检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zhang, Wen Paudel, Bibek Wang, Liang Chen, Jiaoyan Zhu, Hai Zhang, Wei Bernstein, Abraham Chen, Huajun College of Computer Science Zhejiang University Stanford University University of Zurich Department of Computer Science University of Oxford Alibaba Group China Alibaba Group AZFT Joint Lab for Knowledge Engine Department of Informatics University of Zurich Switzerland Zhejiang University AZFT Joint Lab for Knowledge Engine China

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their own advantages and difficulties. Rule-based reasoning is accurate and explainable but rule learning with searching over the graph always suffers from efficiency due to huge search space. Embedding-based reasoning is more scalable and efficient as the reasoning is conducted via computation between embeddings, but it has difficulty learning good representations for sparse entities because a good embedding relies heavily on data richness. Based on this observation, in this paper we explore how embedding and rule learning can be combined together and complement each other's difficulties with their advantages. We propose a novel framework IterE iteratively learning embeddings and rules, in which rules are learned from embeddings with proper pruning strategy and embeddings are learned from existing triples and new triples inferred by rules. Evaluations on embedding qualities of IterE show that rules help improve the quality of sparse entity embeddings and their link prediction results. We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently. Experiments showthat iteratively learning embeddings and rules benefit each other during learning and prediction. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Metrics Reloaded: Recommendations for image analysis validation

arXiv

引用

arXiv 2022年

作者： Maier-Hein, Lena Reinke, Annika Godau, Patrick Tizabi, Minu D. Buettner, Florian Christodoulou, Evangelia Glocker, Ben Isensee, Fabian Kleesiek, Jens Kozubek, Michal Reyes, Mauricio Riegler, Michael A. Wiesenfarth, Manuel Emre Kavur, A. Sudre, Carole H. Baumgartner, Michael Eisenmann, Matthias Heckmann-Nötzel, Doreen Rädsch, Tim Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Benis, Arriel Blaschko, Matthew B. Jorge Cardoso, M. Cheplygina, Veronika Cimini, Beth A. Collins, Gary S. Farahani, Keyvan Ferrer, Luciana Galdran, Adrian Ginneken, Bram Van Haase, Robert Hashimoto, Daniel A. Hoffman, Michael M. Huisman, Merel Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kenngott, Hannes Kofler, Florian Kopp-Schneider, Annette Kreshuk, Anna Kurc, Tahsin Landman, Bennett A. Litjens, Geert Madani, Amin Maier-Hein, Klaus Martel, Anne L. Mattson, Peter Meijering, Erik Menze, Bjoern Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Petersen, Jens Rajpoot, Nasir Rieke, Nicola Saez-Rodriguez, Julio Sánchez, Clara I. Shetty, Shravya Smeden, Maarten Van Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. Calster, Ben Van Varoquaux, Gaël Jäger, Paul F. Heidelberg Division of Intelligent Medical Systems and HI Helmholtz Imaging Germany Faculty of Mathematics and Computer Science and Medical Faculty Heidelberg University Heidelberg Germany NCT Heidelberg a partnership between DKFZ University Medical Center Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Intelligent Medical Systems Germany partner site Frankfurt/Mainz a partnership between DKFZ and UCT Frankfurt-Marburg Germany Heidelberg Goethe University Frankfurt Germany Department of Medicine Goethe University Frankfurt Germany Department of Informatics Frankfurt Cancer Insititute Germany Department of Computing Imperial College London London United Kingdom Heidelberg Division of Medical Image Computing and HI Applied Computer Vision Lab Germany Institute for AI in Medicine University Medicine Essen Essen Germany Centre for Biomedical Image Analysis Faculty of Informatics Masaryk University Brno Czech Republic ARTORG Center for Biomedical Engineering Research University of Bern Bern Switzerland Department of Radiation Oncology University Hospital Bern University of Bern Bern Switzerland Simula Metropolitan Center for Digital Engineering Oslo Norway UiT The Arctic University of Norway Romsø Norway Heidelberg Division of Biostatistics Germany Heidelberg Division of Intelligent Medical Systems Division of Medical Image Computing HI Applied Computer Vision Lab Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London London United Kingdom Heidelberg Division of Medical Image Computing Germany Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montréal

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen performance metrics often do not reflect the domain interest, thus failing to adequately measure scientific progress and hindering translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. It was developed by a large international consortium in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint – a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output. Based on the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as a classification task at image, object or pixel level, namely image-level classification, object detection, semantic segmentation, and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases. © 2022, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Explainable AI: Definition and attributes of a good explanation for health AI

arXiv

引用

arXiv 2024年

作者： Kyrimi, Evangelia McLachlan, Scott Wohlgemut, Jared M. Perkins, Zane B. Lagnado, David A. Marsh, William Gimson, Alexander Shafti, Ali Ercole, Ari Banerjee, Amitava Glocker, Ben Schafer, Burkhard Gatsonis, Constantine Grosan, Crina Sent, Danielle Berman, David S. Glass, David O'Regan, Declan P. Letsios, Dimitrios Morrissey, Dylan Pisirir, Erhan Leofante, Francesco Soyel, Hamit Williamson, Jon Grieman, Keri Dube, Kudakwashe Mardsen, Max Nagendran, Myura Tai, Nigel Kostopoulou, Olga Jones, Owain Curzon, Paul Stoner, Rebecca S. Tandle, Sankalp Joshi, Shalmali Mossadegh, Somayyeh Buijsman, Stefan Miller, Tim Madai, Vince Istvan School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Nursing Midwifery and Palliative Care King's College London London United Kingdom Centre for Trauma Sciences Blizard Institute Queen Mary University of London London United Kingdom Royal London Hospital Barts Health NHS Trust London United Kingdom Department of Experiment Psychology University College London London United Kingdom Cambridge Liver Unit Addenbrooke's Hospital Cambridge University Hospitals Hills Road Box 210 Cambridge United Kingdom University of Cambridge United Kingdom Cambridge Consultants Ltd. United Kingdom Division of Anaesthesia Cambridge Centre for AI in Medicine University of Cambridge Cambridge United Kingdom Magdelene College University of Cambridge United Kingdom Institute of Health Informatics University College London London United Kingdom Department of Computing Imperial College London London United Kingdom SCRIPT Centre for IT and IP Law School of Law University of Edinburgh United Kingdom Center for Statistical Sciences School of Public Health Brown University Providence United States Research Group Artificial Intelligence HU University of Applied Sciences Utrecht Netherlands Jheronimus Academy of Data Science Tilburg University Eindhoven University of Technology s-Hertogenbosch Netherlands Centre for Theoretical Physics Queen Mary University of London London United Kingdom School of Computing Ulster University Belfast United Kingdom MRC Laboratory of Medical Sciences Imperial College London London United Kingdom Department of Informatics King's College London United Kingdom Physiotherapy Department Barts Health NHS Trust London United Kingdom Sport and Exercise Medicine Queen Mary University of London London United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Department of Computing Imperial College London United Kingdom Departmen

Proposals of artificial intelligence (AI) solutions based on increasingly complex and accurate predictive models are becoming ubiquitous across many disciplines. As the complexity of these models grows, transparency and users' understanding often diminish. This suggests that accurate prediction alone is insufficient for making an AI-based solution truly useful. In the development of healthcare systems, this introduces new issues related to accountability and safety. Understanding how and why an AI system makes a recommendation may require complex explanations of its inner workings and reasoning processes. Although research on explainable AI (XAI) has significantly increased in recent years and there is high demand for XAI in medicine, defining what constitutes a good explanation remains ad hoc, and providing adequate explanations continues to be challenging. To fully realize the potential of AI, it is critical to address two fundamental questions about explanations for safety-critical AI applications, such as health-AI: (1) What is an explanation in health-AI? and (2) What are the attributes of a good explanation in health-AI? In this study, we examined published literature and gathered expert opinions through a two-round Delphi study. The research outputs include (1) a definition of what constitutes an explanation in health-AI and (2) a comprehensive list of attributes that characterize a good explanation in health-AI. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Author Correction: AutoTransOP: translating omics signatures without orthologue requirements using deep learning

引用

NPJ systems biology and applications 2024年第1期10卷 148页

作者： Nikolaos Meimetis Krista M Pullen Daniel Y Zhu Avlant Nilsson Trong Nghia Hoang Sara Magliacane Douglas A Lauffenburger Department of Biological Engineering Massachusetts Institute of Technology Cambridge MA 02139 USA. Department of Biology and Biological Engineering Chalmers University of Technology Gothenburg SE 41296 Sweden. School of Electrical Engineering and Computer Science Washington State University Pullman WA 99164-236 USA. Institute of Informatics University of Amsterdam Amsterdam The Netherlands. MIT-IBM Watson AI Lab Cambridge MA 02139 USA. Department of Biological Engineering Massachusetts Institute of Technology Cambridge MA 02139 USA. lauffen@mit.edu.

来源：评论

学校读者我要写书评

暂无评论

Filter sketch for network pruning

arXiv

引用

arXiv 2020年

作者： Lin, Mingbao Cao, Liujuan Li, Shaojie Ye, Qixiang Tian, Yonghong Liu, Jianzhuang Tian, Qi Ji, Rongrong The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China The Fujian Key Laboratory of Sensing and Computing for Smart City Computer Science Department School of Informatics Xiamen University Xiamen361005 China Institute of Artificial Intelligence Xiamen University Xiamen361005 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing101408 China The School of Electronics Engineering and Computer Science Peking University Beijing100871 China The Noah's Ark Lab Huawei Technologies Co. Ltd. Shenzhen518129 China Cloud BU Huawei Technologies Co. Ltd. Shenzhen518129 China

We propose a novel network pruning approach by information preserving of pre-trained network weights (filters). Network pruning with the information preserving is formulated as a matrix sketch problem, which is efficiently solved by the off-the-shelf Frequent Direction method. Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure. FilterSketch requires neither training from scratch nor data-driven iterative optimization, leading to a several-orders-of-magnitude reduction of time cost in the optimization of pruning. Experiments on CIFAR-10 show that FilterSketch reduces 63.3% of FLOPs and prunes 59.9% of network parameters with negligible accuracy cost for ResNet-110. On ILSVRC-2012, it reduces 45.5% of FLOPs and removes 43.0% of parameters with only 0.69% accuracy drop for ResNet-50. Our code and pruned models can be found at https://***/lmbxmu/FilterSketch. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Potential Indicator for Continuous Emotion Arousal by Dynamic Neural Synchrony

arXiv

引用

arXiv 2025年

作者： Pan, Guandong Wu, Zhaobang Yang, Yaqian Wang, Xin Liu, Longzhao Zheng, Zhiming Tang, Shaoting School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Key laboratory of Mathematics Informatics and Behavioral Semantics Beihang University Beijing100191 China Institute of Medical Artificial Intelligence Binzhou Medical University Yantai264003 China Zhongguancun Laboratory Beijing100094 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing100191 China PengCheng Laboratory Shenzhen518055 China State Key Lab of Software Development Environment Beihang University Beijing100191 China

The need for automatic and high-quality emotion annotation is paramount in applications such as continuous emotion recognition and video highlight detection, yet achieving this through manual human annotations is challenging. Inspired by inter-subject correlation (ISC) utilized in neuroscience, this study introduces a novel Electroencephalography (EEG) based ISC methodology that leverages a single-electrode and feature-based dynamic approach. Our contributions are three folds: Firstly, we reidentify two potent emotion features suitable for classifying emotions—first-order difference (FD) an differential entropy (DE). Secondly, through the use of overall correlation analysis, we demonstrate the heterogeneous synchronized performance of electrodes. This performance aligns with neural emotion patterns established in prior studies, thus validating the effectiveness of our approach. Thirdly, by employing a sliding window correlation technique, we showcase the significant consistency of dynamic ISCs across various features or key electrodes in each analyzed film clip. Our findings indicate the method’s reliability in capturing consistent, dynamic shared neural synchrony among individuals, triggered by evocative film stimuli. This underscores the potential of our approach to serve as an indicator of continuous human emotion arousal. The implications of this research are significant for advancements in affective computing and the broader neuroscience field, suggesting a streamlined and effective tool for emotion analysis in real-world applications. © 2025, CC BY-NC-SA.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Dispensed transformer network for unsupervised domain adaptation

arXiv

引用

arXiv 2021年

作者： Li, Yunxiang Li, Jingxiong Dan, Ruilong Wang, Shuai Jin, Kai Zeng, Guodong Wang, Jun Pan, Xiangji Zhang, Qianni Zhou, Huiyu Jin, Qun Wang, Li Wang, Yaqi College of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Artificial Intelligence and Biomedical Image Analysis Lab Westlake University Hangzhou China School of Mechanical Electrical and Information Engineering Shandong University Weihai China Department of Ophthalmology Hospital of Zhejiang University Hangzhou China sitem Center for Translational Medicine and Biomedical Entrepreneurship University of Bern Bern Switzerland School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Computing and Mathematical Sciences University of Leicester United Kingdom Department of Human Informatics and Cognitive Sciences Faculty of Human Sciences Waseda University Tokyo Japan Department of Radiology and Biomedical Research Imaging Center University of North Carolina at Chapel Hill Chapel Hill United States College of Media Engineering Communication University of Zhejiang Hangzhou China

Accurate segmentation is a crucial step in medical image analysis and applying supervised machine learning to segment the organs or lesions has been substantiated effective. However, it is costly to perform data annotation that provides ground truth labels for training the supervised algorithms, and the high variance of data that comes from different domains tends to severely degrade system performance over cross-site or cross-modality datasets. To mitigate this problem, a novel unsupervised domain adaptation (UDA) method named dispensed Transformer network (DTNet) is introduced in this paper. Our novel DTNet contains three modules. First, a dispensed residual transformer block is designed, which realizes global attention by dispensed interleaving operation and deals with the excessive computational cost and GPU memory usage of the Transformer. Second, a multi-scale consistency regularization is proposed to alleviate the loss of details in the low-resolution output for better feature alignment. Finally, a feature ranking discriminator is introduced to automatically assign different weights to domain-gap features to lessen the feature distribution distance, reducing the performance shift of two domains. The proposed method is evaluated on large fluorescein angiography (FA) retinal nonperfusion (RNP) cross-site dataset with 676 images and a wide used cross-modality dataset from the MM-WHS challenge. Extensive results demonstrate that our proposed network achieves the best performance in comparison with several state-of-the-art techniques. © 2021, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fetal Brain Tissue Annotation and Segmentation Challenge Results

arXiv

引用

arXiv 2022年

作者： Payette, Kelly Li, Hongwei De Dumast, Priscille Licandro, Roxane Ji, Hui Siddiquee, Md Mahfuzur Rahman Xu, Daguang Myronenko, Andriy Liu, Hao Pei, Yuchen Wang, Lisheng Peng, Ying Xie, Juanying Zhang, Huiquan Dong, Guiming Fu, Hao Wang, Guotai Rieu, ZunHyan Kim, Donghyeon Kim, Hyun Gi Karimi, Davood Gholipour, Ali Torres, Helena R. Oliveira, Bruno Vilaça, João L. Lin, Yang Avisdris, Netanell Ben-Zvi, Ori Bashat, Dafna Ben Fidon, Lucas Aertsen, Michael Vercauteren, Tom Sobotka, Daniel Langs, Georg Alenyà, Mireia Villanueva, Maria Inmaculada Camara, Oscar Fadida, Bella Specktor Joskowicz, Leo Weibin, Liao Yi, Lv Xuesong, Li Mazher, Moona Qayyum, Abdul Puig, Domenec Kebiri, Hamza Zhang, Zelin Xu, Xinyi Wu, Dan Liao, KuanLun Wu, YiXuan Chen, JinTai Xu, Yunzhi Zhao, Li Vasung, Lana Menze, Bjoern Cuadra, Meritxell Bach Jakab, Andras Center for MR Research University Children's Hospital Zurich University of Zurich Zurich Switzerland Neuroscience Center Zurich University of Zurich Zurich Switzerland Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Informatics Technical University of Munich Munich Germany Medical Image Analysis Laboratory Department of Diagnostic and Interventional Radiology Lausanne University Hospital University of Lausanne Lausanne Switzerland CIBM Center for Biomedical Imaging Lausanne Switzerland Laboratory for Computational Neuroimaging Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Harvard Medical School CharlestownMA United States Medical University of Vienna Vienna Austria Arizona State University United States NVIDIA United States Shanghai Jiaotong University China School of Computer Science Shaanxi Normal University Xi'An710119 China Research Institute NEUROPHET Inc. Seoul06247 Korea Republic of Department of Radiology The Catholic University of Korea Eunpyeong St. Mary's Hospital Seoul06247 Korea Republic of Boston Children's Hospital Harvard Medical School BostonMA United States 2Ai - School of Technology IPCA Barcelos Portugal Algoritmi Center School of Engineering University of Minho Guimarães Portugal School of Medicine University of Minho Braga Portugal ICVS 3B's - PT Government Associate Laboratory Guimarães Braga Portugal School of Computer Science and Engineering The Hebrew University of Jerusalem Israel Sagol Brain Institute Tel Aviv Sourasky Medical Center Israel Sagol School of Neuroscience Tel Aviv University Israel Sackler Faculty of Medicine Tel Aviv University Israel School of Biomedical Engineering & Imaging Sciences King's College London LondonSE1 7EU United Kingdom Department of Radiology University Hospitals Leuven Leuven3000 Belgium Computational Imaging Research Lab Department of Biomedical Imaging and Image-guided Therapy Medical

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, brainstem, deep grey matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero. © 2022, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

GAMMA Challenge: Glaucoma grAding from Multi-Modality imAges

arXiv

引用

arXiv 2022年

作者： Wu, Junde Fang, Huihui Li, Fei Fu, Huazhu Lin, Fengbin Li, Jiongcheng Huang, Yue Yu, Qinji Song, Sifan Xu, Xinxing Xu, Yanyu Wang, Wensai Wang, Lingxiao Lu, Shuai Li, Huiqi Huang, Shihua Lu, Zhichao Ou, Chubin Wei, Xifei Liu, Bingyuan Kobbi, Riadh Tang, Xiaoying Lin, Li Zhou, Qiang Hu, Qiang Bogunović, Hrvoje Orlando, José Ignacio Zhang, Xiulan Xu, Yanwu State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Intelligent Healthcare Unit Baidu Inc. Beijing China Singapore School of Informatics Xiamen University Xiamen China Shanghai Jiao Tong University Shanghai China Xi'an Jiaotong-Liverpool University Suzhou China Institute of High Performance Computing A*STAR Singapore Institute of Biomedical Engineering Chinese Academy of Medical Sciences Peking Union Medical College Tianjin China School of Medical Technology Beijing Institute of Technology Beijing China Department of Computing Hong Kong Polytechnic University Hong Kong Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Weizhi Medical Technology Company Suzhou China École de Technologie Supérieure Montreal Montreal Canada DIAGNOS Inc. Quebec Canada Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Technology Co. Ltd. Shanghai China School of Information and Electronics Beijing Institute of Technology Beijing China Christian Doppler Lab for Artificial Intelligence in Retina Department of Ophthalmology Medical University of Vienna Austria Yatiris Group PLADEMA Institute CONICET UNICEN Tandil Argentina

Glaucoma is a chronic neuro-degenerative condition that is one of the world's leading causes of irreversible but preventable blindness. The blindness is generally caused by the lack of timely detection and treatment. Early screening is thus essential for early treatment to preserve vision and maintain life quality. Color fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both imaging modalities have prominent biomarkers to indicate glaucoma suspects, such as the vertical cup-to-disc ratio (vCDR) on fundus images and retinal nerve fiber layer (RNFL) thickness on OCT volume. In clinical practice, it is often recommended to take both of the screenings for a more accurate and reliable diagnosis. However, although numerous algorithms are proposed based on fundus images or OCT volumes for the automated glaucoma detection, there are few methods that leverage both of the modalities to achieve the target. To fulfill the research gap, we set up the Glaucoma grAding from Multi-Modality imAges (GAMMA) Challenge to encourage the development of fundus & OCT-based glaucoma grading. The primary task of the challenge is to grade glaucoma from both the 2D fundus images and 3D OCT scanning volumes. As part of GAMMA, we have publicly released a glaucoma annotated dataset with both 2D fundus color photography and 3D OCT volumes, which is the first multi-modality dataset for machine learning based glaucoma grading. In addition, an evaluation framework is also established to evaluate the performance of the submitted methods. During the challenge, 1272 results were submitted, and finally, ten best performing teams were selected for the final stage. We analyze their results and summarize their methods in the paper. Since all the teams submitted their source code in the challenge, we conducted a detailed ablation study to verify the effectiveness of the particular modules proposed. Finally, we identify the proposed techniqu

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Segmentation-guided Domain Adaptation and Data Harmonization of Multi-device Retinal Optical Coherence Tomography using Cycle-Consistent Generative Adversarial Networks

arXiv

引用

arXiv 2022年

作者： Chen, Shuo Ma, Da Lee, Sieun Yu, Timothy T.L. Xu, Gavin Lu, Donghuan Popuri, Karteek Ju, Myeong Jin Sarunic, Marinko V. Beg, Mirza Faisal School of Engineering Science Simon Fraser University BurnabyBC Canada Department of Internal Medicine Section of Gerontology and Geriatric Medicine Wake Forest University School of Medicine Winston-SalemNC United States Center for Biomedical Informatics Wake Forest School of Medicine Winston-SalemNC United States Alzheimer’s Disease Research Center Wake Forest School of Medicine Winston-SalemNC United States Mental Health & Clinical Neuroscience University of Nottingham Nottingham United Kingdom Precision Imaging Beacon University of Nottingham Nottingham United Kingdom Tencent Jarvis Lab. Shenzhen China Department of Computer Science Memorial University of Newfoundland St. John’sNL Canada School of Biomedical Engineering University of British Columbia BC Canada Department of Ophthalmology & Visual Sciences The University of British Columbia VancouverBC Canada Institute of Ophthalmology University College London London United Kingdom Department of Medical Physics and Biomedical Engineering University College London United Kingdom

Background: Medical images such as Optical Coherence Tomography (OCT) images acquired from different devices may show significantly different intensity profiles. An automatic segmentation model trained on images from one device may perform poorly when applied to images acquired using a different device, resulting in a lack of generalisability. This study aims to address this issue using domain adaptation methods improved by Cycle-Consistent Generative Adversarial Networks(CycleGAN), especially in cases when the ground-truth labels are only available in the source domain. Methods: A two-stage pipeline is proposed to generate segmentation in the target domain. The first stage involves the training of a state-of-the-art segmentation model in the source domain. The second stage aims to adapt the images from the target domain into the source domain. The adapted target domain images are segmented using the model in the first stage. Ablation tests were performed with a different integration of loss functions, and the statistical significance of these models is reported. Both the segmentation performance and the adapted image quality metrics are evaluated. Results: Regarding the segmentation Dice score, the proposed ssppg model achieves a significant improvement of 46.24% compared to no adaptation, and it reaches 87.4% of the upper limit of the segmentation performance. Moreover, the image quality metrics including the FID and KID score indicate that adapted images with better segmentation also have better image qualities. Conclusion: The proposed method demonstrates the effectiveness of segmentation-driven domain adaptation in retinal imaging processing. It reduces the labour cost of manual labelling, incorporates prior anatomic information to regulate and guide the domain adaptation, and provides insights into improving segmentation qualities in image domains without labels. © 2022, CC BY-NC-SA.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：