Article
Oncology
Ibrahim Ozdemir, Huseyin Murat Bulut, Suecattin Ilker Kocamis
Summary: This study suggests that oral isotretinoin therapy may lead to significant thickening of the retinal nerve fiber layer in patients with small optic disc area.
PHOTODIAGNOSIS AND PHOTODYNAMIC THERAPY
(2022)
Review
Computer Science, Interdisciplinary Applications
Rita Marques, Danilo Andrade De Jesus, Joao Barbosa-Breda, Jan Van Eijgen, Ingeborg Stalmans, Theo van Walsum, Stefan Klein, Pedro G. Vaz, Luisa Sanchez Brea
Summary: This review summarizes the latest technology applications of automatic segmentation of the optic nerve head (ONH) in optical coherence tomography (OCT), pointing out the lack of consensus on segmented regions, extracted parameters, and validation methods, highlighting the importance of establishing standardized methods. Only with a concrete set of guidelines, these automatic segmentation algorithms can enter clinical practice.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Computer Science, Information Systems
Cong Xu, Changqing Yu, Shanwen Zhang
Summary: This study proposes a lightweight multi-scale extended U-Net model (LWMSDU-Net) for crop disease leaf image segmentation. The model utilizes encoding and decoding sub-networks for feature fusion and achieves a segmentation accuracy of 92.17% in experiments.
Review
Agriculture, Multidisciplinary
Shanwen Zhang, Chuanlei Zhang
Summary: Early detection and recognition of plant disease is crucial for controlling plant disease. However, segmenting diseased leaf images is challenging due to their complexity. This study proposes an improved U-Net (MU-Net) for plant diseased leaf image segmentation by introducing a residual block (Resblock) and a residual path (Respath). Experimental results demonstrate that this method enhances the accuracy and efficiency of plant diseased leaf image segmentation.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Ophthalmology
Vishal Raval, Rajeev Reddy, Swathi Kaliki, Taraprasad Das, Arun D. Singh
Summary: The study aimed to identify the diagnostic features of optic nerve head melanocytoma (ONH-MCT) on spectral domain optical coherence tomography (SD OCT) and OCT angiography (OCT-A). The results showed that ONH-MCT tumors occupied 3 tissue spaces and had distinct features on SD OCT and OCT-A compared to nevus and melanoma, which may aid in differentiation.
INDIAN JOURNAL OF OPHTHALMOLOGY
(2021)
Article
Engineering, Biomedical
Jingdong Yang, Jintu Zhu, Hailing Wang, Xin Yang
Summary: This study proposed a Dilated MultiResUNet network to improve end-to-end image segmentation performance based on U-Net, Res2Net, MultiResUNet, Dilated Residual Networks, and Squeeze-and-Excitation Networks. Evaluation on four biomedical datasets showed superior accuracy and generalization performance with significantly fewer parameters compared to the U-Net model.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Biochemistry & Molecular Biology
Casey J. Keuthan, Julie A. Schaub, Meihan Wei, Weixiang Fang, Sarah Quillen, Elizabeth Kimball, Thomas V. Johnson, Hongkai Ji, Donald J. Zack, Harry A. Quigley
Summary: The level of intraocular pressure (IOP) is a major risk factor for glaucomatous optic neuropathy. This study found that the unmyelinated optic nerve region is differentially susceptible to IOP-induced damage compared to the myelinated region. Gene expression patterns in the unmyelinated optic nerve showed significant differences compared to the myelinated optic nerve and retina. Changes in gene expression induced by optic nerve injury were more extensive in the myelinated region than the unmyelinated region.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Medicine, General & Internal
Do-Young Park, Hoon Noh, Changwon Kee, Jong-Chul Han
Summary: This study aimed to investigate the topographic relationships among the deep optic nerve head (ONH) parameters representing myopic axial elongation or changes in the lamina cribrosa (LC) in patients with primary open-angle glaucoma (POAG). The study found that the AL-related parameters showed a strong spatial correspondence with glaucomatous ONH damage, whereas the LC-related parameter had less correlation.
JOURNAL OF CLINICAL MEDICINE
(2022)
Article
Clinical Neurology
Michael J. A. Girard, Satish Panda, Tin Aung Tun, Elisabeth A. Wibroe, Raymond P. Najjar, Tin Aung, Alexandre H. Thiery, Steffen Hamann, Clare Fraser, Dan Milea
Summary: This study developed a deep learning algorithm to automatically identify major structures of the optic nerve head (ONH) in 3D optical coherence tomography (OCT) scans and differentiate between optic disc drusen (ODD), papilledema, and healthy ONHs. The algorithm was able to accurately isolate tissues and regions associated with ODD and achieved high classification performance.
Article
Environmental Sciences
Wenling Yu, Bo Liu, Hua Liu, Guohua Gou
Summary: In this paper, a novel method for building extraction based on U-Net is proposed. By incorporating a recurrent residual deformable convolution unit (RDCU) module and augmented multi-head self-attention (AMSA), the method enhances the ability to learn building shape details and improves feature expression and positions. Experimental results on three datasets demonstrate the effectiveness of the proposed method.
Article
Biology
Shuhang Wang, Vivek Kumar Singh, Eugene Cheah, Xiaohong Wang, Qian Li, Shinn-Huey Chou, Constance D. Lehman, Viksit Kumar, Anthony E. Samir
Summary: Researchers proposed two improvements for U-Net: replacing consecutive convolutions with stacked dilated operation, and using an asymmetric structure with fewer channels in the decoder path. Experiments confirmed that these improvements can enhance the performance of U-Net and its variants while using fewer parameters.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Review
Ophthalmology
Anthony Arnold
Summary: The vascular supply of the optic nerve head is complex and remains unclear. Over the past 50 years, conflicting theories have evolved due to different research techniques used to study the contributions of various blood vessels.
BRITISH JOURNAL OF OPHTHALMOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Gang Sha, Junsheng Wu, Bin Yu
Summary: This paper introduces a method to objectively segment spinal lesions by combining U-net, dense blocks, and dilated convolution, providing assistance in diagnosing spinal diseases and serving as a clinical reference. The proposed DDU-net shows good segmentation performance of spinal lesions, laying a solid foundation for both doctors and patients.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Gang Sha, Junsheng Wu, Bin Yu
Summary: In this paper, a scheme for spinal fracture lesions segmentation based on U-net was proposed, which introduces an attention module and dilated convolution to achieve more accurate lesions segmentation. The attention module focuses on specific regions to improve the model's recognition of lesions, while dilated convolution increases the receptive field for more lesion feature information. Experimental results show that the proposed network outperforms U-net in lesions segmentation performance.
NEURAL PROCESSING LETTERS
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jinke Wang, Xiangyang Zhang, Peiqing Lv, Haiying Wang, Yuanzhi Cheng
Summary: This paper proposes a new network framework for automatic and accurate liver segmentation. By leveraging EfficientNetB4, attention gate, and residual learning techniques, the proposed method achieves impressive results in both qualitative and quantitative assessments.
JOURNAL OF DIGITAL IMAGING
(2022)
Article
Ophthalmology
Xiaofei Wang, Tin A. Tun, Monisha Esther Nongpiur, Hla M. Htoon, Yih Chung Tham, Nicholas G. Strouthidis, Tin Aung, Ching-Yu Cheng, Michael J. A. Girard
Summary: This study compared the shape of the anterior surface of the peripapillary sclera (PPS) between glaucoma and healthy subjects and found that the V-shaped configuration of the PPS was more pronounced in glaucoma eyes than in healthy eyes. This may have an impact on the biomechanical environment of the optic nerve head.
BRITISH JOURNAL OF OPHTHALMOLOGY
(2022)
Article
Ophthalmology
Satish K. Panda, Haris Cheong, Tin A. Tun, Sripad K. Devella, Vijayalakshmi Senthil, Ramaswami Krishnadas, Martin L. Buist, Shamira Perera, Ching-Yu Cheng, Tin Aung, Alexandre H. Thiery, Michael J. A. Girard
Summary: This study develops a novel deep-learning approach for describing the structural phenotype of the glaucomatous optic nerve head (ONH) and serving as a robust glaucoma diagnosis tool. By analyzing the latent parameters, it reveals the changes in ONH morphology during the transition from a non-glaucoma to a glaucoma condition.
AMERICAN JOURNAL OF OPHTHALMOLOGY
(2022)
Article
Biochemistry & Molecular Biology
Nina Marchi, Laura Winkelbach, Ilektra Schulz, Maxime Brami, Zuzana Hofmanova, Jens Bloecher, Carlos S. Reyna-Blanco, Yoan Diekmann, Alexandre Thiery, Adamandia Kapopoulou, Vivian Link, Valerie Piuz, Susanne Kreutzer, Sylwia M. Figarska, Elissavet Ganiatsou, Albert Pukaj, Travis J. Struck, Ryan N. Gutenkunst, Necmi Karul, Fokke Gerritsen, Joachim Pechtl, Joris Peters, Andrea Zeeb-Lanz, Eva Lenneis, Maria Teschler-Nicola, Sevasti Triantaphyllou, Sofija Stefanovic, Christina Papageorgopoulou, Daniel Wegmann, Joachim Burger, Laurent Excoffier
Summary: Demogenomic modeling of ancient genomes sheds light on the genetic origins and differentiation process of early farming populations in Europe and Southwest Asia, as well as the genetic drift they experienced during their migration.
Article
Statistics & Probability
Matthew M. Graham, Alexandre H. Thiery, Alexandros Beskos
Summary: This paper proposes a method for inferring the posterior distribution of nonlinear diffusion processes observed at discrete times, using ideas from statistical physics and computational chemistry. The method is highly automated and applicable in a wide range of settings, outperforming other approaches in the literature.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
(2022)
Article
Energy & Fuels
Hadrien Verbois, Yves-Marie Saint-Drenan, Alexandre Thiery, Philippe Blanc
Summary: The share of solar power in the global and local energy mixes has significantly increased in the past decade, leading to a rise in interest for solar power forecasting. Numerical Weather Prediction (NWP) models and post-processing algorithms are the most popular methods for day-ahead forecasts. However, comparing results across different studies is challenging due to variations in datasets, metrics, and cross-validation methods. This study proposes a rigorous benchmark of solar NWP post-processing models using an open dataset spanning 6 years and 7 locations. The results demonstrate the systematic benefits of using large predictor sets with proper regularization, as well as the superior performance of more complex algorithms such as neural networks and gradient boosting in terms of mean square error. Support vector regression, a more parsimonious algorithm, performs better in terms of mean absolute error. The study highlights the importance of considering systematic ranking when evaluating forecasting models and emphasizes that no single model is superior in all situations.
Article
Ophthalmology
S. A. T. I. S. H. K. PANDA, H. A. R. I. S. CHEONG, T. I. N. A. TUN, T. H. A. N. A. D. E. T. CHUANGSUWANICH, A. I. S. T. E. KADZIAUSKIENE, V. I. J. A. Y. A. L. A. K. S. H. M. I. SENTHIL, R. A. M. A. S. W. A. M. I. KRISHNADAS, M. A. R. T. I. N. L. BUIST, S. H. A. M. I. R. A. PERERA, CHING-YU CHENG, T. I. N. AUNG, A. L. E. X. A. N. D. R. E. H. THIERY, M. I. C. H. A. E. L. J. A. GIRARD
Summary: This study demonstrates the potential of using the 3D structural configuration of the central retinal vessel trunk and its branches as a diagnostic marker for glaucoma, showing higher accuracy in diagnosis compared to traditional RNFL thickness measurements. The segmentation network and diagnostic networks achieved good performance in differentiating glaucoma from non-glaucoma subjects.
AMERICAN JOURNAL OF OPHTHALMOLOGY
(2022)
Article
Ophthalmology
Thanadet Chuangsuwanich, Tin A. Tun, Fabian A. Braeu, Xiaofei Wang, Zhi Yun Chin, Satish Kumar Panda, Martin Buist, Nicholas Strouthidis, Shamira Perera, Monisha Nongpiur, Tin Aung, Michael J. A. Girard
Summary: The purpose of this study was to investigate the associations between optic nerve head strains under intraocular pressure elevation and retinal sensitivity in glaucoma patients. A clinic-based cross-sectional study was conducted on 229 patients with primary open-angle glaucoma, divided into high-tension glaucoma (HTG) and normal-tension glaucoma (NTG) groups. The results showed significant negative associations between optic nerve head strains and retinal sensitivity in patients with HTG, while no significant associations were observed in patients with NTG except in certain regions of the lamina cribrosa.
Article
Clinical Neurology
Michael J. A. Girard, Satish Panda, Tin Aung Tun, Elisabeth A. Wibroe, Raymond P. Najjar, Tin Aung, Alexandre H. Thiery, Steffen Hamann, Clare Fraser, Dan Milea
Summary: This study developed a deep learning algorithm to automatically identify major structures of the optic nerve head (ONH) in 3D optical coherence tomography (OCT) scans and differentiate between optic disc drusen (ODD), papilledema, and healthy ONHs. The algorithm was able to accurately isolate tissues and regions associated with ODD and achieved high classification performance.
Article
Ophthalmology
Fabian A. Braeu, Alexandre H. Thiery, Tin A. Tun, Aiste Kadziauskiene, George Barbastathis, Tin Aung, Michael J. A. Girard
Summary: This study compares the performance of two recent geometric deep learning techniques in diagnosing glaucoma from a single optical coherence tomographic scan of the optic nerve head, and identifies the critical 3D structural features of the optic nerve head for glaucoma diagnosis. Both deep learning approaches accurately detected glaucoma from the 3D optic nerve head point clouds, with critical points located within the neuroretinal rim in the inferior and superior quadrants. This approach has strong potential for clinical applications in diagnosing and prognosing ophthalmic disorders.
AMERICAN JOURNAL OF OPHTHALMOLOGY
(2023)
Article
Ophthalmology
Fabian A. Braeu, Thanadet Chuangsuwanich, Tin A. Tun, Shamira Perera, Rahat Husain, Alexandre H. Thiery, Tin Aung, George Barbastathis, Michael J. A. Girard
Summary: Using artificial intelligence techniques, the study aims to assess the robustness of the optic nerve head (ONH) by analyzing biomechanical knowledge through optical coherence tomography (OCT). Three AI algorithms were compared to predict ONH robustness and the DGCNN algorithm outperformed the others. The study suggests that ONH robustness can be assessed from a single OCT scan, providing potential insights into identifying fast visual field loss progressors.
BRITISH JOURNAL OF OPHTHALMOLOGY
(2023)
Article
Biochemical Research Methods
Christopher Hendra, Ploy N. Pratanwanich, Yuk Kei Wan, W. S. Sho Goh, Alexandre Thiery, Jonathan Goke
Summary: This study introduces a neural-network-based method m6Anet, which leverages multiple instance learning framework to handle missing read-level modification labels in site-level training data, demonstrating superior performance in detecting m6A modifications.
Article
Computer Science, Hardware & Architecture
Jean-Martial Mari, Alban Gabillon
Summary: The emergence of low-cost, low-power long-distance LoRa radio devices enables the development of a new generation of networking paradigms in the Internet of Things. This study proposes an Epidemic Delay Tolerant Network messaging protocol that allows multi-hops between LoRa relay-nodes through a controlled-flooding approach. The protocol has been implemented on low-cost LoRa-chip-equipped microcontrollers, serving as a network transport layer.
COMPUTER STANDARDS & INTERFACES
(2023)
Article
Health Care Sciences & Services
Yiying Cai, Nuraini Nazeha, Shamira Perera, Alexandre H. Thiery, Michael J. A. Girard, Chen E. E. Lee, Weiwei Hong, Nicholas Graves
Summary: This study aimed to design and implement an assessment tool for informing funding decisions for competing health innovations in a tertiary hospital. The assessment tool consists of three components: value to the institution, novelty, and potential for adoption and scaling. The results demonstrated the usefulness of the assessment tool in the decision-making process.
INTERNATIONAL JOURNAL OF TECHNOLOGY ASSESSMENT IN HEALTH CARE
(2023)
Meeting Abstract
Critical Care Medicine
Alexander Tarr, Shannon N. Mohabir, Alejandro Dominguez, Michael J. Girard, Marquand Patton
Meeting Abstract
Ophthalmology
Michael J. A. Girard, Satish Kumar Panda, Tin Aung Tun, Raymond Najjar, Tin Aung, Alexandre Thiery, Steffen Hamann, Clare Louise Fraser, Dan Milea
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2022)
