检索结果-内蒙古大学图书馆

Deep learning-based number detection and recognition for gas meter reading

学校读者我要写书评

暂无评论

IEIE Transactions on Smart processing and Computing 2019年第5期8卷 367-372页

作者： Son, Changeui Park, Seokmok Lee, JaeMin Paik, Joonki Department of Image Engineering Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul06974 Korea Republic of

The meter reading-system field has been researched from conventional methods centered on image processing technology to techniques based on learning methods such as machine learning or deep learning. The biggest problem for meter reading systems based on computer vision is difficulty in recognizing the various kinds of meters. In fact, there are more than five major manufacturers for the meters installed in Korea. There are different meter reading areas, ID regions, and number formats by version. Because of these problems, most of the meter reading is still done hands-on. In this paper, we present an automatic meter-reading system that can work simply and efficiently, compared to existing meter reading systems that need a skilled worker. Our meter reading system consists of three parts: i) detection of meter-reading and ID regions using You Only Look Once (YOLO), ii) digit segmentation for recognition, and iii) convolutional neural network (CNN)-based digit recognition. It is possible to robustly detect and recognize various meter types by using the method presented here. Therefore, it can provide an environment where gas meter checkers can work efficiently without inconvenient procedures. Copyrights © 2019 The Institute of Electronics and Information Engineers

关键词： Computer vision

Impact of scanner variability on lymph node segmentation in computational pathology

学校读者我要写书评

暂无评论

Journal of Pathology Informatics 2022年 13卷 100127-100127页

作者： Khan, Amjad Janowczyk, Andrew Müller, Felix Blank, Annika Nguyen, Huu Giao Abbet, Christian Studer, Linda Lugli, Alessandro Dawson, Heather Thiran, Jean-Philippe Zlobec, Inti Institute of Pathology University of Bern Murtenstrasse 31 Bern CH-3008 Switzerland Case Western Reserve University Department of Biomedical Engineering Cleveland 44106 OH United States Department of Oncology Lausanne University Hospital and Lausanne University Lausanne Switzerland Swiss Federal Institute of Technology Lausanne (EPFL) Signal Processing Laboratory (LTS5) Lausanne Switzerland Institute of Complex Systems (iCoSyS) University of Applied Sciences and Arts Western Switzerland Delémont Switzerland Document Image and Video Analysis (DIVA) Research Group Department of Informatics University of Fribourg Fribourg Switzerland Department of Radiology Lausanne University Hospital Lausanne University Centre d'Imagerie Biomédicale (CIBM) Lausanne Switzerland Institute of Pathology City Hospital Triemli Zürich Switzerland

Computer-aided diagnostics in histopathology are based on the digitization of glass slides. However, heterogeneity between the images generated by different slide scanners can unfavorably affect the performance of computational algorithms. Here, we evaluate the impact of scanner variability on lymph node segmentation due to its clinical importance in colorectal cancer diagnosis. 100 slides containing 276 lymph nodes were digitized using 4 different slide scanners, and 50 of the lymph nodes containing metastatic cancer cells. These 400 scans were subsequently annotated by 2 experienced pathologists to precisely label lymph node boundary. Three different segmentation methods were then applied and compared: Hematoxylin-channel-based thresholding (HCT), Hematoxylin-based active contours (HAC), and a convolution neural network (U-Net). Evaluation of U-Net trained from both a single scanner and an ensemble of all scanners was completed. Mosaic images based on representative tiles from a scanner were used as a reference image to normalize the new data from different test scanners to evaluate the performance of a pre-trained model. Fine-tuning was carried out by using weights of a model trained on one scanner to initialize model weights for other scanners. To evaluate the domain generalization, domain adversarial learning and stain mix-up augmentation were also implemented. Results show that fine-tuning and domain adversarial learning decreased the impact of scanner variability and greatly improved segmentation across scanners. Overall, U-Net with stain mix-up (Matthews correlation coefficient (MCC) = 0.87), domain adversarial learning (MCC = 0.86), and HAC (MCC = 0.87) were shown to outperform HCT (MCC = 0.81) for segmentation of lymph nodes when compared against the ground truth. The findings of this study should be considered for future algorithms applied in diagnostic routines. © 2022 The Author(s)

关键词： Colorectal cancer Computational pathology Domain generalization Fine tuning Lymph node Lymph node segmentation Scanner variability Whole slide image

Understanding metric-related pitfalls in image analysis validation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Reinke, Annika Tizabi, Minu D. Baumgartner, Michael Eisenmann, Matthias Heckmann-Nötzel, Doreen Kavur, A. Emre Rädsch, Tim Sudre, Carole H. Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Benis, Arriel Blaschko, Matthew B. Buettner, Florian Cardoso, M. Jorge Cheplygina, Veronika Chen, Jianxu Christodoulou, Evangelia Cimini, Beth A. Collins, Gary S. Farahani, Keyvan Ferrer, Luciana Galdran, Adrian van Ginneken, Bram Glocker, Ben Godau, Patrick Haase, Robert Hashimoto, Daniel A. Hoffman, Michael M. Huisman, Merel Isensee, Fabian Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kenngott, Hannes Kleesiek, Jens Kofler, Florian Kooi, Thijs Kopp-Schneider, Annette Kozubek, Michal 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 Rafelski, Susanne M. Rajpoot, Nasir Reyes, Mauricio Riegler, Michael A. Rieke, Nicola Saez-Rodriguez, Julio Sánchez, Clara I. Shetty, Shravya Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. van Calster, Ben Varoquaux, Gaël Yaniv, Ziv R. Jäger, Paul F. Maier-Hein, Lena Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Intelligent Medical Systems Germany NCT Heidelberg A Partnership Between DKFZ University Medical Center Heidelberg Germany Heidelberg Division of Medical Image Computing Germany Heidelberg Division of Intelligent Medical Systems 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 Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montreal Canada Division of Computational Pathology Dept of Pathology & Laboratory Medicine Indiana University School of Medicine IU Health Information and Translational Sciences Building Indianapolis United States University of Pennsylvania Richards Medical Research Laboratories FL7 PhiladelphiaPA United States Department of Digital Medical Technologies Holon Institute of Technology Holon Israel European Federation for Medical Informatics Le Mont-sur-Lausanne Switzerland Center for Processing Speech and Images Department of Electrical Engineering KU Leuven Leuven Belgium partner site Frankfurt/Mainz a partnership between DKFZ and UCT Frankfurt Marburg Germany Heidelberg Germany Goethe University Frankfurt Department of Medicine Germany Goethe University Frankfurt Department of Informatics Germany and Frankfurt Cancer Insititute Germany Department of Computer Science IT University of Copenhagen Copenhagen Denmark Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V. Dortmund Germany Imaging Platform Broad Institute of MIT and Harvard CambridgeMA United States Centre for Statistics in Medicine University of Oxford Oxford United Kingdom Center for Biomedical In

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately. While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. While focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation. © 2023, CC BY.

关键词： Computer vision

Learning data-adaptive non-parametric kernels

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

Contrast enhancement for low-light image enhancement: A survey

学校读者我要写书评

暂无评论

IEIE Transactions on Smart processing and Computing 2018年第1期7卷 36-48页

作者： Park, Seonhee Kim, Kiyeon Yu, Soohwan Paik, Joonki Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul06974 Korea Republic of Department of Integrative Engineering Chung-Ang University Seoul06974 Korea Republic of

In this paper, various contrast and low-light image enhancement methods are described and classified into three categories: I) histogram-based, ii) transmission map-based, and iii) retinexbased. The performance of the image enhancement algorithms is evaluated by comparing the resulting images using low-contrast and low-light images acquired under different illumination conditions. Various image enhancement algorithms are analyzed for both performance and efficiency. The described image enhancement algorithms can be applied to various visual surveillance or video analytics applications with low-light, low-contrast video input. © 2018 The Institute of Electronics and Information Engineers.

关键词： image enhancement

Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries (vol 13, 2728, 2023)

学校读者我要写书评

暂无评论

SCIENTIFIC REPORTS 2023年第1期13卷 1-10页

作者： Sendra-Balcells, Carla Campello, Victor M. Torrents-Barrena, Jordina Ahmed, Yahya Ali Elattar, Mustafa Ohene-Botwe, Benard Nyangulu, Pempho Stones, William Ammar, Mohammed Benamer, Lamya Nawal Kisembo, Harriet Nalubega Sereke, Senai Goitom Wanyonyi, Sikolia Z. Temmerman, Marleen Gratacos, Eduard Bonet, Elisenda Eixarch, Elisenda Mikolaj, Kamil Tolsgaard, Martin Gronnebaek Lekadir, Karim Departament de Matemàtiques i Informàtica Universitat de Barcelona Barcelona Spain HP Inc. Barcelona Spain Obstetrics and Gynecology Department School of Medicine Suez University Suez Egypt Medical Imaging and Image Processing Center of Informatics Science Nile University Sheikh Zayed City Egypt Research and Development Division Intixel Cairo Egypt Department of Radiography School of Biomedical and Allied Health Sciences College of Health Sciences University of Ghana Accra Ghana Division of Midwifery and Radiography School of Health and Psychological Sciences University of London London UK Kamuzu University of Health Sciences Blantyre Malawi Department of Electrical Engineering Systems Laboratory of Engineering System and Telecommunication University of M’Hamed Bougara Boumerdes Algiers Algeria Obstetrics and Gynecology Department School of Medicine Algiers University Algiers Algeria Department of Radiology Mulago National Referral and Teaching Hospital Kampala Uganda Department of Radiology and Radiotherapy School of Medicine Makerere University College of Health Sciences Kampala Uganda Department of Obstetrics and Gynaecology Aga Khan University Hospital 3rd Parklands Avenue Nairobi Kenya Centre of Excellence in Women and Child Health Aga Khan University Nairobi Kenya BCNatal Fetal Medicine Research Center Hospital Clínic and Hospital Sant Joan de Déu Universitat de Barcelona Barcelona Spain Institut d’Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS) Barcelona Spain Centre for Biomedical Research on Rare Diseases (CIBER-ER) Barcelona Spain Barcelona Tech Universitat Politècnica de Catalunya Barcelona Spain Copenhagen Academy for Medical Education and Simulation and Department of Obstetrics Rigshospitalet Copenhagen Denmark

Most artificial intelligence (AI) research and innovations have concentrated in high-income countries, where imaging data, IT infrastructures and clinical expertise are plentiful. However, slower progress has been made in limited-resource environments where medical imaging is needed. For example, in Sub-Saharan Africa, the rate of perinatal mortality is very high due to limited access to antenatal screening. In these countries, AI models could be implemented to help clinicians acquire fetal ultrasound planes for the diagnosis of fetal abnormalities. So far, deep learning models have been proposed to identify standard fetal planes, but there is no evidence of their ability to generalise in centres with low resources, i.e. with limited access to high-end ultrasound equipment and ultrasound data. This work investigates for the first time different strategies to reduce the domain-shift effect arising from a fetal plane classification model trained on one clinical centre with high-resource settings and transferred to a new centre with low-resource settings. To that end, a classifier trained with 1792 patients from Spain is first evaluated on a new centre in Denmark in optimal conditions with 1008 patients and is later optimised to reach the same performance in five African centres (Egypt, Algeria, Uganda, Ghana and Malawi) with 25 patients each. The results show that a transfer learning approach for domain adaptation can be a solution to integrate small-size African samples with existing large-scale databases in developed countries. In particular, the model can be re-aligned and optimised to boost the performance on African populations by increasing the recall to\(0.92 \pm 0.04\)and at the same time maintaining a high precision across centres. This framework shows promise for building new AI models generalisable across clinical centres with limited data acquired in challenging and heterogeneous conditions and calls for further research to develop new solutions for the us

关键词：

Metrics Reloaded: Recommendations for image analysis validation

学校读者我要写书评

暂无评论

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

Benchmarking quality-dependent and cost-sensitive score-level multimodal biometric fusion algorithms

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Poh, Norman Bourlai, Thirimachos Kittler, Josef Allano, Lorene Alonso-Fernandez, Fernando Ambekar, Onkar Baker, John Dorizzi, Bernadette Fatukasi, Omolara Fierrez, Julian Ganster, Harald Ortega-Garcia, Javier Maurer, Donald Salah, Albert Ali Scheidat, Tobias Vielhauer, Claus Centre for Vision Speech and Signal Processing School of Electronics and Physical Sciences University of Surrey Guildford SurreyGU2 7XH United Kingdom Biometrics Center Lane Department of Computer Science and Electrical Engineering College of Engineering and Mineral Resources West Virginia University MorgantownWV26506-6109 United States Institut Telecom Telecom and Management SudParis Evry91011 France Biometric Recognition Group – ATVS Escuela Politecnica Superior Universidad Autonoma de Madrid Madrid28049 Spain Amsterdam1098 XG Netherlands Applied Physics Laboratory Johns Hopkins University LaurelMD20723 United States Electronics and Physics Department Institut Telecom Telecom and Management SudParis Evry91011 France Institute of Digital Image Processing Joanneum Research Graz8010 Austria ISLA-ISIS University of Amsterdam Amsterdam1098 XG Netherlands Department of Informatics and Media Brandenburg University of Applied Sciences Brandenburg an der HavelD-14770 Germany Research Group Multimedia and Security Department of Technical and Business Information Systems Faculty of Computer Science Otto-von-Guericke-University of Magdeburg MagdeburgD-39106 Germany

Automatically verifying the identity of a person by means of biometrics (e.g., face and fingerprint) is an important application in our day-to-day activities such as accessing banking services and security control in airports. To increase the system reliability, several biometric devices are often used. Such a combined system is known as a multimodal biometric system. This paper reports a benchmarking study carried out within the framework of the BioSecure DS2 (Access Control) evaluation campaign organized by the University of Surrey, involving face, fingerprint, and iris biometrics for person authentication, targeting the application of physical access control in a medium-size establishment with some 500 persons. While multimodal biometrics is a well-investigated subject in the literature, there exists no benchmark for a fusion algorithm comparison. Working towards this goal, we designed two sets of experiments: quality-dependent and cost-sensitive evaluation. The quality-dependent evaluation aims at assessing how well fusion algorithms can perform under changing quality of raw biometric images principally due to change of devices. The cost-sensitive evaluation, on the other hand, investigates how well a fusion algorithm can perform given restricted computation and in the presence of software and hardware failures, resulting in errors such as failure-to-acquire and failure-to-match. Since multiple capturing devices are available, a fusion algorithm should be able to handle this nonideal but nevertheless realistic scenario. In both evaluations, each fusion algorithm is provided with scores from each biometric comparison subsystem as well as the quality measures of both the template and the query data. The response to the call of the evaluation campaign proved very encouraging, with the submission of 22 fusion systems. To the best of our knowledge, this campaign is the first attempt to benchmark quality-based multimodal fusion algorithms. In the presence of changing

关键词： Benchmarking

A Robust Ensemble Algorithm for Ischemic Stroke Lesion Segmentation: Generalizability and Clinical Utility Beyond the ISLES Challenge

学校读者我要写书评

暂无评论

arXiv 2024年

作者： de la Rosa, Ezequiel Reyes, Mauricio Liew, Sook-Lei Hutton, Alexandre Wiest, Roland Kaesmacher, Johannes Hanning, Uta Hakim, Arsany Zubal, Richard Valenzuela, Waldo Robben, David Sima, Diana M. Anania, Vincenzo Brys, Arne Meakin, James A. Mickan, Anne Broocks, Gabriel Heitkamp, Christian Gao, Shengbo Liang, Kongming Zhang, Ziji Siddiquee, Md Mahfuzur Rahman Myronenko, Andriy Ashtari, Pooya Van Huffel, Sabine Jeong, Hyun-Su Yoon, Chi-Ho Kim, Chulhong Huo, Jiayu Ourselin, Sebastien Sparks, Rachel Clèrigues, Albert Oliver, Arnau Lladó, Xavier Chalcroft, Liam Pappas, Ioannis Bertels, Jeroen Heylen, Ewout Moreau, Juliette Hatami, Nima Frindel, Carole Qayyum, Abdul Mazher, Moona Puig, Domenec Lin, Shao-Chieh Juan, Chun-Jung Hu, Tianxi Boone, Lyndon Goubran, Maged Liu, Yi-Jui Wegener, Susanne Kofler, Florian Ezhov, Ivan Shit, Suprosanna Hernandez Petzsche, Moritz R. Menze, Bjoern Kirschke, Jan S. Wiestler, Benedikt Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Informatics Technical University Munich Germany Icometrix Leuven Belgium ARTORG Center for Biomedical Research University of Bern Bern Switzerland Department of Radiation Oncology University Hospital Bern University of Bern Switzerland University of Bern Bern Switzerland Chan Division of Occupational Science and Occupational Therapy University of Southern California Los AngelesCA United States Stevens Neuroimaging and Informatics Institute Department of Neurology Keck School of Medicine University of Southern California United States University Institute of Diagnostic and Interventional Neuroradiology Inselspital Bern Switzerland University Institute of Diagnostic and Interventional Neuroradiology University Hospital Bern Inselspital University of Bern Bern Switzerland Department of Diagnostic and Interventional neuroradiology University Medical Center Hamburg-Eppendorf Hamburg Germany Department of Medical Imaging Radboud University Medical Center Institute for Health Sciences Nijmegen Netherlands Deepwise AI Lab Beijing China Beijing University of Posts and Telecommunications Bejing China School of Computing and Augmented Intelligence Arizona State University TempeAZ United States NVIDIA Santa ClaraCA United States STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium Pohang Korea Republic of School of Biomedical Engineering & Imaging Sciences King’s College London United Kingdom Institute of Computer Vision and Robotics University of Girona Spain Wellcome Centre for Human Neuroimaging University College London London United Kingdom Laboratory of Neuro Imaging Stevens Institute for Neuroimaging and Informatics Keck School of Medicine University of Southern California Los Angeles United States KU Leuven Leuven Belgium CREATIS Université Lyon1 CNRS UMR5220 INSERM U1206 INSA-Lyon Villeurbanne696

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES’22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. By assessing them against a hidden test set, we identified strengths, weaknesses, and potential biases. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model combines the individual algorithms’ strengths and achieved superior ischemic lesion detection and segmentation accuracy (median Dice score: 0.82, median lesion-wise F1 score: 0.86) on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers like lesion types and affected vascular territories. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm’s segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model’s generalizability (median Dice score: 0.82, median lesion-wise F1 score: 0.86). The algorithm’s outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)rad

关键词： Diagnosis