检索结果-内蒙古大学图书馆

Composite likelihood inference for analysis of individual animal identification data

学校读者我要写书评

暂无评论

Ecological Informatics 2025年 90卷

作者： Xueli Xu Xiaoyue Zhang Hal Whitehead Dehan Kong Ximing Xu Center for Biomedical Digital Science Guangzhou Institutes of Biomedicine and Health Chinese Academy of Sciences Guangzhou 510530 China Department of Biostatistics Harvard University Chan School of Public Health Boston MA United States Department of Biology Dalhousie University Halifax Nova Scotia Canada Department of Statistical Sciences University of Toronto Ontario M5S 3G3 Canada Big Data Center for Children's Medical Care Children's Hospital of Chongqing Medical University； National Clinical Research Center for Child Health and Disorders Ministry of Education Key Laboratory of Child Development and Disorders 400014 China Intelligent Application of Big Data in Pediatrics Engineering Research Center of Chongqing Education Commission of China 400014 China

Individual identification data collection is a common practice in animal behaviour, movement ecology, and conservation biology. While likelihood analysis is widely employed for ecological insights, the complexity of individual identification data, characterized by numerous interdependent individuals and identification times, makes direct likelihood calculation challenging. To address this, we introduce a composite likelihood inference framework. We establish the consistency and asymptotic normality of maximum composite likelihood estimators within this framework. Furthermore, we develop a composite likelihood-based information criterion for model selection, capable of handling complex individual identification data. Our approach is demonstrated through extensive simulations and applied to the northern bottlenose whale population in the Gully, Nova Scotia. This study provides a statistically rigorous framework for individual animal identification models, with potential applications extending beyond whale populations.

关键词： Individual identification data Composite likelihood Model selection Animal movement Animal social structure

The Dynamic Sensorium competition for predicting large-scale mouse visual cortex activity from videos

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Turishcheva, Polina Fahey, Paul G. Hansel, Laura Froebe, Rachel Ponder, Kayla Vystrčilová, Michaela Willeke, Konstantin F. Bashiri, Mohammad Wang, Eric Ding, Zhiwei Tolias, Andreas S. Sinz, Fabian H. Ecker, Alexander S. Qiur, Yongrong Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany Department of Neuroscience Baylor College of Medicine HoustonTX United States Center for Neuroscience and Artificial Intelligence Baylor College of Medicine HoustonTX United States Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine StanfordCA United States Stanford Bio-X Stanford University StanfordCA United States Wu Tsai Neurosciences Institute Stanford University StanfordCA United States International Max Planck Research School for Intelligent Systems University of Tübingen Germany Institute for Bioinformatics and Medical Informatics University of Tübingen Germany Department of Electrical Engineering Stanford University StanfordCA United States Max Planck Institute for Dynamics and Self-Organization Göttingen Germany

Understanding how biological visual systems process information is challenging due to the complex nonlinear relationship between neuronal responses and high-dimensional visual input. Artificial neural networks have already improved our understanding of this system by allowing computational neuroscientists to create predictive models and bridge biological and machine vision. During the Sensorium 2022 competition, we introduced benchmarks for vision models with static input (i.e. images). However, animals operate and excel in dynamic environments, making it crucial to study and understand how the brain functions under these conditions. Moreover, many biological theories, such as predictive coding, suggest that previous input is crucial for current input processing. Currently, there is no standardized benchmark to identify state-of-the-art dynamic models of the mouse visual system. To address this gap, we propose the Sensorium 2023 Benchmark Competition with dynamic input (https://***/). This competition includes the collection of a new large-scale dataset from the primary visual cortex of ten mice, containing responses from over 78,000 neurons to over 2 hours of dynamic stimuli per neuron. Participants in the main benchmark track will compete to identify the best predictive models of neuronal responses for dynamic input (i.e. video). We will also host a bonus track in which submission performance will be evaluated on out-of-domain input, using withheld neuronal responses to dynamic input stimuli whose statistics differ from the training set. Both tracks will offer behavioral data along with video stimuli. As before, we will provide code, tutorials, and strong pre-trained baseline models to encourage participation. We hope this competition will continue to strengthen the accompanying Sensorium benchmarks collection as a standard tool to measure progress in large-scale neural system identification models of the entire mouse visual hierarchy and

关键词： Mammals

Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study

学校读者我要写书评

暂无评论

The Lancet Digital Health 2025年第5期7卷 100868页

作者： Meng, Ziyao Guan, Zhouyu Yu, Shujie Wu, Yilan Zhao, Yaoning Shen, Jie Lim, Cynthia Ciwei Chen, Tingli Yang, Dawei Ran, An Ran He, Feng Hamzah, Haslina Singh, Sarkaaj Abd Raof, Anis Syazwani Lee-Boey, Jian Wen Samuel Lim, Soo-Kun Sun, Xufang Ge, Shuwang Xu, Gang Su, Hua Cheng, Yang Lu, Feng Liao, Xiaofei Jin, Hai Deng, Chenxin Ruan, Lei Zhang, Cuntai Wu, Chan Dai, Rongping Jin, Yixiao Wang, Wenxiao Li, Tingyao Liu, Ruhan Li, Jiajia Shu, Jia Lu, Yuwei Wang, Xiangning Wu, Qiang Qin, Yiming Tang, Jin Sheng, Xiaohua Jiao, Qiong Yang, Xiaokang Guo, Minyi McKay, Gareth J Hogg, Ruth E Liew, Gerald Chee, Evelyn Yi Lyn Hsu, Wynne Lee, Mong Li Szeto, Simon Luk, Andrea O Y Chan, Juliana C N Cheung, Carol Y Tan, Gavin Siew Wei Tham, Yih-Chung Cheng, Ching-Yu Sabanayagam, Charumathi Lim, Lee-Ling Jia, Weiping Li, Huating Sheng, Bin Wong, Tien Yin Shanghai Belt and Road International Joint Laboratory of Intelligent Prevention and Treatment for Metabolic Diseases Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Institute for Proactive Healthcare Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Centre for Diabetes Shanghai Key Laboratory of Diabetes Mellitus Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Beijing Tsinghua Changgung Hospital Eye Center School of Clinical Medicine Tsinghua Medicine Tsinghua University Beijing China Medical Records and Statistics Office Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Renal Medicine Singapore General Hospital SingHealth-Duke Academic Medical Centre Singapore Singapore Department of Ophthalmology Shanghai Health and Medical Center Wuxi China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong Special Administrative Region China Singapore Eye Research Institute Singapore National Eye Centre Singapore Department of Medicine Faculty of Medicine Universiti Malaya Kuala Lumpur Malaysia Department of Ophthalmology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Hubei Wuhan China Department of Nephrology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China Department of Nephrology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China Department of Ophthalmology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Centre for Big Dat

Background: Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (ai) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images. Methods: In this population-based study, we developed a retinal image-based ai-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD;and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up. Findings: For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838–0·846) on the internal validation dataset and AUCs of 0·791–0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825–0·966) on the internal validation dataset and AUCs of 0·733–0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD wit

关键词： Deep learning

A large deviation principle for block models

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Borgs, Christian Chayes, Jennifer Gaudio, Julia Petti, Samantha Sen, Subhabrata University of California Berkeley United States Massachusetts Institute of Technology United States Harvard University United States Berkeley AI Research Group Department of Electrical Engineering and Computer Science Department of Electrical Engineering and Computer Science Department of Mathematics Department of Statistics School of Information Department of Mathematics NSF-Simons Center for Mathematical and Statistical Analysis of Biology Department of Statistics

We initiate a study of large deviations for block model random graphs in the dense regime. Following [14], we establish an LDP for dense block models, viewed as random graphons. As an application of our result, we study upper tail large deviations for homomorphism densities of regular graphs. We identify the existence of a "symmetric" phase, where the graph, conditioned on the rare event, looks like a block model with the same block sizes as the generating graphon. In specific examples, we also identify the existence of a "symmetry breaking" regime, where the conditional structure is not a block model with compatible dimensions. This identifies a "reentrant phase transition" phenomenon for this problem—analogous to one established for Erdős–Rényi random graphs [13, 14]. Finally, extending the analysis of [33], we identify the precise boundary between the symmetry and symmetry breaking regime for homomorphism densities of regular graphs and the operator norm on Erdős–Rényi bipartite *** Codes 60F10, 05C80, 60C05 Copyright © 2020, The Authors. All rights reserved.

关键词： Graphic methods

NTIRE 2023 Challenge on Light Field Image Super-Resolution: dataset, Methods and Results

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany ETH Zürich Switzerland The Shenzhen Campus of Sun Yat-Sen University Sun Yat-Sen University China Bigo Technology Pte. Ltd Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023, CC BY-SA.

关键词： Image enhancement

LCBNI: Link completion bipartite network inference for predicting new lncRNA-miRNA interactions

学校读者我要写书评

暂无评论

LCBNI: Link completion bipartite network inference for predi...

2018 IEEE International Conference of Safety Produce Informatization, IICSPI 2018

作者： Yu, Zhenkun Zhu, Fuxi Tianl, Gang Wang, Hao School of Computer Science Wuhan University Wuhan430072 China AI Application Research Center Wuhan College Wuhan Hubei430211 China State Key Laboratory of Geomechanics and Geotechnical Engineering Institute of Rock and Soil Mechanics Chinese Academy of Sciences Wuhan430071 China

ISBN: (纸本)9781538655139

LncRNAs and miRNAs are two different kinds of non-coding RNAs and are both important for human in the field of health and disease. LncRNAs can interact with miRNAs, and the interactions play key roles in gene regulatory networks. Predicting IncRNA-miRNA interactions is an urgent and significant task and can help to explore the mechanism of involved complicated diseases, but very few computational methods are developed. In this paper, we introduce a computational method named link completion bipartite network inference (LCBNI) to predict the potential interactions between IncRNAs and miRNAs. LCBNI formulates the observed IncRNA-miRNA interactions as a bipartite network. Considering that there is no any known interaction for new IncRNAs or miRNAs, LCBNI calculates the sequence similarity and utilizes weighted nearest neighbor interaction information to construct new interaction scores for these IncRNAs and miRNAs. Then, we implement a resource allocation algorithm on the bipartite network to predict IncRNA-miRNA interactions. The experimental results demonstrate that LCBNI can effectively predict IncRNA-miRNA interactions with higher accuracy compared with other state-of-the-art methods and network-based methods, including random walk with restart (RWR), IncRNA-based collaborative filtering (LncCF) and miRNA-based collaborative filtering (MiCF). Furthermore, case studies are performed to demonstrate the prediction capability of LCBNI using real data. © 2018 IEEE.

关键词： Collaborative filtering

Magnetic and levitation properties of YBCO/polymer composite drop-casting films

学校读者我要写书评

暂无评论

Next Materials

Next Materials 2025年 8卷

作者： Beatriz Lucas Miguel Brito Canan Aksoy Bakiye Cakir Elvan Coşkun Ali Gencer Anabela Pronto Isabel Ferreira CENIMAT|i3N Department of Materials Science School of Science and Technology NOVA University Lisbon Caparica Portugal Electrical and Computer Engineering Department School of Science and Technology NOVA University Lisbon Caparica Portugal Electronics and Communication Engineering Faculty of Technology Karadeniz Technical University Trabzon 61830 Turkiye Vocational School of Health Services Artvin Çoruh University Artvin 08000 Turkiye Ankara University Superconductor Technologies Application and Research Center Gölbaşı Ankara Turkiye Ankara University Faculty of Sciences Physics Department Ankara 06100 Turkiye Center of Technology and Systems CTS/UNINOVA School of Science and Technology NOVA University Lisbon Caparica Portugal

Superconducting materials have been extensively studied for various applications, with YBCO alloys among the most researched and widely applied. This paper investigates the feasibility of using YBCO powder-based inks to produce cost-effective films with magnetic properties. Our studies demonstrate that levitation in liquid nitrogen is consistently observed in all fabricated films, regardless of ink composition or application method. Both drop-casting and spray-coating techniques were successfully employed to create levitating films. Additionally, various substrates—including aluminum foil (with and without adhesive), plastic foil, Teflon, and paper—were evaluated, with no significant impact on levitation performance. The levitation height was also compared to samples without a substrate. Depending on the binder, the resulting films exhibit rigidity or flexibility while maintaining their levitation capabilities even after multiple bending cycles. However, film conductivity is influenced by the binder type and concentration, which also affects the critical current density. A film with a thickness of 300 μm demonstrated a Jc of 2 kA/cm² at 65 K and zero magnetic field.

关键词： YBCO superconductor powders Polymers superconductor hybrid materials Selfsustained drop-casting films Levitation and magnetic properties Surface and chemical analysis

Measurement of the Pr141(n,γ) cross section up to stellar s-process temperatures at the China Spallation Neutron Source Back-n facility

学校读者我要写书评

暂无评论

Physical Review C 2023年第3期108卷 035802-035802页

作者： Xiankai Li Zhendong An Wei Jiang Jingyi Zhang Ruoran Bai Shaokun Liu Xinxiang Li Zhichao Zhu Gaole Yang Weiwei Qiu Zhengfa Liao Ziyue Zhuang Xiaoping Zhang Shengli Chen Chenchen Guo Erxi Xiao Xiao Fang Hongwei Wang Xinrong Hu Bing Jiang Wenqing Shen Jincheng Wang Jie Ren Xichao Ruan Wen Luo Haoyang Lan Zongwei Cao Xu Ma Yingdu Liu Pusen Wang Yi Yang Ping Su Xiangai Deng Wanbing He Yugang Ma Chunwang Ma Yuting Wang Zhitao Dai Ertao Li Pengqin He RenGuang Tang Tao Zhou Jing Wang Han Yi Yue Zhang Yonghao Chen Ruirui Fan Keqing Gao Qiang Li Kang Sun Zhixin Tan Minhao Gu Hantao Jing Jingyu Tang School of Nuclear Science and Technology University of South China Hengyang 421001 China School of Physics and Astronomy Sun Yat-sen University Zhuhai 519082 China Shanghai Institute of Applied Physics Chinese Academy of Sciences Shanghai 201800 China State Key Laboratory of Lunar and Planetary Sciences Macau University of Science and Technology Macau 999078 China CNSA Macau Center for Space Exploration and Science Macau 999078 China Institute of High Energy Physics Chinese Academy of Sciences Beijing 100049 China Spallation Neutron Source Science Center Dongguan 523803 China University of Chinese Academy of Sciences Beijing 100049 China Sino-French Institute of Nuclear Engineering and Technology Sun Yat-sen University Zhuhai 519082 China Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai 201210 China Key Laboratory of Nuclear Data China Institute of Atomic Energy Beijing 102413 China State Key Laboratory of Nuclear Physics and Technology and CAPT Peking University Beijing 100871 China Beijing Laser Acceleration Innovation Center Huairou Beijing 101400 China Shool of Materials Science and Engineering Xiangtan University Xiangtan 411100 China Key Laboratory of Nuclear Physics and Ion-beam Application (MOE) Institute of Modern Physics Department of Nuclear Science and Technology Fudan University Shanghai 200433 China Institute of Particle and Nuclear Physics Henan Normal University Xinxiang 453007 China School of Physics Henan Normal University Xinxiang 453007 China Shenzhen Center Cancer hospital Chinese Academy of Medical Sciences Shenzhen 518100 China Institute for Advanced Study in Nuclear Energy and Safety College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen 518060 China

In nuclear astrophysics, Pr141 is mainly produced by an s process, which has a neutron magic number (N=82) leading to its low capture cross section and strongly affecting the s process. Its neutron capture cross section is an important input parameter for nuclear astrophysical network calculations. According to the EXFOR database, the measurement precision for the Pr141(n,γ) cross section should be improved in the resolved and unresolved resonance region. The (n,γ) cross section of Pr141 was measured between 1 eV and 500 keV at the Back-n facility of the Chinese Spallation Neutron Source using the time-of-flight (TOF) method. The prompt γ rays were detected by four C6D6 liquid scintillator detectors, and the data was analyzed using the pulse-height weighting technique (PHWT). The majority of results are in agreement with the evaluated data libraries ENDF/B-VIII.0, JENDL-5.0, and TENDL-2021, with some significant exceptions for small resonances. The multilevel R-matrix Bayesian code sammy was used to extract the resonance parameters of Pr141 in the resolved resonance region. And the Maxwell average cross section (MACS) from kT=5 to 100 keV is calculated in the temperature range of the s-process nucleosynthesis model. In particular, at kT=30 keV the MACS value of Pr141 is 145.0±13.7 mb, which shows an obvious discrepancy with the Karlsruhe Astrophysical database of Nucleosynthesis in Stars (KADoNiS) recommended value 111.4±1.4 mb.

关键词： Neutron physics Nuclear astrophysics Nuclear reactions Nucleosynthesis in explosive environments Radiative capture Resonance reactions 90 ≤ A ≤ 149 Nuclear data analysis & compilation Radiation detectors

Unleashing the Strengths of Unlabeled data in Pan-cancer Abdominal Organ Quantification: The FLARE22 Challenge

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Jun Zhang, Yao Gu, Song Ge, Cheng Ma, Shihao Young, Adamo Zhu, Cheng Meng, Kangkang Yang, Xin Huang, Ziyan Zhang, Fan Liu, Wentao Pan, YuanKe Huang, Shoujin Wang, Jiacheng Sun, Mingze Xu, Weixin Jia, Dengqiang Choi, Jae Won Alves, Natália de Wilde, Bram Koehler, Gregor Wu, Yajun Wiesenfarth, Manuel Zhu, Qiongjie Dong, Guoqiang He, Jian Wang, Bo He, Junjun Yang, Hua Yang, Huihua Huang, Bingding Lyu, Mengye Ma, Yongkang Guo, Heng Zhang, Rongguo Maier-Hein, Klaus The Department of Laboratory Medicine and Pathobiology University of Toronto Peter Munk Cardiac Centre University Health Network Vector Institute Toronto Canada Shanghai AI Laboratory Shanghai200232 China The Department of Image Reconstruction Nanjing Anke Medical Technology Co. Ltd. Nanjing211113 China Ocean University of China Qingdao266100 China The Department of Computer Science University of Toronto Peter Munk Cardiac Centre University Health Network Vector Institute Toronto Canada Tinavi Medical Technologies Co. Ltd. Beijing100192 China University of Science and Technology Beijing Beijing100083 China The School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen518055 China The Department of Radiological Algorithm Fosun Aitrox Information Technology Co. Ltd. Shanghai200033 China The School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Shenzhen Technology University Shenzhen518000 China Xiamen University Xiamen361005 China Alibaba Beijing100084 China Infervision Medical Technology Co. Ltd. Beijing100025 China Hong Kong Centre for Cerebro-cardiovascular Health Engineering 000000 Hong Kong The Department of Radiology Armed Forces Yangju Hospital Yangju11429 Korea Republic of The Department of Radiology Radboudumc Nijmegen6525XZ Netherlands The Department of Medical Image Computing German Cancer Research Center Heidelberg69120 Germany ShenZhen Yorktal DMIT LLC Shenzhen518100 China Heidelberg69120 Germany The Department of Nuclear Medicine Nanjing Drum Tower Hospital Nanjing210008 China The College of Big Data and Internet Shenzhen Technology University Shenzhen518188 China The College of Health Science and Environmental Engineering Shenzhen Technology University Shenzhen China The Manteia Technologies Co. Ltd Xiamen China The Alibaba DAMO Academy Beijing China The Peter Munk Cardiac Centre University Health Network Department of Laboratory M

Quantitative organ assessment is an essential step in automated abdominal disease diagnosis and treatment planning. Artificial intelligence (ai) has shown great potential to automatize this process. However, most existing ai algorithms rely on many expert annotations and lack a comprehensive evaluation of accuracy and efficiency in real-world multinational settings. To overcome these limitations, we organized the FLARE 2022 Challenge, the largest abdominal organ analysis challenge to date, to benchmark fast, low-resource, accurate, annotation-efficient, and generalized ai algorithms. We constructed an intercontinental and multinational dataset from more than 50 medical groups, including Computed Tomography (CT) scans with different races, diseases, phases, and manufacturers. We independently validated that a set of ai algorithms achieved a median Dice Similarity Coefficient (DSC) of 90.0% by using 50 labeled scans and 2000 unlabeled scans, which can significantly reduce annotation requirements. The best-performing algorithms successfully generalized to holdout external validation sets, achieving a median DSC of 89.5%, 90.9%, and 88.3% on North American, European, and Asian cohorts, respectively. They also enabled automatic extraction of key organ biology features, which was labor-intensive with traditional manual measurements. This opens the potential to use unlabeled data to boost performance and alleviate annotation shortages for modern ai models. © 2023, CC BY-NC-ND.

关键词： Diseases