Robust Multi-scale Anatomical Landmark Detection in Incomplete 3D-CT Data View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2017-09-04

AUTHORS

Florin C. Ghesu , Bogdan Georgescu , Sasa Grbic , Andreas K. Maier , Joachim Hornegger , Dorin Comaniciu

ABSTRACT

Robust and fast detection of anatomical structures is an essential prerequisite for the next-generation automated medical support tools. While machine learning techniques are most often applied to address this problem, the traditional object search scheme is typically driven by suboptimal and exhaustive strategies. Most importantly, these techniques do not effectively address cases of incomplete data, i.e., scans taken with a partial field-of-view. To address these limitations, we present a solution that unifies the anatomy appearance model and the search strategy by formulating a behavior-learning task. This is solved using the capabilities of deep reinforcement learning with multi-scale image analysis and robust statistical shape modeling. Using these mechanisms artificial agents are taught optimal navigation paths in the image scale-space that can account for missing structures to ensure the robust and spatially-coherent detection of the observed anatomical landmarks. The identified landmarks are then used as robust guidance in estimating the extent of the body-region. Experiments show that our solution outperforms a state-of-the-art deep learning method in detecting different anatomical structures, without any failure, on a dataset of over 2300 3D-CT volumes. In particular, we achieve 0% false-positive and 0% false-negative rates at detecting the landmarks or recognizing their absence from the field-of-view of the scan. In terms of runtime, we reduce the detection-time of the reference method by 15−20 times to under 40 ms, an unmatched performance in the literature for high-resolution 3D-CT. More... »

PAGES

194-202

Book

TITLE

Medical Image Computing and Computer Assisted Intervention − MICCAI 2017

ISBN

978-3-319-66181-0
978-3-319-66182-7

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-66182-7_23

DOI

http://dx.doi.org/10.1007/978-3-319-66182-7_23

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1091429439


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t, Erlangen, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5330.5", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
            "Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t, Erlangen, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ghesu", 
        "givenName": "Florin C.", 
        "id": "sg:person.012717301041.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012717301041.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Georgescu", 
        "givenName": "Bogdan", 
        "id": "sg:person.0703547214.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703547214.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Grbic", 
        "givenName": "Sasa", 
        "id": "sg:person.01126227511.07", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01126227511.07"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t, Erlangen, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5330.5", 
          "name": [
            "Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t, Erlangen, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Maier", 
        "givenName": "Andreas K.", 
        "id": "sg:person.01244543441.88", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01244543441.88"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t, Erlangen, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5330.5", 
          "name": [
            "Pattern Recognition Lab, Friedrich-Alexander-Universit\u00e4t, Erlangen, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hornegger", 
        "givenName": "Joachim", 
        "id": "sg:person.01322323610.92", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01322323610.92"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Comaniciu", 
        "givenName": "Dorin", 
        "id": "sg:person.01066111014.77", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066111014.77"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2017-09-04", 
    "datePublishedReg": "2017-09-04", 
    "description": "Robust and fast detection of anatomical structures is an essential prerequisite for the next-generation automated medical support tools. While machine learning techniques are most often applied to address this problem, the traditional object search scheme is typically driven by suboptimal and exhaustive strategies. Most importantly, these techniques do not effectively address cases of incomplete data, i.e., scans taken with a partial field-of-view. To address these limitations, we present a solution that unifies the anatomy appearance model and the search strategy by formulating a behavior-learning task. This is solved using the capabilities of deep reinforcement learning with multi-scale image analysis and robust statistical shape modeling. Using these mechanisms artificial agents are taught optimal navigation paths in the image scale-space that can account for missing structures to ensure the robust and spatially-coherent detection of the observed anatomical landmarks. The identified landmarks are then used as robust guidance in estimating the extent of the body-region. Experiments show that our solution outperforms a state-of-the-art deep learning method in detecting different anatomical structures, without any failure, on a dataset of over 2300 3D-CT volumes. In particular, we achieve 0% false-positive and 0% false-negative rates at detecting the landmarks or recognizing their absence from the field-of-view of the scan. In terms of runtime, we reduce the detection-time of the reference method by 15\u221220 times to under 40 ms, an unmatched performance in the literature for high-resolution 3D-CT.", 
    "editor": [
      {
        "familyName": "Descoteaux", 
        "givenName": "Maxime", 
        "type": "Person"
      }, 
      {
        "familyName": "Maier-Hein", 
        "givenName": "Lena", 
        "type": "Person"
      }, 
      {
        "familyName": "Franz", 
        "givenName": "Alfred", 
        "type": "Person"
      }, 
      {
        "familyName": "Jannin", 
        "givenName": "Pierre", 
        "type": "Person"
      }, 
      {
        "familyName": "Collins", 
        "givenName": "D. Louis", 
        "type": "Person"
      }, 
      {
        "familyName": "Duchesne", 
        "givenName": "Simon", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-66182-7_23", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-66181-0", 
        "978-3-319-66182-7"
      ], 
      "name": "Medical Image Computing and Computer Assisted Intervention \u2212 MICCAI 2017", 
      "type": "Book"
    }, 
    "keywords": [
      "art deep learning methods", 
      "optimal navigation paths", 
      "multi-scale image analysis", 
      "anatomical landmark detection", 
      "deep learning methods", 
      "machine learning techniques", 
      "terms of runtime", 
      "high-resolution 3D CT", 
      "navigation path", 
      "deep reinforcement", 
      "learning techniques", 
      "landmark detection", 
      "search scheme", 
      "artificial agents", 
      "appearance model", 
      "learning method", 
      "support tool", 
      "shape modeling", 
      "unmatched performance", 
      "exhaustive strategy", 
      "incomplete data", 
      "image analysis", 
      "statistical shape modeling", 
      "search strategy", 
      "anatomical structures", 
      "fast detection", 
      "different anatomical structures", 
      "false negative rate", 
      "runtime", 
      "landmarks", 
      "detection", 
      "dataset", 
      "robust guidance", 
      "partial fields", 
      "task", 
      "images", 
      "anatomical landmarks", 
      "scheme", 
      "technique", 
      "capability", 
      "solution", 
      "coherent detection", 
      "essential prerequisite", 
      "tool", 
      "path", 
      "data", 
      "performance", 
      "method", 
      "view", 
      "modeling", 
      "strategies", 
      "field", 
      "limitations", 
      "model", 
      "experiments", 
      "terms", 
      "guidance", 
      "structure", 
      "time", 
      "prerequisite", 
      "problem", 
      "state", 
      "scans", 
      "reference method", 
      "reinforcement", 
      "agents", 
      "literature", 
      "analysis", 
      "ms", 
      "cases", 
      "volume", 
      "failure", 
      "rate", 
      "extent", 
      "absence", 
      "medical support tools", 
      "traditional object search scheme", 
      "object search scheme", 
      "anatomy appearance model", 
      "behavior-learning task", 
      "robust statistical shape modeling", 
      "mechanisms artificial agents", 
      "observed anatomical landmarks", 
      "Robust Multi-scale Anatomical Landmark Detection", 
      "Multi-scale Anatomical Landmark Detection", 
      "Incomplete 3D-CT Data"
    ], 
    "name": "Robust Multi-scale Anatomical Landmark Detection in Incomplete 3D-CT Data", 
    "pagination": "194-202", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1091429439"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-66182-7_23"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-66182-7_23", 
      "https://app.dimensions.ai/details/publication/pub.1091429439"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:14", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_258.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-66182-7_23"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-66182-7_23'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-66182-7_23'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-66182-7_23'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-66182-7_23'


 

This table displays all metadata directly associated to this object as RDF triples.

210 TRIPLES      23 PREDICATES      111 URIs      104 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-66182-7_23 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nde86fad5d37d4d898510003c96d2a920
4 schema:datePublished 2017-09-04
5 schema:datePublishedReg 2017-09-04
6 schema:description Robust and fast detection of anatomical structures is an essential prerequisite for the next-generation automated medical support tools. While machine learning techniques are most often applied to address this problem, the traditional object search scheme is typically driven by suboptimal and exhaustive strategies. Most importantly, these techniques do not effectively address cases of incomplete data, i.e., scans taken with a partial field-of-view. To address these limitations, we present a solution that unifies the anatomy appearance model and the search strategy by formulating a behavior-learning task. This is solved using the capabilities of deep reinforcement learning with multi-scale image analysis and robust statistical shape modeling. Using these mechanisms artificial agents are taught optimal navigation paths in the image scale-space that can account for missing structures to ensure the robust and spatially-coherent detection of the observed anatomical landmarks. The identified landmarks are then used as robust guidance in estimating the extent of the body-region. Experiments show that our solution outperforms a state-of-the-art deep learning method in detecting different anatomical structures, without any failure, on a dataset of over 2300 3D-CT volumes. In particular, we achieve 0% false-positive and 0% false-negative rates at detecting the landmarks or recognizing their absence from the field-of-view of the scan. In terms of runtime, we reduce the detection-time of the reference method by 15−20 times to under 40 ms, an unmatched performance in the literature for high-resolution 3D-CT.
7 schema:editor N1b00471dd7024575a7669d8d856d6987
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N2b447da649ed4a0ca87682260f624d14
12 schema:keywords Incomplete 3D-CT Data
13 Multi-scale Anatomical Landmark Detection
14 Robust Multi-scale Anatomical Landmark Detection
15 absence
16 agents
17 analysis
18 anatomical landmark detection
19 anatomical landmarks
20 anatomical structures
21 anatomy appearance model
22 appearance model
23 art deep learning methods
24 artificial agents
25 behavior-learning task
26 capability
27 cases
28 coherent detection
29 data
30 dataset
31 deep learning methods
32 deep reinforcement
33 detection
34 different anatomical structures
35 essential prerequisite
36 exhaustive strategy
37 experiments
38 extent
39 failure
40 false negative rate
41 fast detection
42 field
43 guidance
44 high-resolution 3D CT
45 image analysis
46 images
47 incomplete data
48 landmark detection
49 landmarks
50 learning method
51 learning techniques
52 limitations
53 literature
54 machine learning techniques
55 mechanisms artificial agents
56 medical support tools
57 method
58 model
59 modeling
60 ms
61 multi-scale image analysis
62 navigation path
63 object search scheme
64 observed anatomical landmarks
65 optimal navigation paths
66 partial fields
67 path
68 performance
69 prerequisite
70 problem
71 rate
72 reference method
73 reinforcement
74 robust guidance
75 robust statistical shape modeling
76 runtime
77 scans
78 scheme
79 search scheme
80 search strategy
81 shape modeling
82 solution
83 state
84 statistical shape modeling
85 strategies
86 structure
87 support tool
88 task
89 technique
90 terms
91 terms of runtime
92 time
93 tool
94 traditional object search scheme
95 unmatched performance
96 view
97 volume
98 schema:name Robust Multi-scale Anatomical Landmark Detection in Incomplete 3D-CT Data
99 schema:pagination 194-202
100 schema:productId N2e80c133bf0c40b7b5693846ca60d5f4
101 N62b25cdc3b914471a1438fa7fac1786c
102 schema:publisher N5a05b9473a1443f780c7d7ce74bb688a
103 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091429439
104 https://doi.org/10.1007/978-3-319-66182-7_23
105 schema:sdDatePublished 2022-01-01T19:14
106 schema:sdLicense https://scigraph.springernature.com/explorer/license/
107 schema:sdPublisher N81f6595e198748e0b1ed2d1c3876e9b9
108 schema:url https://doi.org/10.1007/978-3-319-66182-7_23
109 sgo:license sg:explorer/license/
110 sgo:sdDataset chapters
111 rdf:type schema:Chapter
112 N117d5121f60f4a43a054a0ca3e705b72 schema:familyName Franz
113 schema:givenName Alfred
114 rdf:type schema:Person
115 N164e580aece9498b8c3f95e40276a298 rdf:first N117d5121f60f4a43a054a0ca3e705b72
116 rdf:rest N996d4de4f2cc4803b357d80e4cb89a08
117 N1b00471dd7024575a7669d8d856d6987 rdf:first N4ca9e1f90bba43d7985580d9f45eb729
118 rdf:rest N3a9f210ae4db42e98ec29b54c1e1e006
119 N28b0a22ff1f54ff19964e4b803c91145 rdf:first sg:person.0703547214.37
120 rdf:rest N5bb08020c0c3478fb5d643de024c6589
121 N2b447da649ed4a0ca87682260f624d14 schema:isbn 978-3-319-66181-0
122 978-3-319-66182-7
123 schema:name Medical Image Computing and Computer Assisted Intervention − MICCAI 2017
124 rdf:type schema:Book
125 N2e80c133bf0c40b7b5693846ca60d5f4 schema:name dimensions_id
126 schema:value pub.1091429439
127 rdf:type schema:PropertyValue
128 N3a9f210ae4db42e98ec29b54c1e1e006 rdf:first Nac083d7d2cd74e31b6c52687c592c918
129 rdf:rest N164e580aece9498b8c3f95e40276a298
130 N4ca9e1f90bba43d7985580d9f45eb729 schema:familyName Descoteaux
131 schema:givenName Maxime
132 rdf:type schema:Person
133 N5a05b9473a1443f780c7d7ce74bb688a schema:name Springer Nature
134 rdf:type schema:Organisation
135 N5b4e698e8eae4e1084e62e0c0c575aae schema:familyName Duchesne
136 schema:givenName Simon
137 rdf:type schema:Person
138 N5bb08020c0c3478fb5d643de024c6589 rdf:first sg:person.01126227511.07
139 rdf:rest N7dc2ea75977f4e80965b3b5f03e8487a
140 N62b25cdc3b914471a1438fa7fac1786c schema:name doi
141 schema:value 10.1007/978-3-319-66182-7_23
142 rdf:type schema:PropertyValue
143 N7dc2ea75977f4e80965b3b5f03e8487a rdf:first sg:person.01244543441.88
144 rdf:rest N8c8aa87aeb1c4d15bf75261c4a12811b
145 N81f6595e198748e0b1ed2d1c3876e9b9 schema:name Springer Nature - SN SciGraph project
146 rdf:type schema:Organization
147 N8c8aa87aeb1c4d15bf75261c4a12811b rdf:first sg:person.01322323610.92
148 rdf:rest Nc68c28cb6dc94432949aaaeefae45736
149 N996d4de4f2cc4803b357d80e4cb89a08 rdf:first Ne65a1eaad3574d629ed921dd6fab047f
150 rdf:rest Na8d798fa743f4c8b8196f220ef48507e
151 N9cd12ca9937f4174b02be144f72a3faf schema:familyName Collins
152 schema:givenName D. Louis
153 rdf:type schema:Person
154 Na8d798fa743f4c8b8196f220ef48507e rdf:first N9cd12ca9937f4174b02be144f72a3faf
155 rdf:rest Nbe0d987150424e5a9d6cc7ee800ef8fe
156 Nac083d7d2cd74e31b6c52687c592c918 schema:familyName Maier-Hein
157 schema:givenName Lena
158 rdf:type schema:Person
159 Nbe0d987150424e5a9d6cc7ee800ef8fe rdf:first N5b4e698e8eae4e1084e62e0c0c575aae
160 rdf:rest rdf:nil
161 Nc68c28cb6dc94432949aaaeefae45736 rdf:first sg:person.01066111014.77
162 rdf:rest rdf:nil
163 Nde86fad5d37d4d898510003c96d2a920 rdf:first sg:person.012717301041.17
164 rdf:rest N28b0a22ff1f54ff19964e4b803c91145
165 Ne65a1eaad3574d629ed921dd6fab047f schema:familyName Jannin
166 schema:givenName Pierre
167 rdf:type schema:Person
168 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
169 schema:name Information and Computing Sciences
170 rdf:type schema:DefinedTerm
171 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
172 schema:name Artificial Intelligence and Image Processing
173 rdf:type schema:DefinedTerm
174 sg:person.01066111014.77 schema:affiliation grid-institutes:grid.415886.6
175 schema:familyName Comaniciu
176 schema:givenName Dorin
177 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066111014.77
178 rdf:type schema:Person
179 sg:person.01126227511.07 schema:affiliation grid-institutes:grid.415886.6
180 schema:familyName Grbic
181 schema:givenName Sasa
182 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01126227511.07
183 rdf:type schema:Person
184 sg:person.01244543441.88 schema:affiliation grid-institutes:grid.5330.5
185 schema:familyName Maier
186 schema:givenName Andreas K.
187 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01244543441.88
188 rdf:type schema:Person
189 sg:person.012717301041.17 schema:affiliation grid-institutes:grid.5330.5
190 schema:familyName Ghesu
191 schema:givenName Florin C.
192 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012717301041.17
193 rdf:type schema:Person
194 sg:person.01322323610.92 schema:affiliation grid-institutes:grid.5330.5
195 schema:familyName Hornegger
196 schema:givenName Joachim
197 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01322323610.92
198 rdf:type schema:Person
199 sg:person.0703547214.37 schema:affiliation grid-institutes:grid.415886.6
200 schema:familyName Georgescu
201 schema:givenName Bogdan
202 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703547214.37
203 rdf:type schema:Person
204 grid-institutes:grid.415886.6 schema:alternateName Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA
205 schema:name Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA
206 rdf:type schema:Organization
207 grid-institutes:grid.5330.5 schema:alternateName Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen, Germany
208 schema:name Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA
209 Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen, Germany
210 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...