Article
Biochemical Research Methods
Jiaxuan Li, Peiyao Jin, Jianfeng Zhu, Haidong Zou, Xun Xu, Min Tang, Minwen Zhou, Yu Gan, Jiangnan He, Yuye Ling, Yikai Su
Summary: The research team developed a novel two-stage framework assisted by a graph convolutional network for labeling the nine retinal layers and optic disc simultaneously, with promising results in accuracy metrics compared to other techniques.
BIOMEDICAL OPTICS EXPRESS
(2021)
Article
Computer Science, Artificial Intelligence
Jason Kugelman, David Alonso-Caneiro, Scott A. Read, Stephen J. Vincent, Fred K. Chen, Michael J. Collins
Summary: This study proposes using GANs to augment data for OCT chorio-retinal boundary segmentation, showing that models trained on synthetic data can perform comparably to those trained on real data. Data augmentation capabilities are demonstrated with improved classification performance realized on sparse datasets, highlighting the potential use of GANs in future work with chorio-retinal OCT images.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yuhui Ma, Huaying Hao, Jianyang Xie, Huazhu Fu, Jiong Zhang, Jianlong Yang, Zhen Wang, Jiang Liu, Yalin Zheng, Yitian Zhao
Summary: In this study, a new dataset ROSE for retinal vessel OCTA images was constructed, and a novel vessel segmentation network OCTA-Net was proposed with superior performance. Experimental results demonstrated potential advantages in studying neurodegenerative diseases through fractal dimension analysis.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Interdisciplinary Applications
Sandra Morales, Adrian Colomer, Jose M. Mossi, Rocio del Amor, David Woldbye, Kristian Klemp, Michael Larsen, Valery Naranjo
Summary: This study presented two different approaches to detect the most significant retinal layers in a rat OCT image, utilizing local intensity profiles and deep learning technology. Both approaches achieved satisfactory results on the rat OCT database, with the deep learning method outperforming the other. Additionally, the study demonstrated the superiority of the first approach over commercial image segmentation software.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Engineering, Biomedical
Wei Tang, Yanqing Ye, Xinjian Chen, Fei Shi, Dehui Xiang, Zhongyue Chen, Weifang Zhu
Summary: In this paper, a novel two-stage multi-class retinal fluid joint segmentation framework based on cascaded convolutional neural networks is proposed. It can accurately segment retinal fluid in optical coherence tomography images, which is of great importance for the diagnosis and treatment of related fundus diseases.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Review
Chemistry, Analytical
Xing Wei, Ruifang Sui
Summary: Optical coherence tomography (OCT) is an emerging imaging technique used for diagnosing ophthalmic diseases and analyzing retinal structure changes. Researchers have focused on applying machine learning algorithms to automate retinal cyst/fluid segmentation, providing valuable tools for improved interpretation and treatment decisions.
Article
Ophthalmology
Bart Liefers, Paul Taylor, Abdulrahman Alsaedi, Clare Bailey, Konstantinos Balaskas, Narendra Dhingra, Catherine A. Egan, Filipa Gomes Rodrigues, Cristina Gonzalez Gonzalo, Tjebo F. C. Heeren, Andrew Lotery, Philipp L. Muller, Abraham Olvera-Barrios, Bobby Paul, Roy Schwartz, Darren S. Thomas, Alasdair N. Warwick, Adnan Tufail, Clara Sanchez
Summary: The study aimed to develop and validate a deep learning model for segmentation of 13 features associated with age-related macular degeneration. The results showed that the model's performance matches that of experienced observers for most features, and even exceeds human performance for some features.
AMERICAN JOURNAL OF OPHTHALMOLOGY
(2021)
Article
Multidisciplinary Sciences
Olivier Morelle, Maximilian W. M. Wintergerst, Robert P. Finger, Thomas Schultz
Summary: Drusen are important biomarkers for age-related macular degeneration (AMD). Accurate segmentation of drusen based on optical coherence tomography (OCT) is crucial for disease detection, assessment, and treatment. This study proposes a novel deep learning architecture that predicts the position of retinal layers in OCT and achieves state-of-the-art results in retinal layer segmentation.
SCIENTIFIC REPORTS
(2023)
Article
Immunology
Christina Noll, Michael Hiltensperger, Lilian Aly, Rebecca Wicklein, Ali Maisam Afzali, Christian Mardin, Christiane Gasperi, Achim Berthele, Bernhard Hemmer, Thomas Korn, Benjamin Knier
Summary: This study found that rarefication of the retinal vasculature during RRMS is associated with higher frequencies of activated B cells and higher levels of pro-inflammatory cytokines in the cerebrospinal fluid. Furthermore, vessel loss in the retina is linked to future disability worsening.
FRONTIERS IN IMMUNOLOGY
(2022)
Article
Multidisciplinary Sciences
Jason Kugelman, Joseph Allman, Scott A. Read, Stephen J. Vincent, Janelle Tong, Michael Kalloniatis, Fred K. Chen, Michael J. Collins, David Alonso-Caneiro
Summary: In this study, eight U-Net architecture variants were compared across four different OCT datasets, and minimal differences were found between most of the tested architectures. Adding an extra convolutional layer per pooling block slightly improved segmentation performance for all architectures. The study demonstrates that the vanilla U-Net is sufficient for OCT retinal layer segmentation and that state-of-the-art methods and other architectural changes are potentially unnecessary for this particular task.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Interdisciplinary Applications
S. J. Pawan, Rahul Sankar, Anubhav Jain, Mahir Jain, D. V. Darshan, B. N. Anoop, Abhishek R. Kothari, M. Venkatesan, Jeny Rajan
Summary: This paper introduces the central serous chorioretinopathy (CSCR) and the importance of qualitative assessment and automated segmentation in the study of this disease, proposing an enhanced model called DRIP-Caps for SRF segmentation, which outperforms the benchmark architecture with reduced trainable parameters.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2021)
Article
Engineering, Electrical & Electronic
Vineeta Das, Samarendra Dandapat, Prabin Kumar Bora
Summary: The proposed Deep Multi-scale Fusion Convolutional Neural Network (DMF-CNN) effectively encodes multi-scaled disease characteristics by using multiple CNNs with different receptive fields and fusing them, resulting in reliable classification for retinal diseases. The method achieves state-of-the-art performance on publicly available OCT databases and offers an impressive overall accuracy for diagnostic purposes.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoming Liu, Shaocheng Wang, Ying Zhang, Dong Liu, Wei Hu
Summary: An improved U-Net segmentation method with attention mechanism and dense skip connections is proposed in this paper, which makes the segmentation results more precise and avoids excessive calculation. The method includes a joint loss function to address the problem of merging multiple fluid regions into one.
Article
Medicine, General & Internal
Syed Muhammad Ali Imran, Muhammad Waqas Saleem, Muhammad Talha Hameed, Abida Hussain, Rizwan Ali Naqvi, Seung Won Lee
Summary: Ophthalmic diseases are increasing globally, and manual methods for analysis are unreliable and time-consuming. This study proposes an AI-based method called FPM-Net for accurate retinal vessel segmentation, which outperforms existing methods in computational efficiency and segmentation performance.
FRONTIERS IN MEDICINE
(2023)
Article
Multidisciplinary Sciences
Varsha Alex, Tahmineh Motevasseli, William R. Freeman, Jefy A. Jayamon, Dirk-Uwe G. Bartsch, Shyamanga Borooah
Summary: The study compared the performance of two retinal layer segmentation software in normal and diseased eyes, and found that the cross-platform software performed significantly better in some layers compared to the proprietary software, with moderate to strong correlation in volume calculations for most retinal layers between the two softwares.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yunfeng Wu, Pinnan Chen, Xin Luo, Hui Huang, Lifang Liao, Yuchen Yao, Meihong Wu, Rangaraj M. Rangayyan
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2016)
Article
Biochemical Research Methods
Jiancang Zeng, Dapeng Li, Yunfeng Wu, Quan Zou, Xiangrong Liu
CURRENT BIOINFORMATICS
(2016)
Article
Biotechnology & Applied Microbiology
Meihong Wu, Lifang Liao, Xin Luo, Xiaoquan Ye, Yuchen Yao, Pinnan Chen, Lei Shi, Hui Huang, Yunfeng Wu
BIOMED RESEARCH INTERNATIONAL
(2016)
Article
Biochemical Research Methods
Li Song, Dapeng Li, Xiangxiang Zeng, Yunfeng Wu, Li Guo, Quan Zou
BMC BIOINFORMATICS
(2014)
Article
Biology
Quan Zou, Yaozong Mao, Lingling Hu, Yunfeng Wu, Zhiliang Ji
COMPUTERS IN BIOLOGY AND MEDICINE
(2014)
Article
Engineering, Electrical & Electronic
Bangquan Zhang, Weikai Xu, Yunfeng Wu, Lin Wang
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2019)
Editorial Material
Mathematical & Computational Biology
Yunfeng Wu, Sridhar Krishnan, Behnaz Ghoraani
Summary: Biomedical signal processing and data analysis are crucial in advanced medical expert systems. Signal processing tools improve signal quality, while data analysis techniques reduce redundancy and extract important features related to pathological conditions. Recent computational methods have greatly enhanced the efficiency and accuracy of diagnosis and decision-making in medical fields.
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2022)
Editorial Material
Chemistry, Analytical
Yunfeng Wu, Behnaz Ghoraani
Article
Chemistry, Analytical
Guidong Bao, Mengchen Lin, Xiaoqian Sang, Yangcan Hou, Yixuan Liu, Yunfeng Wu
Summary: This article proposes a novel semi-supervised competitive learning (SSCL) algorithm for vocal pattern classifications in Parkinson's disease (PD). The algorithm uses acoustic parameters for feature extraction and computes linear correlations between the parameters. Through principal component analysis (PCA), the redundant dimensions of the parameters in each family are eliminated. The Mann-Whitney-Wilcoxon hypothesis test evaluates the differences in PCA-projected features between healthy subjects and PD patients. Based on selected eigenvalues and the results of the hypothesis test, eight dominant PCA-projected features are chosen for competitive prototype seed selection, K-means optimization, and nearest neighbor classifications. Experimental results show that the proposed SSCL algorithm outperforms conventional KNN or SVM classifiers in terms of accuracy, recall, specificity, precision, F-score, Matthews correlation coefficient, area under the receiver operating characteristic curve, and Kappa coefficient.
Proceedings Paper
Engineering, Electrical & Electronic
Yunfeng Wu, Yixuan Liu, Yangcan Hou, Xi Chen, Tingxuan Gao
Summary: Detection of phonation impairment in patients with Parkinson's disease is important for assessing pathological progress, and a novel semi-supervised learning method was proposed to analyze voice patterns in PD. Experimental results showed that the method achieved high recall, specificity, and overall accuracy, outperforming previous studies in the literature.
2021 15TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION AND COMMUNICATION TECHNOLOGY (ISMICT)
(2021)
Article
Engineering, Biomedical
Yunfeng Wu, Yuchen Yao, Yugui Xiao, Xiaoquan Ye, Pinnan Chen, Lifang Liao, Meihong Wu, Rangaraj M. Rangayyan
BIOMEDICAL ENGINEERING-APPLICATIONS BASIS COMMUNICATIONS
(2017)
Article
Mathematical & Computational Biology
Yunfeng Wu, Pinnan Chen, Yuchen Yao, Xiaoquan Ye, Yugui Xiao, Lifang Liao, Meihong Wu, Jian Chen
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2017)
Article
Engineering, Biomedical
Yunfeng Wu, Pinnan Chen, Xin Luo, Meihong Wu, Lifang Liao, Shanshan Yang, Rangaraj M. Rangayyan
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2017)
Proceedings Paper
Engineering, Biomedical
Yunfeng Wu, Xin Luo, Pinnan Chen, Lifang Liao, Shanshan Yang, Rangaraj M. Rangayyan
2015 IEEE INTERNATIONAL SYMPOSIUM ON MEDICAL MEASUREMENTS AND APPLICATIONS (MEMEA) PROCEEDINGS
(2015)