1
|
Liu S, Brandt M, Nord-Larsen T, Chave J, Reiner F, Lang N, Tong X, Ciais P, Igel C, Pascual A, Guerra-Hernandez J, Li S, Mugabowindekwe M, Saatchi S, Yue Y, Chen Z, Fensholt R. The overlooked contribution of trees outside forests to tree cover and woody biomass across Europe. Sci Adv 2023; 9:eadh4097. [PMID: 37713489 PMCID: PMC10881069 DOI: 10.1126/sciadv.adh4097] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Accepted: 08/15/2023] [Indexed: 09/17/2023]
Abstract
Trees are an integral part in European landscapes, but only forest resources are systematically assessed by national inventories. The contribution of urban and agricultural trees to national-level carbon stocks remains largely unknown. Here we produced canopy cover, height and above-ground biomass maps from 3-meter resolution nanosatellite imagery across Europe. Our biomass estimates have a systematic bias of 7.6% (overestimation; R = 0.98) compared to national inventories of 30 countries, and our dataset is sufficiently highly resolved spatially to support the inclusion of tree biomass outside forests, which we quantify to 0.8 petagrams. Although this represents only 2% of the total tree biomass, large variations between countries are found (10% for UK) and trees in urban areas contribute substantially to national carbon stocks (8% for the Netherlands). The agreement with national inventory data, the scalability, and spatial details across landscapes, including trees outside forests, make our approach attractive for operational implementation to support national carbon stock inventory schemes.
Collapse
Affiliation(s)
- Siyu Liu
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Martin Brandt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Thomas Nord-Larsen
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Jerome Chave
- Laboratoire Evolution et Diversité Biologique, CNRS, UPS, IRD, Université Paul Sabatier, Toulouse, France
| | - Florian Reiner
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Nico Lang
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Xiaoye Tong
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Philippe Ciais
- Laboratoire des Sciences du Climat et de l’Environnement, CEA/CNRS/UVSQ/Université Paris Saclay, Gif-sur-Yvette, France
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Adrian Pascual
- Department of Geographical Sciences, University of Maryland, College Park, MD, USA
| | - Juan Guerra-Hernandez
- Forest Research Center, School of Agriculture, University of Lisbon, Lisbon, Portugal
| | - Sizhuo Li
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Maurice Mugabowindekwe
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Sassan Saatchi
- Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA
| | - Yuemin Yue
- Key Laboratory for Agro-ecological Processes in Subtropical Region, Institute of Subtropical Agriculture, Chinese Academy of Sciences, Changsha, China
| | - Zhengchao Chen
- Airborne Remote Sensing Center, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
| | - Rasmus Fensholt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
2
|
Reiner F, Brandt M, Tong X, Skole D, Kariryaa A, Ciais P, Davies A, Hiernaux P, Chave J, Mugabowindekwe M, Igel C, Oehmcke S, Gieseke F, Li S, Liu S, Saatchi S, Boucher P, Singh J, Taugourdeau S, Dendoncker M, Song XP, Mertz O, Tucker CJ, Fensholt R. More than one quarter of Africa's tree cover is found outside areas previously classified as forest. Nat Commun 2023; 14:2258. [PMID: 37130845 PMCID: PMC10154416 DOI: 10.1038/s41467-023-37880-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2022] [Accepted: 03/29/2023] [Indexed: 05/04/2023] Open
Abstract
The consistent monitoring of trees both inside and outside of forests is key to sustainable land management. Current monitoring systems either ignore trees outside forests or are too expensive to be applied consistently across countries on a repeated basis. Here we use the PlanetScope nanosatellite constellation, which delivers global very high-resolution daily imagery, to map both forest and non-forest tree cover for continental Africa using images from a single year. Our prototype map of 2019 (RMSE = 9.57%, bias = -6.9%). demonstrates that a precise assessment of all tree-based ecosystems is possible at continental scale, and reveals that 29% of tree cover is found outside areas previously classified as tree cover in state-of-the-art maps, such as in croplands and grassland. Such accurate mapping of tree cover down to the level of individual trees and consistent among countries has the potential to redefine land use impacts in non-forest landscapes, move beyond the need for forest definitions, and build the basis for natural climate solutions and tree-related studies.
Collapse
Affiliation(s)
- Florian Reiner
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark.
| | - Martin Brandt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark.
| | - Xiaoye Tong
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - David Skole
- Global Observatory for Ecosystem Services, Department of Forestry, Michigan State University, East Lansing, MI, 48823, USA
| | - Ankit Kariryaa
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Philippe Ciais
- Laboratoire des Sciences du Climat et de l'Environnement, CEA/CNRS/UVSQ/Université Paris Saclay, Gif-sur-Yvette, France
| | - Andrew Davies
- Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, 02138, USA
| | | | - Jérôme Chave
- Laboratoire Evolution et Diversité Biologique, CNRS, UPS, IRD, Université Paul Sabatier, Toulouse, France
| | - Maurice Mugabowindekwe
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Stefan Oehmcke
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Fabian Gieseke
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
- Department of Information Systems, University of Münster, Münster, Germany
| | - Sizhuo Li
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
- Université Paris Saclay, Gif-sur-Yvette, France
| | - Siyu Liu
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Sassan Saatchi
- Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, 91109, USA
| | - Peter Boucher
- Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, 02138, USA
| | - Jenia Singh
- Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, 02138, USA
| | | | - Morgane Dendoncker
- Earth and Life Institute, Environmental Sciences, Université catholique de Louvain, Louvain-la-Neuve, Belgium
| | - Xiao-Peng Song
- Department of Geographical Sciences, University of Maryland, College Park, MD, 20740, USA
| | - Ole Mertz
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Compton J Tucker
- Earth Sciences Division, NASA Goddard Space Flight Center, Greenbelt, MD, 20771, USA
| | - Rasmus Fensholt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
3
|
Due JK, Pedersen MG, Antonsen S, Rommedahl J, Agerbo E, Mortensen PB, Sørensen HT, Lotz JF, Piqueras LC, Fierro C, Karamolegkou A, Igel C, Rust P, Søgaard A, Pedersen CB. Towards more comprehensive nationwide familial aggregation studies in Denmark: The Danish Civil Registration System versus the lite Danish Multi-Generation Register. Scand J Public Health 2023:14034948221147096. [PMID: 37036022 DOI: 10.1177/14034948221147096] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/11/2023]
Abstract
AIM Linking information on family members in the Danish Civil Registration System (CRS) with information in Danish national registers provides unique possibilities for research on familial aggregation of diseases, health patterns, social factors and demography. However, the CRS is limited in the number of generations that it can identify. To allow more complete familial linkages, we introduce the lite Danish Multi-Generation Register (lite MGR) and the future full Danish MGR that is currently being developed. METHODS We generated the lite MGR by linking the current version of the CRS with historical versions stored by the Danish National Archives in the early 1970s, which contain familial links not saved in the current CRS. We describe and compare the completeness of familial links in the lite MGR and the current version of the CRS. We also describe planned procedures for generating the full MGR by linking the current CRS with scanned archived records from Parish Registers. RESULTS Among people born in Denmark in 1960 or later, the current CRS contains information on both parents. However, it has limited parental information for people born earlier. Among the 732,232 people born in Denmark during 1950-1959, 444,084 (60.65%) had information on both parents in the CRS. In the lite MGR, it was 560,594 (76.56%). CONCLUSIONS
The lite MGR offers more complete information on familial relationships than the current CRS. The lite and full MGR will offer an infrastructure tying together existing research infrastructures, registers and biobanks, raising their joint research value to an unparalleled level.
Collapse
Affiliation(s)
| | - Marianne Giørtz Pedersen
- National Centre for Register-Based Research, Aarhus BSS, Aarhus University, Denmark
- Centre for Integrated Register-based Research, CIRRAU, Aarhus University, Denmark
| | - Sussie Antonsen
- National Centre for Register-Based Research, Aarhus BSS, Aarhus University, Denmark
| | | | - Esben Agerbo
- National Centre for Register-Based Research, Aarhus BSS, Aarhus University, Denmark
- Centre for Integrated Register-based Research, CIRRAU, Aarhus University, Denmark
| | - Preben Bo Mortensen
- National Centre for Register-Based Research, Aarhus BSS, Aarhus University, Denmark
- Centre for Integrated Register-based Research, CIRRAU, Aarhus University, Denmark
| | - Henrik Toft Sørensen
- Department of Clinical Epidemiology, Aarhus University Hospital and Aarhus University, Denmark
| | - Jonas Færch Lotz
- Department of Computer Science, University of Copenhagen, Denmark
| | | | - Constanza Fierro
- Department of Computer Science, University of Copenhagen, Denmark
| | | | - Christian Igel
- Department of Computer Science, University of Copenhagen, Denmark
| | - Phillip Rust
- Department of Computer Science, University of Copenhagen, Denmark
| | - Anders Søgaard
- Department of Computer Science, University of Copenhagen, Denmark
| | - Carsten Bøcker Pedersen
- National Centre for Register-Based Research, Aarhus BSS, Aarhus University, Denmark
- Centre for Integrated Register-based Research, CIRRAU, Aarhus University, Denmark
| |
Collapse
|
4
|
Li S, Brandt M, Fensholt R, Kariryaa A, Igel C, Gieseke F, Nord-Larsen T, Oehmcke S, Carlsen AH, Junttila S, Tong X, d’Aspremont A, Ciais P. Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale. PNAS Nexus 2023; 2:pgad076. [PMID: 37065619 PMCID: PMC10096914 DOI: 10.1093/pnasnexus/pgad076] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 01/28/2023] [Accepted: 02/27/2023] [Indexed: 04/18/2023]
Abstract
Sustainable tree resource management is the key to mitigating climate warming, fostering a green economy, and protecting valuable habitats. Detailed knowledge about tree resources is a prerequisite for such management but is conventionally based on plot-scale data, which often neglects trees outside forests. Here, we present a deep learning-based framework that provides location, crown area, and height for individual overstory trees from aerial images at country scale. We apply the framework on data covering Denmark and show that large trees (stem diameter >10 cm) can be identified with a low bias (12.5%) and that trees outside forests contribute to 30% of the total tree cover, which is typically unrecognized in national inventories. The bias is high (46.6%) when our results are evaluated against all trees taller than 1.3 m, which involve undetectable small or understory trees. Furthermore, we demonstrate that only marginal effort is needed to transfer our framework to data from Finland, despite markedly dissimilar data sources. Our work lays the foundation for digitalized national databases, where large trees are spatially traceable and manageable.
Collapse
Affiliation(s)
- Sizhuo Li
- To whom correspondence should be addressed: ;
| | | | - Rasmus Fensholt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen 1350, Denmark
| | - Ankit Kariryaa
- Department of Computer Science, University of Copenhagen, Copenhagen 2100, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen 2100, Denmark
| | - Fabian Gieseke
- Department of Computer Science, University of Copenhagen, Copenhagen 2100, Denmark
- Department of Information Systems, University of Münster, Münster 48149, Germany
| | - Thomas Nord-Larsen
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen 1350, Denmark
| | - Stefan Oehmcke
- Department of Computer Science, University of Copenhagen, Copenhagen 2100, Denmark
| | - Ask Holm Carlsen
- Department of Earth Observations, The Danish Agency for Data Supply and Infrastructure, Copenhagen 2400, Denmark
| | - Samuli Junttila
- Department of Forest Sciences, University of Eastern Finland, Joensuu 80101, Finland
| | - Xiaoye Tong
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen 1350, Denmark
| | | | | |
Collapse
|
5
|
Tucker C, Brandt M, Hiernaux P, Kariryaa A, Rasmussen K, Small J, Igel C, Reiner F, Melocik K, Meyer J, Sinno S, Romero E, Glennie E, Fitts Y, Morin A, Pinzon J, McClain D, Morin P, Porter C, Loeffler S, Kergoat L, Issoufou BA, Savadogo P, Wigneron JP, Poulter B, Ciais P, Kaufmann R, Myneni R, Saatchi S, Fensholt R. Sub-continental-scale carbon stocks of individual trees in African drylands. Nature 2023; 615:80-86. [PMID: 36859581 PMCID: PMC9977681 DOI: 10.1038/s41586-022-05653-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2021] [Accepted: 12/13/2022] [Indexed: 03/03/2023]
Abstract
The distribution of dryland trees and their density, cover, size, mass and carbon content are not well known at sub-continental to continental scales1-14. This information is important for ecological protection, carbon accounting, climate mitigation and restoration efforts of dryland ecosystems15-18. We assessed more than 9.9 billion trees derived from more than 300,000 satellite images, covering semi-arid sub-Saharan Africa north of the Equator. We attributed wood, foliage and root carbon to every tree in the 0-1,000 mm year-1 rainfall zone by coupling field data19, machine learning20-22, satellite data and high-performance computing. Average carbon stocks of individual trees ranged from 0.54 Mg C ha-1 and 63 kg C tree-1 in the arid zone to 3.7 Mg C ha-1 and 98 kg tree-1 in the sub-humid zone. Overall, we estimated the total carbon for our study area to be 0.84 (±19.8%) Pg C. Comparisons with 14 previous TRENDY numerical simulation studies23 for our area found that the density and carbon stocks of scattered trees have been underestimated by three models and overestimated by 11 models, respectively. This benchmarking can help understand the carbon cycle and address concerns about land degradation24-29. We make available a linked database of wood mass, foliage mass, root mass and carbon stock of each tree for scientists, policymakers, dryland-restoration practitioners and farmers, who can use it to estimate farmland tree carbon stocks from tablets or laptops.
Collapse
Affiliation(s)
- Compton Tucker
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA.
| | - Martin Brandt
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark.
| | - Pierre Hiernaux
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.
- Pastoralisme Conseil, Caylus, France.
| | - Ankit Kariryaa
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Kjeld Rasmussen
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Jennifer Small
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Florian Reiner
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Katherine Melocik
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Jesse Meyer
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Scott Sinno
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Eric Romero
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Erin Glennie
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Yasmin Fitts
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - August Morin
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Jorge Pinzon
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Devin McClain
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- Science Systems and Applications, Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Paul Morin
- Learning and Environmental Sciences, University of Minnesota, Saint Paul, MN, USA
| | - Claire Porter
- Learning and Environmental Sciences, University of Minnesota, Saint Paul, MN, USA
| | - Shane Loeffler
- Learning and Environmental Sciences, University of Minnesota, Saint Paul, MN, USA
| | - Laurent Kergoat
- Géosciences Environnement Toulouse, Observatoire Midi-Pyrénées, UMR 5563 (CNRS/UPS/IRD/CNES), Toulouse, France
| | | | | | | | - Benjamin Poulter
- Earth Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Philippe Ciais
- Laboratoire des Sciences du Climat et de l'Environnement, CEA-CNRS-UVSQ, CE Orme des Merisiers, Gif sur Yvette, France
| | - Robert Kaufmann
- Department of Earth & Environment, Boston University, Boston, MA, USA
| | - Ranga Myneni
- Department of Earth & Environment, Boston University, Boston, MA, USA
| | - Sassan Saatchi
- Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA
| | - Rasmus Fensholt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
6
|
Bilic P, Christ P, Li HB, Vorontsov E, Ben-Cohen A, Kaissis G, Szeskin A, Jacobs C, Mamani GEH, Chartrand G, Lohöfer F, Holch JW, Sommer W, Hofmann F, Hostettler A, Lev-Cohain N, Drozdzal M, Amitai MM, Vivanti R, Sosna J, Ezhov I, Sekuboyina A, Navarro F, Kofler F, Paetzold JC, Shit S, Hu X, Lipková J, Rempfler M, Piraud M, Kirschke J, Wiestler B, Zhang Z, Hülsemeyer C, Beetz M, Ettlinger F, Antonelli M, Bae W, Bellver M, Bi L, Chen H, Chlebus G, Dam EB, Dou Q, Fu CW, Georgescu B, Giró-I-Nieto X, Gruen F, Han X, Heng PA, Hesser J, Moltz JH, Igel C, Isensee F, Jäger P, Jia F, Kaluva KC, Khened M, Kim I, Kim JH, Kim S, Kohl S, Konopczynski T, Kori A, Krishnamurthi G, Li F, Li H, Li J, Li X, Lowengrub J, Ma J, Maier-Hein K, Maninis KK, Meine H, Merhof D, Pai A, Perslev M, Petersen J, Pont-Tuset J, Qi J, Qi X, Rippel O, Roth K, Sarasua I, Schenk A, Shen Z, Torres J, Wachinger C, Wang C, Weninger L, Wu J, Xu D, Yang X, Yu SCH, Yuan Y, Yue M, Zhang L, Cardoso J, Bakas S, Braren R, Heinemann V, Pal C, Tang A, Kadoury S, Soler L, van Ginneken B, Greenspan H, Joskowicz L, Menze B. The Liver Tumor Segmentation Benchmark (LiTS). Med Image Anal 2023; 84:102680. [PMID: 36481607 PMCID: PMC10631490 DOI: 10.1016/j.media.2022.102680] [Citation(s) in RCA: 61] [Impact Index Per Article: 61.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2021] [Revised: 09/27/2022] [Accepted: 10/29/2022] [Indexed: 11/18/2022]
Abstract
In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.
Collapse
Affiliation(s)
- Patrick Bilic
- Department of Informatics, Technical University of Munich, Germany
| | - Patrick Christ
- Department of Informatics, Technical University of Munich, Germany
| | - Hongwei Bran Li
- Department of Informatics, Technical University of Munich, Germany; Department of Quantitative Biomedicine, University of Zurich, Switzerland.
| | | | - Avi Ben-Cohen
- Department of Biomedical Engineering, Tel-Aviv University, Israel
| | - Georgios Kaissis
- Institute for AI in Medicine, Technical University of Munich, Germany; Institute for diagnostic and interventional radiology, Klinikum rechts der Isar, Technical University of Munich, Germany; Department of Computing, Imperial College London, London, United Kingdom
| | - Adi Szeskin
- School of Computer Science and Engineering, the Hebrew University of Jerusalem, Israel
| | - Colin Jacobs
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | | | - Gabriel Chartrand
- The University of Montréal Hospital Research Centre (CRCHUM) Montréal, Québec, Canada
| | - Fabian Lohöfer
- Institute for diagnostic and interventional radiology, Klinikum rechts der Isar, Technical University of Munich, Germany
| | - Julian Walter Holch
- Department of Medicine III, University Hospital, LMU Munich, Munich, Germany; Comprehensive Cancer Center Munich, Munich, Germany; Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Wieland Sommer
- Department of Radiology, University Hospital, LMU Munich, Germany
| | - Felix Hofmann
- Department of General, Visceral and Transplantation Surgery, University Hospital, LMU Munich, Germany; Department of Radiology, University Hospital, LMU Munich, Germany
| | - Alexandre Hostettler
- Department of Surgical Data Science, Institut de Recherche contre les Cancers de l'Appareil Digestif (IRCAD), France
| | - Naama Lev-Cohain
- Department of Radiology, Hadassah University Medical Center, Jerusalem, Israel
| | | | | | | | - Jacob Sosna
- Department of Radiology, Hadassah University Medical Center, Jerusalem, Israel
| | - Ivan Ezhov
- Department of Informatics, Technical University of Munich, Germany
| | - Anjany Sekuboyina
- Department of Informatics, Technical University of Munich, Germany; Department of Quantitative Biomedicine, University of Zurich, Switzerland
| | - Fernando Navarro
- Department of Informatics, Technical University of Munich, Germany; Department of Radiation Oncology and Radiotherapy, Klinikum rechts der Isar, Technical University of Munich, Germany; TranslaTUM - Central Institute for Translational Cancer Research, Technical University of Munich, Germany
| | - Florian Kofler
- Department of Informatics, Technical University of Munich, Germany; Institute for diagnostic and interventional neuroradiology, Klinikum rechts der Isar,Technical University of Munich, Germany; Helmholtz AI, Helmholtz Zentrum München, Neuherberg, Germany; TranslaTUM - Central Institute for Translational Cancer Research, Technical University of Munich, Germany
| | - Johannes C Paetzold
- Department of Computing, Imperial College London, London, United Kingdom; Institute for Tissue Engineering and Regenerative Medicine, Helmholtz Zentrum München, Neuherberg, Germany
| | - Suprosanna Shit
- Department of Informatics, Technical University of Munich, Germany
| | - Xiaobin Hu
- Department of Informatics, Technical University of Munich, Germany
| | - Jana Lipková
- Brigham and Women's Hospital, Harvard Medical School, USA
| | - Markus Rempfler
- Department of Informatics, Technical University of Munich, Germany
| | - Marie Piraud
- Department of Informatics, Technical University of Munich, Germany; Helmholtz AI, Helmholtz Zentrum München, Neuherberg, Germany
| | - Jan Kirschke
- Institute for diagnostic and interventional neuroradiology, Klinikum rechts der Isar,Technical University of Munich, Germany
| | - Benedikt Wiestler
- Institute for diagnostic and interventional neuroradiology, Klinikum rechts der Isar,Technical University of Munich, Germany
| | - Zhiheng Zhang
- Department of Hepatobiliary Surgery, the Affiliated Drum Tower Hospital of Nanjing University Medical School, China
| | | | - Marcel Beetz
- Department of Informatics, Technical University of Munich, Germany
| | | | - Michela Antonelli
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK
| | | | | | - Lei Bi
- School of Computer Science, the University of Sydney, Australia
| | - Hao Chen
- Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, China
| | - Grzegorz Chlebus
- Fraunhofer MEVIS, Bremen, Germany; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Erik B Dam
- Department of Computer Science, University of Copenhagen, Denmark
| | - Qi Dou
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Chi-Wing Fu
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | | | - Xavier Giró-I-Nieto
- Signal Theory and Communications Department, Universitat Politecnica de Catalunya, Catalonia, Spain
| | - Felix Gruen
- Institute of Control Engineering, Technische Universität Braunschweig, Germany
| | - Xu Han
- Department of computer science, UNC Chapel Hill, USA
| | - Pheng-Ann Heng
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Jürgen Hesser
- Mannheim Institute for Intelligent Systems in Medicine, department of Medicine Mannheim, Heidelberg University, Germany; Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Germany; Central Institute for Computer Engineering (ZITI), Heidelberg University, Germany
| | | | - Christian Igel
- Department of Computer Science, University of Copenhagen, Denmark
| | - Fabian Isensee
- Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany; Helmholtz Imaging, Germany
| | - Paul Jäger
- Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany; Helmholtz Imaging, Germany
| | - Fucang Jia
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China
| | - Krishna Chaitanya Kaluva
- Medical Imaging and Reconstruction Lab, Department of Engineering Design, Indian Institute of Technology Madras, India
| | - Mahendra Khened
- Medical Imaging and Reconstruction Lab, Department of Engineering Design, Indian Institute of Technology Madras, India
| | | | - Jae-Hun Kim
- Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, South Korea
| | | | - Simon Kohl
- Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Tomasz Konopczynski
- Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Germany
| | - Avinash Kori
- Medical Imaging and Reconstruction Lab, Department of Engineering Design, Indian Institute of Technology Madras, India
| | - Ganapathy Krishnamurthi
- Medical Imaging and Reconstruction Lab, Department of Engineering Design, Indian Institute of Technology Madras, India
| | - Fan Li
- Sensetime, Shanghai, China
| | - Hongchao Li
- Department of Computer Science, Guangdong University of Foreign Studies, China
| | - Junbo Li
- Philips Research China, Philips China Innovation Campus, Shanghai, China
| | - Xiaomeng Li
- Department of Electrical and Electronic Engineering, The University of Hong Kong, China
| | - John Lowengrub
- Departments of Mathematics, Biomedical Engineering, University of California, Irvine, USA; Center for Complex Biological Systems, University of California, Irvine, USA; Chao Family Comprehensive Cancer Center, University of California, Irvine, USA
| | - Jun Ma
- Department of Mathematics, Nanjing University of Science and Technology, China
| | - Klaus Maier-Hein
- Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany; Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany; Helmholtz Imaging, Germany
| | | | - Hans Meine
- Fraunhofer MEVIS, Bremen, Germany; Medical Image Computing Group, FB3, University of Bremen, Germany
| | - Dorit Merhof
- Institute of Imaging & Computer Vision, RWTH Aachen University, Germany
| | - Akshay Pai
- Department of Computer Science, University of Copenhagen, Denmark
| | - Mathias Perslev
- Department of Computer Science, University of Copenhagen, Denmark
| | - Jens Petersen
- Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Jordi Pont-Tuset
- Eidgenössische Technische Hochschule Zurich (ETHZ), Zurich, Switzerland
| | - Jin Qi
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, China
| | - Xiaojuan Qi
- Department of Electrical and Electronic Engineering, The University of Hong Kong, China
| | - Oliver Rippel
- Institute of Imaging & Computer Vision, RWTH Aachen University, Germany
| | | | - Ignacio Sarasua
- Institute for diagnostic and interventional radiology, Klinikum rechts der Isar, Technical University of Munich, Germany; Department of Child and Adolescent Psychiatry, Ludwig-Maximilians-Universität, Munich, Germany
| | - Andrea Schenk
- Fraunhofer MEVIS, Bremen, Germany; Institute for Diagnostic and Interventional Radiology, Hannover Medical School, Hannover, Germany
| | - Zengming Shen
- Beckman Institute, University of Illinois at Urbana-Champaign, USA; Siemens Healthineers, USA
| | - Jordi Torres
- Barcelona Supercomputing Center, Barcelona, Spain; Universitat Politecnica de Catalunya, Catalonia, Spain
| | - Christian Wachinger
- Department of Informatics, Technical University of Munich, Germany; Institute for diagnostic and interventional radiology, Klinikum rechts der Isar, Technical University of Munich, Germany; Department of Child and Adolescent Psychiatry, Ludwig-Maximilians-Universität, Munich, Germany
| | - Chunliang Wang
- Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Sweden
| | - Leon Weninger
- Institute of Imaging & Computer Vision, RWTH Aachen University, Germany
| | - Jianrong Wu
- Tencent Healthcare (Shenzhen) Co., Ltd, China
| | | | - Xiaoping Yang
- Department of Mathematics, Nanjing University, China
| | - Simon Chun-Ho Yu
- Department of Imaging and Interventional Radiology, Chinese University of Hong Kong, Hong Kong, China
| | - Yading Yuan
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, NY, USA
| | - Miao Yue
- CGG Services (Singapore) Pte. Ltd., Singapore
| | - Liping Zhang
- Department of Imaging and Interventional Radiology, Chinese University of Hong Kong, Hong Kong, China
| | - Jorge Cardoso
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK
| | - Spyridon Bakas
- Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, PA, USA; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, USA; Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, PA, USA
| | - Rickmer Braren
- German Cancer Consortium (DKTK), Germany; Institute for diagnostic and interventional radiology, Klinikum rechts der Isar, Technical University of Munich, Germany; Comprehensive Cancer Center Munich, Munich, Germany
| | - Volker Heinemann
- Department of Hematology/Oncology & Comprehensive Cancer Center Munich, LMU Klinikum Munich, Germany
| | | | - An Tang
- Department of Radiology, Radiation Oncology and Nuclear Medicine, University of Montréal, Canada
| | | | - Luc Soler
- Department of Surgical Data Science, Institut de Recherche contre les Cancers de l'Appareil Digestif (IRCAD), France
| | - Bram van Ginneken
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Hayit Greenspan
- Department of Biomedical Engineering, Tel-Aviv University, Israel
| | - Leo Joskowicz
- School of Computer Science and Engineering, the Hebrew University of Jerusalem, Israel
| | - Bjoern Menze
- Department of Informatics, Technical University of Munich, Germany; Department of Quantitative Biomedicine, University of Zurich, Switzerland
| |
Collapse
|
7
|
Mugabowindekwe M, Brandt M, Chave J, Reiner F, Skole DL, Kariryaa A, Igel C, Hiernaux P, Ciais P, Mertz O, Tong X, Li S, Rwanyiziri G, Dushimiyimana T, Ndoli A, Uwizeyimana V, Lillesø JPB, Gieseke F, Tucker CJ, Saatchi S, Fensholt R. Nation-wide mapping of tree-level aboveground carbon stocks in Rwanda. Nat Clim Chang 2022; 13:91-97. [PMID: 36684409 PMCID: PMC9845119 DOI: 10.1038/s41558-022-01544-w] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/08/2022] [Accepted: 10/31/2022] [Indexed: 06/17/2023]
Abstract
Trees sustain livelihoods and mitigate climate change but a predominance of trees outside forests and limited resources make it difficult for many tropical countries to conduct automated nation-wide inventories. Here, we propose an approach to map the carbon stock of each individual overstory tree at the national scale of Rwanda using aerial imagery from 2008 and deep learning. We show that 72% of the mapped trees are located in farmlands and savannas and 17% in plantations, accounting for 48.6% of the national aboveground carbon stocks. Natural forests cover 11% of the total tree count and 51.4% of the national carbon stocks, with an overall carbon stock uncertainty of 16.9%. The mapping of all trees allows partitioning to any landscapes classification and is urgently needed for effective planning and monitoring of restoration activities as well as for optimization of carbon sequestration, biodiversity and economic benefits of trees.
Collapse
Affiliation(s)
- Maurice Mugabowindekwe
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
- Centre for Geographic Information Systems and Remote Sensing, College of Science and Technology, University of Rwanda, Kigali, Rwanda
| | - Martin Brandt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Jérôme Chave
- Laboratoire Evolution et Diversité Biologique, CNRS, UPS, IRD, Université Paul Sabatier, Toulouse, France
| | - Florian Reiner
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - David L. Skole
- Global Observatory for Ecosystem Services, Department of Forestry, Michigan State University, East Lansing, MI USA
| | - Ankit Kariryaa
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | | | - Philippe Ciais
- Laboratoire des Sciences du Climat et de l’Environnement, CEA/CNRS/UVSQ/Université Paris Saclay, Gif-sur-Yvette, France
| | - Ole Mertz
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Xiaoye Tong
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Sizhuo Li
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
- Université Paris Saclay, Gif-sur-Yvette, France
| | - Gaspard Rwanyiziri
- Centre for Geographic Information Systems and Remote Sensing, College of Science and Technology, University of Rwanda, Kigali, Rwanda
- Department of Geography and Urban Planning, College of Science and Technology, University of Rwanda, Kigali, Rwanda
| | - Thaulin Dushimiyimana
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Alain Ndoli
- International Union for Conservation of Nature—Eastern and Southern Africa Region, Kigali, Rwanda
| | - Valens Uwizeyimana
- General Directorate of Land, Water, and Forestry, Ministry of Environment, Kigali, Rwanda
- Division of Forest, Nature and Landscape, Department of Earth and Environmental Sciences, KU Leuven, Leuven, Belgium
| | | | - Fabian Gieseke
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
- Department of Information Systems, University of Münster, Münster, Germany
| | - Compton J. Tucker
- Earth Sciences Division, NASA Goddard Space Flight Center, Greenbelt, MD USA
| | - Sassan Saatchi
- Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA USA
| | - Rasmus Fensholt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
8
|
Perslev M, Pai A, Runhaar J, Igel C, Dam EB. Cross-Cohort Automatic Knee MRI Segmentation With Multi-Planar U-Nets. J Magn Reson Imaging 2021; 55:1650-1663. [PMID: 34918423 PMCID: PMC9106804 DOI: 10.1002/jmri.27978] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2021] [Revised: 10/18/2021] [Accepted: 10/20/2021] [Indexed: 12/16/2022] Open
Abstract
Background Segmentation of medical image volumes is a time‐consuming manual task. Automatic tools are often tailored toward specific patient cohorts, and it is unclear how they behave in other clinical settings. Purpose To evaluate the performance of the open‐source Multi‐Planar U‐Net (MPUnet), the validated Knee Imaging Quantification (KIQ) framework, and a state‐of‐the‐art two‐dimensional (2D) U‐Net architecture on three clinical cohorts without extensive adaptation of the algorithms. Study Type Retrospective cohort study. Subjects A total of 253 subjects (146 females, 107 males, ages 57 ± 12 years) from three knee osteoarthritis (OA) studies (Center for Clinical and Basic Research [CCBR], Osteoarthritis Initiative [OAI], and Prevention of OA in Overweight Females [PROOF]) with varying demographics and OA severity (64/37/24/53/2 scans of Kellgren and Lawrence [KL] grades 0–4). Field Strength/Sequence 0.18 T, 1.0 T/1.5 T, and 3 T sagittal three‐dimensional fast‐spin echo T1w and dual‐echo steady‐state sequences. Assessment All models were fit without tuning to knee magnetic resonance imaging (MRI) scans with manual segmentations from three clinical cohorts. All models were evaluated across KL grades. Statistical Tests Segmentation performance differences as measured by Dice coefficients were tested with paired, two‐sided Wilcoxon signed‐rank statistics with significance threshold α = 0.05. Results The MPUnet performed superior or equal to KIQ and 2D U‐Net on all compartments across three cohorts. Mean Dice overlap was significantly higher for MPUnet compared to KIQ and U‐Net on CCBR (0.83±0.04 vs. 0.81±0.06 and 0.82±0.05), significantly higher than KIQ and U‐Net OAI (0.86±0.03 vs. 0.84±0.04 and 0.85±0.03), and not significantly different from KIQ while significantly higher than 2D U‐Net on PROOF (0.78±0.07 vs. 0.77±0.07, P=0.10, and 0.73±0.07). The MPUnet performed significantly better on N=22 KL grade 3 CCBR scans with 0.78±0.06 vs. 0.75±0.08 for KIQ and 0.76±0.06 for 2D U‐Net. Data Conclusion The MPUnet matched or exceeded the performance of state‐of‐the‐art knee MRI segmentation models across cohorts of variable sequences and patient demographics. The MPUnet required no manual tuning making it both accurate and easy‐to‐use. Level of Evidence 3 Technical Efficacy Stage 2
Collapse
Affiliation(s)
- Mathias Perslev
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Akshay Pai
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,Cerebriu A/S, Copenhagen, Denmark
| | | | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Erik B Dam
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,Cerebriu A/S, Copenhagen, Denmark
| |
Collapse
|
9
|
Lorenzen SS, Nielsen M, Jimenez-Solem E, Petersen TS, Perner A, Thorsen-Meyer HC, Igel C, Sillesen M. Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark. Sci Rep 2021; 11:18959. [PMID: 34556789 PMCID: PMC8460747 DOI: 10.1038/s41598-021-98617-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Accepted: 09/08/2021] [Indexed: 11/16/2022] Open
Abstract
The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.
Collapse
Affiliation(s)
| | - Mads Nielsen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Espen Jimenez-Solem
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg, Copenhagen, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology, Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Tonny Studsgaard Petersen
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg, Copenhagen, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Anders Perner
- Department of Intensive Care, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | | | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Martin Sillesen
- Department of Surgical Gastroenterology, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark.
- Center for Surgical Translational and Artificial Intelligence Research (CSTAR), Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark.
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.
| |
Collapse
|
10
|
Igel C. Data, Knowledge, and Computation. Künstl Intell 2021. [DOI: 10.1007/s13218-021-00739-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
11
|
Desai AD, Caliva F, Iriondo C, Mortazi A, Jambawalikar S, Bagci U, Perslev M, Igel C, Dam EB, Gaj S, Yang M, Li X, Deniz CM, Juras V, Regatte R, Gold GE, Hargreaves BA, Pedoia V, Chaudhari AS. The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset. Radiol Artif Intell 2021; 3:e200078. [PMID: 34235438 PMCID: PMC8231759 DOI: 10.1148/ryai.2021200078] [Citation(s) in RCA: 38] [Impact Index Per Article: 12.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2020] [Revised: 01/08/2021] [Accepted: 01/25/2021] [Indexed: 02/05/2023]
Abstract
PURPOSE To organize a multi-institute knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic segmentation methods relevant for monitoring osteoarthritis progression. MATERIALS AND METHODS A dataset partition consisting of three-dimensional knee MRI from 88 retrospective patients at two time points (baseline and 1-year follow-up) with ground truth articular (femoral, tibial, and patellar) cartilage and meniscus segmentations was standardized. Challenge submissions and a majority-vote ensemble were evaluated against ground truth segmentations using Dice score, average symmetric surface distance, volumetric overlap error, and coefficient of variation on a holdout test set. Similarities in automated segmentations were measured using pairwise Dice coefficient correlations. Articular cartilage thickness was computed longitudinally and with scans. Correlation between thickness error and segmentation metrics was measured using the Pearson correlation coefficient. Two empirical upper bounds for ensemble performance were computed using combinations of model outputs that consolidated true positives and true negatives. RESULTS Six teams (T 1-T 6) submitted entries for the challenge. No differences were observed across any segmentation metrics for any tissues (P = .99) among the four top-performing networks (T 2, T 3, T 4, T 6). Dice coefficient correlations between network pairs were high (> 0.85). Per-scan thickness errors were negligible among networks T 1-T 4 (P = .99), and longitudinal changes showed minimal bias (< 0.03 mm). Low correlations (ρ < 0.41) were observed between segmentation metrics and thickness error. The majority-vote ensemble was comparable to top-performing networks (P = .99). Empirical upper-bound performances were similar for both combinations (P = .99). CONCLUSION Diverse networks learned to segment the knee similarly, where high segmentation accuracy did not correlate with cartilage thickness accuracy and voting ensembles did not exceed individual network performance.See also the commentary by Elhalawani and Mak in this issue.Keywords: Cartilage, Knee, MR-Imaging, Segmentation © RSNA, 2020Supplemental material is available for this article.
Collapse
Affiliation(s)
- Arjun D. Desai
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Francesco Caliva
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Claudia Iriondo
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Aliasghar Mortazi
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Sachin Jambawalikar
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Ulas Bagci
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Mathias Perslev
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Christian Igel
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Erik B. Dam
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Sibaji Gaj
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Mingrui Yang
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Xiaojuan Li
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Cem M. Deniz
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Vladimir Juras
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Ravinder Regatte
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Garry E. Gold
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Brian A. Hargreaves
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Valentina Pedoia
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - Akshay S. Chaudhari
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| | - on behalf of the IWOAI Segmentation Challenge Writing Group
- From the Departments of Radiology (A.D.D., G.E.G., B.A.H., A.S.C.)
and Electrical Engineering (A.D.D., B.A.H.), Stanford University, Lucas Center
for Imaging, 1201 Welch Rd, PS 055B, Stanford, CA 94305; Department of
Radiology, University of California, San Francisco, San Francisco, Calif (F.C.,
C. Iriondo, V.P.); Berkeley Joint Graduate Group in Bioengineering, University
of California, Berkeley, Berkeley, Calif (C. Iriondo); Department of Computer
Science, University of Central Florida, Orlando, Fla (A.M., U.B.); Department of
Radiology, Northwestern University, Chicago, Ill (U.B.); Department of
Radiology, Columbia University, New York, NY (S.J.); Department of Computer
Science, University of Copenhagen, Copenhagen, Denmark (M.P., C. Igel, E.B.D.);
Department of Biomedical Engineering, Cleveland Clinic, Cleveland, Ohio (S.G.,
M.Y., X.L.); Department of Radiology, New York University Langone Health, New
York, NY (C.M.D., R.R.); and Department of Biomedical Imaging and Image-guided
Therapy, High-Field MR Centre, Medical University of Vienna, Vienna, Austria
(V.J.)
| |
Collapse
|
12
|
Abstract
Sleep disorders affect a large portion of the global population and are strong predictors of morbidity and all-cause mortality. Sleep staging segments a period of sleep into a sequence of phases providing the basis for most clinical decisions in sleep medicine. Manual sleep staging is difficult and time-consuming as experts must evaluate hours of polysomnography (PSG) recordings with electroencephalography (EEG) and electrooculography (EOG) data for each patient. Here, we present U-Sleep, a publicly available, ready-to-use deep-learning-based system for automated sleep staging ( sleep.ai.ku.dk ). U-Sleep is a fully convolutional neural network, which was trained and evaluated on PSG recordings from 15,660 participants of 16 clinical studies. It provides accurate segmentations across a wide range of patient cohorts and PSG protocols not considered when building the system. U-Sleep works for arbitrary combinations of typical EEG and EOG channels, and its special deep learning architecture can label sleep stages at shorter intervals than the typical 30 s periods used during training. We show that these labels can provide additional diagnostic information and lead to new ways of analyzing sleep. U-Sleep performs on par with state-of-the-art automatic sleep staging systems on multiple clinical datasets, even if the other systems were built specifically for the particular data. A comparison with consensus-scores from a previously unseen clinic shows that U-Sleep performs as accurately as the best of the human experts. U-Sleep can support the sleep staging workflow of medical experts, which decreases healthcare costs, and can provide highly accurate segmentations when human expertize is lacking.
Collapse
Affiliation(s)
- Mathias Perslev
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Sune Darkner
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Lykke Kempfner
- Danish Center for Sleep Medicine, Rigshospitalet, Copenhagen, Denmark
| | - Miki Nikolic
- Danish Center for Sleep Medicine, Rigshospitalet, Copenhagen, Denmark
| | | | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
| |
Collapse
|
13
|
Jimenez-Solem E, Petersen TS, Hansen C, Hansen C, Lioma C, Igel C, Boomsma W, Krause O, Lorenzen S, Selvan R, Petersen J, Nyeland ME, Ankarfeldt MZ, Virenfeldt GM, Winther-Jensen M, Linneberg A, Ghazi MM, Detlefsen N, Lauritzen AD, Smith AG, de Bruijne M, Ibragimov B, Petersen J, Lillholm M, Middleton J, Mogensen SH, Thorsen-Meyer HC, Perner A, Helleberg M, Kaas-Hansen BS, Bonde M, Bonde A, Pai A, Nielsen M, Sillesen M. Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients. Sci Rep 2021; 11:3246. [PMID: 33547335 PMCID: PMC7864944 DOI: 10.1038/s41598-021-81844-x] [Citation(s) in RCA: 45] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2020] [Accepted: 01/12/2021] [Indexed: 12/15/2022] Open
Abstract
Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics—Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.
Collapse
Affiliation(s)
- Espen Jimenez-Solem
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.,Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology and Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Tonny S Petersen
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Casper Hansen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Christian Hansen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Christina Lioma
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Wouter Boomsma
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Oswin Krause
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Stephan Lorenzen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Raghavendra Selvan
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Janne Petersen
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Section of Biostatistics, Department of Public Health, University of Copenhagen, Copenhagen, Denmark.,Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology and Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Martin Erik Nyeland
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Mikkel Zöllner Ankarfeldt
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology and Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Gert Mehl Virenfeldt
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Matilde Winther-Jensen
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Allan Linneberg
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | | | - Nicki Detlefsen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,DTU Compute, Denmarks Technical University, Lyngby, Denmark
| | | | | | - Marleen de Bruijne
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,Department of Radiology and Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Bulat Ibragimov
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Jens Petersen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Martin Lillholm
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Jon Middleton
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | | | | | - Anders Perner
- Department of Intensive Care Medicine, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Marie Helleberg
- Department of Infectious Diseases, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | | | - Mikkel Bonde
- Center for Surgical Translational and Artificial Intelligence Research (CSTAR), Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Alexander Bonde
- Department of Surgical Gastroenterology, Copenhagen University Hospital, Rigshospitalet, Blegdamsvej 9, 2100, Copenhagen Ø, Denmark.,Center for Surgical Translational and Artificial Intelligence Research (CSTAR), Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Akshay Pai
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,Cerebriu A/S, Copenhagen, Denmark
| | - Mads Nielsen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Martin Sillesen
- Department of Surgical Gastroenterology, Copenhagen University Hospital, Rigshospitalet, Blegdamsvej 9, 2100, Copenhagen Ø, Denmark. .,Center for Surgical Translational and Artificial Intelligence Research (CSTAR), Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark. .,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.
| |
Collapse
|
14
|
Brandt M, Tucker CJ, Kariryaa A, Rasmussen K, Abel C, Small J, Chave J, Rasmussen LV, Hiernaux P, Diouf AA, Kergoat L, Mertz O, Igel C, Gieseke F, Schöning J, Li S, Melocik K, Meyer J, Sinno S, Romero E, Glennie E, Montagu A, Dendoncker M, Fensholt R. An unexpectedly large count of trees in the West African Sahara and Sahel. Nature 2020; 587:78-82. [PMID: 33057199 DOI: 10.1038/s41586-020-2824-5] [Citation(s) in RCA: 64] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2019] [Accepted: 09/09/2020] [Indexed: 11/09/2022]
Abstract
A large proportion of dryland trees and shrubs (hereafter referred to collectively as trees) grow in isolation, without canopy closure. These non-forest trees have a crucial role in biodiversity, and provide ecosystem services such as carbon storage, food resources and shelter for humans and animals1,2. However, most public interest relating to trees is devoted to forests, and trees outside of forests are not well-documented3. Here we map the crown size of each tree more than 3 m2 in size over a land area that spans 1.3 million km2 in the West African Sahara, Sahel and sub-humid zone, using submetre-resolution satellite imagery and deep learning4. We detected over 1.8 billion individual trees (13.4 trees per hectare), with a median crown size of 12 m2, along a rainfall gradient from 0 to 1,000 mm per year. The canopy cover increases from 0.1% (0.7 trees per hectare) in hyper-arid areas, through 1.6% (9.9 trees per hectare) in arid and 5.6% (30.1 trees per hectare) in semi-arid zones, to 13.3% (47 trees per hectare) in sub-humid areas. Although the overall canopy cover is low, the relatively high density of isolated trees challenges prevailing narratives about dryland desertification5-7, and even the desert shows a surprisingly high tree density. Our assessment suggests a way to monitor trees outside of forests globally, and to explore their role in mitigating degradation, climate change and poverty.
Collapse
Affiliation(s)
- Martin Brandt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark. .,Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.
| | | | - Ankit Kariryaa
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,HCI Group, University of Bremen, Bremen, Germany
| | - Kjeld Rasmussen
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Christin Abel
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Jennifer Small
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Jerome Chave
- Laboratoire Evolution and Diversité Biologique, CNRS, UPS, IRD, Université Paul Sabatier, Toulouse, France
| | - Laura Vang Rasmussen
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Pierre Hiernaux
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,Pastoralisme Conseil, Caylus, France
| | | | - Laurent Kergoat
- Geosciences Environnement Toulouse (GET), Observatoire Midi-Pyrénées, UMR 5563 (CNRS/UPS/IRD/CNES), Toulouse, France
| | - Ole Mertz
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Christian Igel
- Department of Computer Science (DIKU), University of Copenhagen, Copenhagen, Denmark
| | - Fabian Gieseke
- Department of Computer Science (DIKU), University of Copenhagen, Copenhagen, Denmark.,Department of Information Systems, University of Műnster, Műnster, Germany
| | | | - Sizhuo Li
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| | - Katherine Melocik
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Jesse Meyer
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Scott Sinno
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Eric Romero
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Erin Glennie
- Science Systems and Applications Inc., NASA Goddard Space Flight Center, Greenbelt, MD, USA.,NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - Amandine Montagu
- Département de Géosciences, Ecole Normale Supérieure, Paris, France
| | - Morgane Dendoncker
- Earth and Life Institute, Environmental Sciences, Université Catholique de Louvain, Louvain-la-Neuve, Belgium
| | - Rasmus Fensholt
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
15
|
|
16
|
Shakibfar S, Krause O, Lund-Andersen C, Strycko F, Moll J, Osman Andersen T, Høgh Petersen H, Hastrup Svendsen J, Igel C. Impact of device programming on the success of the first anti-tachycardia pacing therapy: An anonymized large-scale study. PLoS One 2019; 14:e0219533. [PMID: 31393871 PMCID: PMC6687124 DOI: 10.1371/journal.pone.0219533] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2018] [Accepted: 06/27/2019] [Indexed: 12/21/2022] Open
Abstract
Background Antitachycardia pacing (ATP) is an effective treatment for ventricular tachycardia (VT). We evaluated the efficacy of different ATP programs based on a large remote monitoring data set from patients with implantable cardioverter-defibrillators (ICDs). Methods A dataset from 18,679 ICD patients was used to evaluate the first delivered ATP treatment. We considered all device programs that were used for at least 50 patients, leaving us with 7 different programs and a total of 32,045 episodes. We used the two-proportions z-test (α = 0.01) to compare the probability of success and the probability for acceleration in each group with the corresponding values of the default setting. Results Overall, the first ATP treatment terminated in 78.4%–97.5% of episodes with slow VT and 81.5%–91.1% of episodes with fast VT. The default setting of the ATP programs with the number of sequences S = 3 was applied to treat 30.1% of the slow and 36.6% of the fast episodes. Reducing the maximum number of sequences to S = 2 decreased the success rate for slow VT (P < 0.0001, h = 0.38), while the setting S = 4 resulted in the highest success rate of 97.5% (P < 0.0001, h = 0.27). Conclusion While the default programs performed well, we found that increasing the number of sequences from 3 to 4 was a promising option to improve the overall ATP performance.
Collapse
Affiliation(s)
- Saeed Shakibfar
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Oswin Krause
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Casper Lund-Andersen
- Department of Cardiology, The Heart Centre, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Filip Strycko
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Jonas Moll
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | | | - Helen Høgh Petersen
- Department of Cardiology, The Heart Centre, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Jesper Hastrup Svendsen
- Department of Cardiology, The Heart Centre, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
- Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
- * E-mail:
| |
Collapse
|
17
|
Shakibfar S, Krause O, Lund-Andersen C, Aranda A, Moll J, Andersen TO, Svendsen JH, Petersen HH, Igel C. Predicting electrical storms by remote monitoring of implantable cardioverter-defibrillator patients using machine learning. Europace 2019; 21:268-274. [PMID: 30508072 DOI: 10.1093/europace/euy257] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2018] [Accepted: 10/10/2018] [Indexed: 01/06/2023] Open
Abstract
Aims Electrical storm (ES) is a serious arrhythmic syndrome that is characterized by recurrent episodes of ventricular arrhythmias. Electrical storm is associated with increased mortality and morbidity despite the use of implantable cardioverter-defibrillators (ICDs). Predicting ES could be essential; however, models for predicting this event have never been developed. The goal of this study was to construct and validate machine learning models to predict ES based on daily ICD remote monitoring summaries. Methods and results Daily ICD summaries from 19 935 patients were used to construct and evaluate two models [logistic regression (LR) and random forest (RF)] for predicting the short-term risk of ES. The models were evaluated on the parts of the data not used for model development. Random forest performed significantly better than LR (P < 0.01), achieving a test accuracy of 0.96 and an area under the curve (AUC) of 0.80 (vs. an accuracy of 0.96 and an AUC of 0.75). The percentage of ventricular pacing and the daytime activity were the most relevant variables in the RF model. Conclusion The use of large-scale machine learning showed that daily summaries of ICD measurements in the absence of clinical information can predict the short-term risk of ES.
Collapse
Affiliation(s)
- Saeed Shakibfar
- Department of Computer Science, University of Copenhagen, Universitetsparken 5, Copenhagen 2100, Denmark
| | - Oswin Krause
- Department of Computer Science, University of Copenhagen, Universitetsparken 5, Copenhagen 2100, Denmark
| | - Casper Lund-Andersen
- Department of Cardiology, The Heart Centre, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Alfonso Aranda
- Medtronic, Medtronic Bakken Research Center, Maastricht, The Netherlands
| | - Jonas Moll
- Department of Computer Science, University of Copenhagen, Universitetsparken 5, Copenhagen 2100, Denmark
| | - Tariq Osman Andersen
- Department of Computer Science, University of Copenhagen, Universitetsparken 5, Copenhagen 2100, Denmark
| | - Jesper Hastrup Svendsen
- Department of Cardiology, The Heart Centre, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Helen Høgh Petersen
- Department of Cardiology, The Heart Centre, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Universitetsparken 5, Copenhagen 2100, Denmark
| |
Collapse
|
18
|
|
19
|
Gieseke F, Oancea C, Igel C. bufferkdtree: A Python library for massive nearest neighbor queries on multi-many-core devices. Knowl Based Syst 2017. [DOI: 10.1016/j.knosys.2017.01.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
20
|
Sørensen L, Igel C, Pai A, Balas I, Anker C, Lillholm M, Nielsen M. Differential diagnosis of mild cognitive impairment and Alzheimer's disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry. Neuroimage Clin 2016; 13:470-482. [PMID: 28119818 PMCID: PMC5237821 DOI: 10.1016/j.nicl.2016.11.025] [Citation(s) in RCA: 102] [Impact Index Per Article: 12.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/10/2016] [Revised: 10/21/2016] [Accepted: 11/26/2016] [Indexed: 01/01/2023]
Abstract
This paper presents a brain T1-weighted structural magnetic resonance imaging (MRI) biomarker that combines several individual MRI biomarkers (cortical thickness measurements, volumetric measurements, hippocampal shape, and hippocampal texture). The method was developed, trained, and evaluated using two publicly available reference datasets: a standardized dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the imaging arm of the Australian Imaging Biomarkers and Lifestyle flagship study of ageing (AIBL). In addition, the method was evaluated by participation in the Computer-Aided Diagnosis of Dementia (CADDementia) challenge. Cross-validation using ADNI and AIBL data resulted in a multi-class classification accuracy of 62.7% for the discrimination of healthy normal controls (NC), subjects with mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD). This performance generalized to the CADDementia challenge where the method, trained using the ADNI and AIBL data, achieved a classification accuracy 63.0%. The obtained classification accuracy resulted in a first place in the challenge, and the method was significantly better (McNemar's test) than the bottom 24 methods out of the total of 29 methods contributed by 15 different teams in the challenge. The method was further investigated with learning curve and feature selection experiments using ADNI and AIBL data. The learning curve experiments suggested that neither more training data nor a more complex classifier would have improved the obtained results. The feature selection experiment showed that both common and uncommon individual MRI biomarkers contributed to the performance; hippocampal volume, ventricular volume, hippocampal texture, and parietal lobe thickness were the most important. This study highlights the need for both subtle, localized measurements and global measurements in order to discriminate NC, MCI, and AD simultaneously based on a single structural MRI scan. It is likely that additional non-structural MRI features are needed to further improve the obtained performance, especially to improve the discrimination between NC and MCI. The algorithm that won the CADDementia challenge is described and analyzed. Evaluation on data from ADNI, AIBL and the CADDementia challenge. Hippocampal texture is shown to be an important feature in the algorithm. Structural MRI intensity variations may include so far unused information. It is conjectured that additional features are needed in order to improve diagnostic performance.
Collapse
Affiliation(s)
- Lauge Sørensen
- Department of Computer Science, University of Copenhagen, Copenhagen Ø DK-2100, Denmark; Biomediq A/S, Copenhagen Ø DK-2100, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen Ø DK-2100, Denmark
| | - Akshay Pai
- Department of Computer Science, University of Copenhagen, Copenhagen Ø DK-2100, Denmark; Biomediq A/S, Copenhagen Ø DK-2100, Denmark
| | - Ioana Balas
- Department of Computer Science, University of Copenhagen, Copenhagen Ø DK-2100, Denmark
| | | | - Martin Lillholm
- Department of Computer Science, University of Copenhagen, Copenhagen Ø DK-2100, Denmark; Biomediq A/S, Copenhagen Ø DK-2100, Denmark
| | - Mads Nielsen
- Department of Computer Science, University of Copenhagen, Copenhagen Ø DK-2100, Denmark; Biomediq A/S, Copenhagen Ø DK-2100, Denmark
| | | |
Collapse
|
21
|
Raket LL, Grimme B, Schöner G, Igel C, Markussen B. Separating Timing, Movement Conditions and Individual Differences in the Analysis of Human Movement. PLoS Comput Biol 2016; 12:e1005092. [PMID: 27657545 PMCID: PMC5033575 DOI: 10.1371/journal.pcbi.1005092] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2016] [Accepted: 07/29/2016] [Indexed: 11/18/2022] Open
Abstract
A central task in the analysis of human movement behavior is to determine systematic patterns and differences across experimental conditions, participants and repetitions. This is possible because human movement is highly regular, being constrained by invariance principles. Movement timing and movement path, in particular, are linked through scaling laws. Separating variations of movement timing from the spatial variations of movements is a well-known challenge that is addressed in current approaches only through forms of preprocessing that bias analysis. Here we propose a novel nonlinear mixed-effects model for analyzing temporally continuous signals that contain systematic effects in both timing and path. Identifiability issues of path relative to timing are overcome by using maximum likelihood estimation in which the most likely separation of space and time is chosen given the variation found in data. The model is applied to analyze experimental data of human arm movements in which participants move a hand-held object to a target location while avoiding an obstacle. The model is used to classify movement data according to participant. Comparison to alternative approaches establishes nonlinear mixed-effects models as viable alternatives to conventional analysis frameworks. The model is then combined with a novel factor-analysis model that estimates the low-dimensional subspace within which movements vary when the task demands vary. Our framework enables us to visualize different dimensions of movement variation and to test hypotheses about the effect of obstacle placement and height on the movement path. We demonstrate that the approach can be used to uncover new properties of human movement. When you move a cup to a new location on a table, the movement of lifting, transporting, and setting down the cup appears to be completely automatic. Although the hand could take continuously many different paths and move on any temporal trajectory, real movements are highly regular and reproducible. From repetition to repetition movements vary, and the pattern of variance reflects movement conditions and movement timing. If another person performs the same task, the movement will be similar. When we look more closely, however, there are systematic individual differences. Some people will overcompensate when avoiding an obstacle and some people will systematically move slower than others. When we want to understand human movement, all these aspects are important. We want to know which parts of a movement are common across people and we want to quantify the different types of variability. Thus, the models we use to analyze movement data should contain all the mentioned effects. In this work, we developed a framework for statistical analysis of movement data that respects these structures of movements. We showed how this framework modeled the individual characteristics of participants better than other state-of-the-art modeling approaches. We combined the timing-and-path-separating model with a novel factor analysis model for analyzing the effect of obstacles on spatial movement paths. This combination allowed for an unprecedented ability to quantify and display different sources of variation in the data. We analyzed data from a designed experiment of arm movements under various obstacle avoidance conditions. Using the proposed statistical models, we documented three findings: a linearly amplified deviation in mean path related to increase in obstacle height; a consistent asymmetric pattern of variation along the movement path related to obstacle placement; and the existence of obstacle-distance invariant focal points where mean trajectories intersect in the frontal and vertical planes.
Collapse
Affiliation(s)
- Lars Lau Raket
- Department of Mathematical Sciences, University of Copenhagen, Copenhagen, Denmark
- * E-mail:
| | - Britta Grimme
- Institut für Neuroinformatik, Ruhr-Universität Bochum, Bochum, Germany
| | - Gregor Schöner
- Institut für Neuroinformatik, Ruhr-Universität Bochum, Bochum, Germany
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Bo Markussen
- Department of Mathematical Sciences, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
22
|
Sørensen L, Igel C, Nielsen M. P4‐177: MCI Trial Enrichment Using MRI Hippocampus Texture. Alzheimers Dement 2016. [DOI: 10.1016/j.jalz.2016.06.2269] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Affiliation(s)
- Lauge Sørensen
- University of CopenhagenCopenhagenDenmark
- Biomediq A/SCopenhagenDenmark
| | | | - Mads Nielsen
- University of CopenhagenCopenhagenDenmark
- Biomediq A/SCopenhagenDenmark
| |
Collapse
|
23
|
Kallenberg M, Petersen K, Nielsen M, Ng AY, Igel C, Vachon CM, Holland K, Winkel RR, Karssemeijer N, Lillholm M. Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring. IEEE Trans Med Imaging 2016; 35:1322-1331. [PMID: 26915120 DOI: 10.1109/tmi.2016.2532122] [Citation(s) in RCA: 278] [Impact Index Per Article: 34.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/14/2023]
Abstract
Mammographic risk scoring has commonly been automated by extracting a set of handcrafted features from mammograms, and relating the responses directly or indirectly to breast cancer risk. We present a method that learns a feature hierarchy from unlabeled data. When the learned features are used as the input to a simple classifier, two different tasks can be addressed: i) breast density segmentation, and ii) scoring of mammographic texture. The proposed model learns features at multiple scales. To control the models capacity a novel sparsity regularizer is introduced that incorporates both lifetime and population sparsity. We evaluated our method on three different clinical datasets. Our state-of-the-art results show that the learned breast density scores have a very strong positive relationship with manual ones, and that the learned texture scores are predictive of breast cancer. The model is easy to apply and generalizes to many other segmentation and scoring problems.
Collapse
|
24
|
Sørensen L, Igel C, Liv Hansen N, Osler M, Lauritzen M, Rostrup E, Nielsen M. Early detection of Alzheimer's disease using MRI hippocampal texture. Hum Brain Mapp 2015; 37:1148-61. [PMID: 26686837 DOI: 10.1002/hbm.23091] [Citation(s) in RCA: 109] [Impact Index Per Article: 12.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2015] [Revised: 11/06/2015] [Accepted: 12/06/2015] [Indexed: 11/08/2022] Open
Abstract
Cognitive impairment in patients with Alzheimer's disease (AD) is associated with reduction in hippocampal volume in magnetic resonance imaging (MRI). However, it is unknown whether hippocampal texture changes in persons with mild cognitive impairment (MCI) that does not have a change in hippocampal volume. We tested the hypothesis that hippocampal texture has association to early cognitive loss beyond that of volumetric changes. The texture marker was trained and evaluated using T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and subsequently applied to score independent data sets from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL) and the Metropolit 1953 Danish Male Birth Cohort (Metropolit). Hippocampal texture was superior to volume reduction as predictor of MCI-to-AD conversion in ADNI (area under the receiver operating characteristic curve [AUC] 0.74 vs. 0.67; DeLong test, p = 0.005), and provided even better prognostic results in AIBL (AUC 0.83). Hippocampal texture, but not volume, correlated with Addenbrooke's cognitive examination score (Pearson correlation, r = -0.25, p < 0.001) in the Metropolit cohort. The hippocampal texture marker correlated with hippocampal glucose metabolism as indicated by fluorodeoxyglucose-positron emission tomography (Pearson correlation, r = -0.57, p < 0.001). Texture statistics remained significant after adjustment for volume in all cases, and the combination of texture and volume did not improve diagnostic or prognostic AUCs significantly. Our study highlights the presence of hippocampal texture abnormalities in MCI, and the possibility that texture may serve as a prognostic neuroimaging biomarker of early cognitive impairment.
Collapse
Affiliation(s)
- Lauge Sørensen
- The Image Group, Department of Computer Science, University of Copenhagen, Denmark.,Biomediq A/S, Denmark
| | - Christian Igel
- The Image Group, Department of Computer Science, University of Copenhagen, Denmark
| | - Naja Liv Hansen
- Functional Imaging Unit, Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, Denmark.,Center for Healthy Aging, University of Copenhagen, Denmark
| | - Merete Osler
- Center for Healthy Aging, University of Copenhagen, Denmark.,Research Centre for Prevention and Health, Rigshospitalet-Glostrup, Denmark
| | - Martin Lauritzen
- Center for Healthy Aging, University of Copenhagen, Denmark.,Department of Neuroscience and Pharmacology, University of Copenhagen, Denmark.,Department of Clinical Neurophysiology, Rigshospitalet, Denmark
| | - Egill Rostrup
- Functional Imaging Unit, Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, Denmark.,Center for Healthy Aging, University of Copenhagen, Denmark
| | - Mads Nielsen
- The Image Group, Department of Computer Science, University of Copenhagen, Denmark.,Biomediq A/S, Denmark
| | | |
Collapse
|
25
|
Prasoon A, Igel C, Loog M, Lauze F, Dam EB, Nielsen M. Femoral cartilage segmentation in knee MRI scans using two stage voxel classification. Annu Int Conf IEEE Eng Med Biol Soc 2015; 2013:5469-72. [PMID: 24110974 DOI: 10.1109/embc.2013.6610787] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Using more than one classification stage and exploiting class population imbalance allows for incorporating powerful classifiers in tasks requiring large scale training data, even if these classifiers scale badly with the number of training samples. This led us to propose a two-stage classifier for segmenting tibial cartilage in knee MRI scans combining nearest neighbor classification and support vector machines (SVMs). Here we apply it to femoral cartilage segmentation. We describe the similarities and differences between segmenting these two knee cartilages. For further speeding up batch SVM training, we propose loosening the stopping condition in the quadratic program solver before considering moving on to other approximation techniques such as online SVMs. The two-stage approach reached a higher accuracy in comparison to the one-stage state-of-the-art method. It also achieved better inter-scan segmentation reproducibility when compared to a radiologist as well as the current state-of-the-art method.
Collapse
|
26
|
Sørensen L, Igel C, Nielsen M. P2‐139: Hippocampal MRI texture is related to hippocampal glucose metabolism. Alzheimers Dement 2015. [DOI: 10.1016/j.jalz.2015.06.677] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Affiliation(s)
- Lauge Sørensen
- University of CopenhagenCopenhagenDenmark
- Biomediq A/SCopenhagenDenmark
| | | | - Mads Nielsen
- University of CopenhagenCopenhagenDenmark
- Biomediq A/SCopenhagenDenmark
| |
Collapse
|
27
|
Sørensen L, Igel C, Hansen NL, Lauritzen MJ, Osler M, Rostrup E, Nielsen M. O1‐02‐05: VALIDATION OF HIPPOCAMPAL TEXTURE FOR EARLY ALZHEIMER'S DISEASE DETECTION: GENERALIZATION TO INDEPENDENT COHORTS AND EXTRAPOLATION TO VERY EARLY SIGNS OF DEMENTIA. Alzheimers Dement 2014. [DOI: 10.1016/j.jalz.2014.04.066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/24/2022]
|
28
|
|
29
|
|
30
|
|
31
|
Stallkamp J, Schlipsing M, Salmen J, Igel C. Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Netw 2012; 32:323-32. [DOI: 10.1016/j.neunet.2012.02.016] [Citation(s) in RCA: 274] [Impact Index Per Article: 22.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2011] [Revised: 01/13/2012] [Accepted: 02/07/2012] [Indexed: 10/28/2022]
|
32
|
Pai A, Sørensen L, Darkner S, Suhy J, Oh J, Chen G, Igel C, Nielsen M. IC‐P‐013: Hippocampal texture provides volume independent information for Alzheimer's diagnosis. Alzheimers Dement 2012. [DOI: 10.1016/j.jalz.2012.05.045] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Akshai Pai
- University of CopenhagenCopenhagenDenmark
| | | | | | - Joyce Suhy
- Synarc Inc.NewarkCaliforniaUnited States
| | - Joonmi Oh
- Synarc Inc.NewarkCaliforniaUnited States
| | | | | | | |
Collapse
|
33
|
Abstract
Optimization based on k-step contrastive divergence (CD) has become a common way to train restricted Boltzmann machines (RBMs). The k-step CD is a biased estimator of the log-likelihood gradient relying on Gibbs sampling. We derive a new upper bound for this bias. Its magnitude depends on k, the number of variables in the RBM, and the maximum change in energy that can be produced by changing a single variable. The last reflects the dependence on the absolute values of the RBM parameters. The magnitude of the bias is also affected by the distance in variation between the modeled distribution and the starting distribution of the Gibbs chain.
Collapse
Affiliation(s)
- Asja Fischer
- Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780 Bochum, Germany
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, 2100 Copenhagen Ø, Denmark
| |
Collapse
|
34
|
Markounikau V, Igel C, Grinvald A, Jancke D. A dynamic neural field model of mesoscopic cortical activity captured with voltage-sensitive dye imaging. PLoS Comput Biol 2010; 6:e1000919. [PMID: 20838578 PMCID: PMC2936513 DOI: 10.1371/journal.pcbi.1000919] [Citation(s) in RCA: 42] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2009] [Accepted: 08/04/2010] [Indexed: 11/18/2022] Open
Abstract
A neural field model is presented that captures the essential non-linear characteristics of activity dynamics across several millimeters of visual cortex in response to local flashed and moving stimuli. We account for physiological data obtained by voltage-sensitive dye (VSD) imaging which reports mesoscopic population activity at high spatio-temporal resolution. Stimulation included a single flashed square, a single flashed bar, the line-motion paradigm--for which psychophysical studies showed that flashing a square briefly before a bar produces sensation of illusory motion within the bar--and moving squares controls. We consider a two-layer neural field (NF) model describing an excitatory and an inhibitory layer of neurons as a coupled system of non-linear integro-differential equations. Under the assumption that the aggregated activity of both layers is reflected by VSD imaging, our phenomenological model quantitatively accounts for the observed spatio-temporal activity patterns. Moreover, the model generalizes to novel similar stimuli as it matches activity evoked by moving squares of different speeds. Our results indicate that feedback from higher brain areas is not required to produce motion patterns in the case of the illusory line-motion paradigm. Physiological interpretation of the model suggests that a considerable fraction of the VSD signal may be due to inhibitory activity, supporting the notion that balanced intra-layer cortical interactions between inhibitory and excitatory populations play a major role in shaping dynamic stimulus representations in the early visual cortex.
Collapse
|
35
|
Glasmachers T, Igel C. Maximum likelihood model selection for 1-norm soft margin SVMs with multiple parameters. IEEE Trans Pattern Anal Mach Intell 2010; 32:1522-1528. [PMID: 20421674 DOI: 10.1109/tpami.2010.95] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/29/2023]
Abstract
Adapting the hyperparameters of support vector machines (SVMs) is a challenging model selection problem, especially when flexible kernels are to be adapted and data are scarce. We present a coherent framework for regularized model selection of 1-norm soft margin SVMs for binary classification. It is proposed to use gradient-ascent on a likelihood function of the hyperparameters. The likelihood function is based on logistic regression for robustly estimating the class conditional probabilities and can be computed efficiently. Overfitting is an important issue in SVM model selection and can be addressed in our framework by incorporating suitable prior distributions over the hyperparameters. We show empirically that gradient-based optimization of the likelihood function is able to adapt multiple kernel parameters and leads to better models than four concurrent state-of-the-art methods.
Collapse
Affiliation(s)
- Tobias Glasmachers
- Dalle Molle Institute for Artificial Intelligence (IDSIA), 6928 Manno-Lugano, Switzerland.
| | | |
Collapse
|
36
|
Fischer A, Igel C. Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines. Artificial Neural Networks – ICANN 2010 2010. [DOI: 10.1007/978-3-642-15825-4_26] [Citation(s) in RCA: 26] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/23/2023]
|
37
|
Winter S, Pechlivanis I, Dekomien C, Igel C, Schmieder K. Toward registration of 3D ultrasound and CT images of the spine in clinical praxis: design and evaluation of a data acquisition protocol. Ultrasound Med Biol 2009; 35:1773-1782. [PMID: 19716226 DOI: 10.1016/j.ultrasmedbio.2009.06.1089] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/05/2008] [Revised: 06/03/2009] [Accepted: 06/10/2009] [Indexed: 05/28/2023]
Abstract
Recent work has demonstrated the accuracy and operational viability of an algorithm proposed by the authors that successfully registers 3-D ultrasound data with CT or MRI data. The successful application of this method to intraoperative navigation, however, depends critically on the quality of the acquired ultrasound data. This gives rise to two questions concerning the usability of the algorithm in clinical praxis. First, how can one guarantee high-quality, user-independent ultrasound registration data with this procedure? Second, can this approach work reliably in clinical practice, namely within the operating theater? To address both of these questions, we present an ultrasound data acquisition protocol that leads the user through the data acquisition process and also provides the criteria to adjust the relevant ultrasound parameters. We also evaluated criteria for the visual inspection of the suitability of the ultrasound data for the registration process. Results for this evaluation show that these visual criteria can be used to decide preoperatively if an ultrasound registration will be successful in a patient. The intraoperative evaluation of the protocol showed that high-quality registrations can be achieved under realistic conditions. This protocol and the visual inspection criteria, together with the ultrasound registration algorithm, provide a surgical team with a means of performing precise, cost-effective navigation in patients for whom a navigated intervention was previously impossible. We evaluated the proposed procedure in clinical practice.
Collapse
Affiliation(s)
- Susanne Winter
- Institut für Neuroinformatik, Ruhr-Universität Bochum, 44801 Bochum, Germany.
| | | | | | | | | |
Collapse
|
38
|
Abstract
Oligo kernels for biological sequence classification have a high discriminative power. A new parameterization for the K-mer oligo kernel is presented, where all oligomers of length K are weighted individually. The task specific choice of these parameters increases the classification performance and reveals information about discriminative features. For adapting the multiple kernel parameters based on cross-validation the covariance matrix adaptation evolution strategy is proposed. It is applied to optimize the trimer oligo kernels for the detection of bacterial gene starts. The resulting kernels lead to higher classification rates, and the adapted parameters reveal the importance of particular triplets for classification, for example of those occurring in the Shine-Dalgarno Sequence.
Collapse
Affiliation(s)
- Britta Mersch
- Abteilung Molekulare Biophysik, German Cancer Research Center, 69120 Heidelberg, Germany.
| | | | | | | |
Collapse
|
39
|
Abstract
Iterative learning algorithms that approximate the solution of support vector machines (SVMs) have two potential advantages. First, they allow online and active learning. Second, for large data sets, computing the exact SVM solution may be too time-consuming, and an efficient approximation can be preferable. The powerful LASVM iteratively approaches the exact SVM solution using sequential minimal optimization (SMO). It allows efficient online and active learning. Here, this algorithm is considerably improved in speed and accuracy by replacing the working set selection in the SMO steps. A second-order working set selection strategy, which greedily aims at maximizing the progress in each single step, is incorporated.
Collapse
Affiliation(s)
- Tobias Glasmachers
- Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780 Bochum, Germany
| | - Christian Igel
- Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780 Bochum, Germany
| |
Collapse
|
40
|
Heidrich-Meisner V, Igel C. Variable Metric Reinforcement Learning Methods Applied to the Noisy Mountain Car Problem. Lecture Notes in Computer Science 2008. [DOI: 10.1007/978-3-540-89722-4_11] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/12/2023]
|
41
|
Glasmachers T, Igel C. Uncertainty Handling in Model Selection for Support Vector Machines. Parallel Problem Solving from Nature – PPSN X 2008. [DOI: 10.1007/978-3-540-87700-4_19] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/12/2023]
|
42
|
|
43
|
Igel C, Glasmachers T, Mersch B, Pfeifer N, Meinicke P. Gradient-based optimization of kernel-target alignment for sequence kernels applied to bacterial gene start detection. IEEE/ACM Trans Comput Biol Bioinform 2007; 4:216-26. [PMID: 17473315 DOI: 10.1109/tcbb.2007.070208] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/15/2023]
Abstract
Biological data mining using kernel methods can be improved by a task-specific choice of the kernel function. Oligo kernels for genomic sequence analysis have proven to have a high discriminative power and to provide interpretable results. Oligo kernels that consider subsequences of different lengths can be combined and parameterized to increase their flexibility. For adapting these parameters efficiently, gradient-based optimization of the kernel-target alignment is proposed. The power of this new, general model selection procedure and the benefits of fitting kernels to problem classes are demonstrated by adapting oligo kernels for bacterial gene start detection.
Collapse
Affiliation(s)
- Christian Igel
- Institut für Neuroinformatik, Ruhr-Universität Bochum, Bochum, Germany.
| | | | | | | | | |
Collapse
|
44
|
Niehaus J, Igel C, Banzhaf W. Reducing the number of fitness evaluations in graph genetic programming using a canonical graph indexed database. Evol Comput 2007; 15:199-221. [PMID: 17535139 DOI: 10.1162/evco.2007.15.2.199] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/15/2023]
Abstract
In this paper we describe the genetic programming system GGP operating on graphs and introduce the notion of graph isomorphisms to explain how they influence the dynamics of GP. It is shown empirically how fitness databases can improve the performance of GP and how mapping graphs to a canonical form can increase these improvements by saving considerable evaluation time.
Collapse
Affiliation(s)
- Jens Niehaus
- Visual Systems Automation GmbH, 59174 Kamen, Germany.
| | | | | |
Collapse
|
45
|
Abstract
The covariance matrix adaptation evolution strategy (CMA-ES) is one of the most powerful evolutionary algorithms for real-valued single-objective optimization. In this paper, we develop a variant of the CMA-ES for multi-objective optimization (MOO). We first introduce a single-objective, elitist CMA-ES using plus-selection and step size control based on a success rule. This algorithm is compared to the standard CMA-ES. The elitist CMA-ES turns out to be slightly faster on unimodal functions, but is more prone to getting stuck in sub-optimal local minima. In the new multi-objective CMAES (MO-CMA-ES) a population of individuals that adapt their search strategy as in the elitist CMA-ES is maintained. These are subject to multi-objective selection. The selection is based on non-dominated sorting using either the crowding-distance or the contributing hypervolume as second sorting criterion. Both the elitist single-objective CMA-ES and the MO-CMA-ES inherit important invariance properties, in particular invariance against rotation of the search space, from the original CMA-ES. The benefits of the new MO-CMA-ES in comparison to the well-known NSGA-II and to NSDE, a multi-objective differential evolution algorithm, are experimentally shown.
Collapse
Affiliation(s)
- Christian Igel
- Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780 Bochum, Germany.
| | | | | |
Collapse
|
46
|
Abstract
Gradient-based optimizing of gaussian kernel functions is considered. The gradient for the adaptation of scaling and rotation of the input space is computed to achieve invariance against linear transformations. This is done by using the exponential map as a parameterization of the kernel parameter manifold. By restricting the optimization to a constant trace subspace, the kernel size can be controlled. This is, for example, useful to prevent overfitting when minimizing radius-margin generalization performance measures. The concepts are demonstrated by training hard margin support vector machines on toy data.
Collapse
Affiliation(s)
- Tobias Glasmachers
- Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780 Bochum, Germany.
| | | |
Collapse
|
47
|
Winter S, Brendel B, Igel C. Registration of bone structures in 3D ultrasound and CT data: Comparison of different optimization strategies. ACTA ACUST UNITED AC 2005. [DOI: 10.1016/j.ics.2005.03.351] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
48
|
|
49
|
|
50
|
|