods in a Large Ultrasound Muti-Task Images Dataset
Deep learning in ultrasound(US) imaging aims to construct foundational models that accurately reflect the modality's unique characteristics. Nevertheless, the limited datasets and narrow task types have restricted this field in recent years. To address these challenges, we introduce US-MTD120K, a multi-task ultrasound dataset with 120,354 real-world two-dimensional images. This dataset covers three standard plane recognition and two diagnostic tasks in ultrasound imaging, providing a rich basis for model training and evaluation. We detail the data collection, distribution, and labelling processes, ensuring a thorough understanding of the dataset's structure. Furthermore, we conduct extensive benchmark tests on 27 state-of-the-art methods from both supervised and self-supervised learning(SSL) perspectives. In the realm of supervised learning, we analyze the sensitivity of two main feature computation methods to ultrasound images at the representational level, highlighting that models which judiciously constrain global feature computation could potentially serve as a viable analytical approach for US image analysis. In the context of self-supervised learning, we delved into the modelling process of self-supervised learning models for medical images and proposed an improvement strategy, named MoCo-US, a solution that addresses the excessive reliance on pretext task design from the input side. It achieves competitive performance with minimal pretext task design and enhances other SSL methods simply. The dataset and the code will be available at https://github.com/JsongZhang/CDOA-for-UMTD .
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (12) , 9119-9130
Benchmarking Supervised and Self-Supervised Learning Methods in a Large Ultrasound Muti-Task Images Dataset
Deep learning in ultrasound(US) imaging aims to construct foundational models that accurately reflect the modality's unique characteristics. Nevertheless, the limited datasets and narrow task types have restricted this field in recent years. To address these challenges, we introduce US-MTD120K, a multi-task ultrasound dataset with 120,354 real-world two-dimensional images. This dataset covers three standard plane recognition and two diagnostic tasks in ultrasound imaging, providing a rich basis for model training and evaluation. We detail the data collection, distribution, and labelling processes, ensuring a thorough understanding of the dataset's structure. Furthermore, we conduct extensive benchmark tests on 27 state-of-the-art methods from both supervised and self-supervised learning(SSL) perspectives. In the realm of supervised learning, we analyze the sensitivity of two main feature computation methods to ultrasound images at the representational level, highlighting that models which judiciously constrain global feature computation could potentially serve as a viable analytical approach for US image analysis. In the context of self-supervised learning, we delved into the modelling process of self-supervised learning models for medical images and proposed an improvement strategy, named MoCo-US, a solution that addresses the excessive reliance on pretext task design from the input side. It achieves competitive performance with minimal pretext task design and enhances other SSL methods simply. The dataset and the code will be available at https://github.com/JsongZhang/CDOA-for-UMTD .