Haibei Song

Dr. Haibei Song


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
19 September 2022 in Digital Health
Verified
Journal Article
Open access
LFLi Feng
Li Feng
ZHZong Hai Huang
Zong Hai Huang
YZYan Mei Zhong
Yan Mei Zhong
WXWenKe Xiao
WenKe Xiao
CWChuan Biao Wen
Chuan Biao Wen
JGJinhong Guo
Jinhong Guo
Objective: To explore the technical research and application characteristics of deep learning in tongue-facial diagnosis. Methods: Through summarizing the merits and demerits of current image processing techniques used in the traditional medical tongue and face diagnosis, the research status of deep learning in tongue image preprocessing, segmentation, and classification was analyzed and reviewed, and the algorithm was compared and verified with the real tongue and face image. Images of the face and tongue used for diagnosis in conventional medicine were systematically reviewed, from acquisition and pre-processing to segmentation, classification, algorithm comparison, result from analysis, and application. Results: Deep learning improved the speed and accuracy of tongue and face diagnostic image data processing. Among them, the average intersection ratio of U-net and Seg-net models exceeded 0.98, and the segmentation speed ranged from 54 to 58 ms. Conclusion: There is no unified standard for lingual-facial diagnosis objectification in terms of image acquisition conditions and image processing methods, thus further research is indispensable. It is feasible to use the images acquired by mobile in the field of medical image analysis by reducing the influence of environmental and other factors on the quality of lingual-facial diagnosis images and improving the efficiency of image processing.

23 June 2023 in Medicine
Verified
Journal Article
Open access
YMYiyi Ma
Yiyi Ma
YZYanmei Mmsc Zhong
Yanmei Mmsc Zhong
QSQin Be Su
Qin Be Su
LXLuman Be Xu
Luman Be Xu
HSHaibei Song
Haibei Song
CWChuan-biao Wen
Chuan-biao Wen
When the similarity of medicinal materials is high and easily confused, the traditional subjective judgment has an impact on the identification results. Use high-dimensional features to identify medicinal materials to ensure the quality of Chinese herbal concoction products and proprietary Chinese medicines. Objective: To study the identification algorithm of traditional Chinese medicinals (TCM) microscopic images based on convolutional neural network (CNN) to improve the objectivity and accuracy of microscopic image identification of TCM powders. Methods: Microscopic image datasets of 4 TCM powders sclereids of Rhizoma Coptidis, Cortex Magnoliae Officinalis, Cortex Phellodendri Chinensis, and Cortex Cinnamomi were constructed, and 400 collected images, as the model training and testing objects, were identified and classified by AlexNet model, VGGNet-16, VGGNet-19, and GoogLeNet model. Results: The average recognition accuracy in the tested microscopic image of AlexNet model, VGGNet-16, VGGNet-19, and the GoogLeNet model is 93.50%, 95.75%, 95.75%, and 97.50% correspondingly. Conclusion: The GoogLeNet model has a higher classification accuracy and is the best model to achieve real-time. Applying the CNN to the identification of microscopic images of TCM powders makes the operation of TCM identification simpler and the measurement more accurate while improving repeatability.

3 November 2022 in Digital Health
Verified
Journal Article
Open access
HSHaibei Song
Haibei Song
ZHZonghai Huang
Zonghai Huang
LFLi Feng
Li Feng
YZYanmei Zhong
Yanmei Zhong
CWChuan-biao Wen
Chuan-biao Wen
JGJinhong Guo
Jinhong Guo
Objective: Due to the complexity of face images, tongue segmentation is susceptible to interference from uneven tongue texture, lips and face, resulting in traditional methods failing to segment the tongue accurately. To address this problem, RAFF-Net, an automatic tongue region segmentation network based on residual attention network and multiscale feature fusion, was proposed. It aims to improve tongue segmentation accuracy and achieve end-to-end automated segmentation. Methods: Based on the UNet backbone network, different numbers of ResBlocks combined with the Squeeze-and-Excitation (SE) block was used as an encoder to extract image layered features. The decoder structure of UNet was simplified and the number of parameters of the network model was reduced. Meanwhile, the multiscale feature fusion module was designed to optimize the network parameters by combining a custom loss function instead of the common cross-entropy loss function to further improve the detection accuracy. Results: The RAFF-Net network structure achieved Mean Intersection over Union (MIoU) and F1-score of 97.85% and 97.73%, respectively, which improved 0.56% and 0.46%, respectively, compared with the original UNet; ablation experiments demonstrated that the improved algorithm could contribute to the enhancement of tongue segmentation effect. Conclusion: This study combined the residual attention network with multiscale feature fusion to effectively improve the segmentation accuracy of the tongue region, and optimized the input and output of the UNet network using different numbers of ResBlocks, SE block, multiscale feature fusion and weighted loss function, increased the stability of the network and improved the overall effect of the network.

14 April 2023 in Journal of Visualized Experiments
Verified
Journal Article
Closed access
PDF file
LFLi Feng
Li Feng
WXWenke Xiao
Wenke Xiao
CWChuanbiao Wen
Chuanbiao Wen
QDQiaoling Deng
Qiaoling Deng
JGJinhong Guo
Jinhong Guo
HSHaibei Song
Haibei Song
Tongue diagnosis is an essential technique of traditional Chinese medicine (TCM) diagnosis, and the need for objectifying tongue images through image processing technology is growing. The present study provides an overview of the progress made in tongue objectification over the past decade and compares segmentation models. Various deep learning models are constructed to verify and compare algorithms using real tongue image sets. The strengths and weaknesses of each model are analyzed. The findings indicate that the U-Net algorithm outperforms other models regarding precision accuracy (PA), recall, and mean intersection over union (MIoU) metrics. However, despite the significant progress in tongue image acquisition and processing, a uniform standard for objectifying tongue diagnosis has yet to be established. To facilitate the widespread application of tongue images captured using mobile devices in tongue diagnosis objectification, further research could address the challenges posed by tongue images captured in complex environments.

17 February 2023 in Journal of Visualized Experiments
Verified
Journal Article
Closed access
JWJing Wang
Jing Wang
PDPeipei Du
Peipei Du
LZLinda Ld Zhong
Linda Ld Zhong
YRYaxuan Ren
Yaxuan Ren
LFLi Feng
Li Feng
HSHaibei Song
Haibei Song
Meta Analysis Effectiveness Safety Shugan Jieyu Capsules For. JoVE publishes peer-reviewed scientific video protocols to accelerate biological, medical, chemical and physical research. Watch our scientific video articles. JoVE is the world-leading producer and provider of science videos with the mission to improve scientific research, scientific journals, and education. Millions of scientists, educators and students at thousands of universities, colleges, hospitals and biopharmaceutical companies worldwide use JoVE for their research, teaching and learning.

15 October 2026 in Bioengineering
Verified
Journal Article
Open access
PDF file
YGYulin Gou
Yulin Gou
ZZZiyang Zhang
Ziyang Zhang
HSHaibei Song
Haibei Song
Alan WangAlan Wang
Alan Wang
Intelligent tongue diagnosis demands high-precision segmentation on resource-constrained mobile devices. All deep learning models outperform conventional approaches, improving mean intersection over union (mIoU) by approximately 9% and accelerating inference by more than two orders of magnitude. Among the evaluated models, UNet++ achieves the highest test mIoU (0.9543) and Dice (0.9764), with paired bootstrap analysis confirming statistically significant advantages over BiSeNet, PP-LiteSeg, and HRNet. BiSeNet achieves the fastest inference speed (310.03 FPS) and the highest mPA (0.9766), making it the most efficient model for real-time deployment. HRNet and PP-LiteSeg provide a favorable accuracy–efficiency balance, suitable for mobile-based tongue diagnosis. Deployment of PP-LiteSeg on three Android devices achieved inference latency of 233–262 ms and throughput of 3.2–3.4 FPS, demonstrating the feasibility of lightweight models on commodity mobile hardware. These findings establish an evidence-based framework for model selection in mobile tongue diagnosis, supporting AI deployment on portable devices for clinical assistance and remote monitoring.