ImageCLEF 2004: Combining Image and Multi-lingual Search for Medical Image Retrieval View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2005

AUTHORS

Henning Müller , Antoine Geissbühler , Patrick Ruch

ABSTRACT

This article describes the technologies used for the various runs submitted by the University of Geneva in the context of the 2004 ImageCLEF competition. As our expertise is mainly in the field of medical image retrieval, most of our effort was concentrated on the medical image retrieval task. Described are the runs that were submitted including technical details for each of the single runs and a short explication of the obtained results compared with the results of submissions from other groups. We describe the problems encountered with respect to optimising the system and with respect to finding a balance between weighting textual and visual features for retrieval. A better balance seems possible when using training data for optimisation and with relevance judgements being available for a control of the retrieval quality.The results show that relevance feedback is extremely important for optimal results. Query expansion with visual features only gives minimal changes in result quality. If textual features are added in the automatic query expansion, the results improve significantly. Visual and textual results combined deliver the best performance. More... »

PAGES

718-727

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11519645_70

DOI

http://dx.doi.org/10.1007/11519645_70

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1040886757


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": "Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland", 
          "id": "http://www.grid.ac/institutes/grid.150338.c", 
          "name": [
            "Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "M\u00fcller", 
        "givenName": "Henning", 
        "id": "sg:person.07552063233.67", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07552063233.67"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland", 
          "id": "http://www.grid.ac/institutes/grid.150338.c", 
          "name": [
            "Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Geissb\u00fchler", 
        "givenName": "Antoine", 
        "id": "sg:person.0600360343.20", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0600360343.20"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Swiss Federal Institute of Technology, LITH, IN-Ecublens, CH-1015, Lausanne, Switzerland", 
          "id": "http://www.grid.ac/institutes/grid.5801.c", 
          "name": [
            "Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland", 
            "Swiss Federal Institute of Technology, LITH, IN-Ecublens, CH-1015, Lausanne, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ruch", 
        "givenName": "Patrick", 
        "id": "sg:person.016176475704.89", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016176475704.89"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2005", 
    "datePublishedReg": "2005-01-01", 
    "description": "This article describes the technologies used for the various runs submitted by the University of Geneva in the context of the 2004 ImageCLEF competition. As our expertise is mainly in the field of medical image retrieval, most of our effort was concentrated on the medical image retrieval task. Described are the runs that were submitted including technical details for each of the single runs and a short explication of the obtained results compared with the results of submissions from other groups. We describe the problems encountered with respect to optimising the system and with respect to finding a balance between weighting textual and visual features for retrieval. A better balance seems possible when using training data for optimisation and with relevance judgements being available for a control of the retrieval quality.The results show that relevance feedback is extremely important for optimal results. Query expansion with visual features only gives minimal changes in result quality. If textual features are added in the automatic query expansion, the results improve significantly. Visual and textual results combined deliver the best performance.", 
    "editor": [
      {
        "familyName": "Peters", 
        "givenName": "Carol", 
        "type": "Person"
      }, 
      {
        "familyName": "Clough", 
        "givenName": "Paul", 
        "type": "Person"
      }, 
      {
        "familyName": "Gonzalo", 
        "givenName": "Julio", 
        "type": "Person"
      }, 
      {
        "familyName": "Jones", 
        "givenName": "Gareth J. F.", 
        "type": "Person"
      }, 
      {
        "familyName": "Kluck", 
        "givenName": "Michael", 
        "type": "Person"
      }, 
      {
        "familyName": "Magnini", 
        "givenName": "Bernardo", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/11519645_70", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-27420-9", 
        "978-3-540-32051-7"
      ], 
      "name": "Multilingual Information Access for Text, Speech and Images", 
      "type": "Book"
    }, 
    "keywords": [
      "medical image retrieval", 
      "image retrieval", 
      "query expansion", 
      "visual features", 
      "medical image retrieval task", 
      "image retrieval tasks", 
      "automatic query expansion", 
      "ImageCLEF competition", 
      "relevance feedback", 
      "retrieval quality", 
      "retrieval tasks", 
      "result quality", 
      "relevance judgments", 
      "results of submissions", 
      "training data", 
      "textual features", 
      "textual results", 
      "retrieval", 
      "better performance", 
      "good balance", 
      "technical details", 
      "short explication", 
      "optimal results", 
      "single run", 
      "features", 
      "task", 
      "images", 
      "technology", 
      "optimization", 
      "quality", 
      "search", 
      "performance", 
      "feedback", 
      "University of Geneva", 
      "submission", 
      "system", 
      "run", 
      "expertise", 
      "results", 
      "context", 
      "minimal changes", 
      "efforts", 
      "detail", 
      "data", 
      "respect", 
      "field", 
      "University", 
      "control", 
      "article", 
      "judgments", 
      "competition", 
      "balance", 
      "explication", 
      "expansion", 
      "Geneva", 
      "changes", 
      "group", 
      "problem", 
      "Multi-lingual Search"
    ], 
    "name": "ImageCLEF 2004: Combining Image and Multi-lingual Search for Medical Image Retrieval", 
    "pagination": "718-727", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1040886757"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11519645_70"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11519645_70", 
      "https://app.dimensions.ai/details/publication/pub.1040886757"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T19:58", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/chapter/chapter_176.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/11519645_70"
  }
]
 

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.10.1007/11519645_70'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11519645_70'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11519645_70'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11519645_70'


 

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

162 TRIPLES      23 PREDICATES      85 URIs      78 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11519645_70 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nf86512088a9240a88b04660d069106c8
4 schema:datePublished 2005
5 schema:datePublishedReg 2005-01-01
6 schema:description This article describes the technologies used for the various runs submitted by the University of Geneva in the context of the 2004 ImageCLEF competition. As our expertise is mainly in the field of medical image retrieval, most of our effort was concentrated on the medical image retrieval task. Described are the runs that were submitted including technical details for each of the single runs and a short explication of the obtained results compared with the results of submissions from other groups. We describe the problems encountered with respect to optimising the system and with respect to finding a balance between weighting textual and visual features for retrieval. A better balance seems possible when using training data for optimisation and with relevance judgements being available for a control of the retrieval quality.The results show that relevance feedback is extremely important for optimal results. Query expansion with visual features only gives minimal changes in result quality. If textual features are added in the automatic query expansion, the results improve significantly. Visual and textual results combined deliver the best performance.
7 schema:editor N991227e1af634025b88e8e8404335c7a
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N52e9baadc25a4ff7adda7f9e0bf814b2
12 schema:keywords Geneva
13 ImageCLEF competition
14 Multi-lingual Search
15 University
16 University of Geneva
17 article
18 automatic query expansion
19 balance
20 better performance
21 changes
22 competition
23 context
24 control
25 data
26 detail
27 efforts
28 expansion
29 expertise
30 explication
31 features
32 feedback
33 field
34 good balance
35 group
36 image retrieval
37 image retrieval tasks
38 images
39 judgments
40 medical image retrieval
41 medical image retrieval task
42 minimal changes
43 optimal results
44 optimization
45 performance
46 problem
47 quality
48 query expansion
49 relevance feedback
50 relevance judgments
51 respect
52 result quality
53 results
54 results of submissions
55 retrieval
56 retrieval quality
57 retrieval tasks
58 run
59 search
60 short explication
61 single run
62 submission
63 system
64 task
65 technical details
66 technology
67 textual features
68 textual results
69 training data
70 visual features
71 schema:name ImageCLEF 2004: Combining Image and Multi-lingual Search for Medical Image Retrieval
72 schema:pagination 718-727
73 schema:productId N907f5cac692f41f1977933424c8def8b
74 Nabb693dcbc354bb59280879386a682f3
75 schema:publisher N1413f784ff1846608e189a3c50edcbf5
76 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040886757
77 https://doi.org/10.1007/11519645_70
78 schema:sdDatePublished 2021-12-01T19:58
79 schema:sdLicense https://scigraph.springernature.com/explorer/license/
80 schema:sdPublisher Ndb68fc7994b445fc8255e1b502c8c0d3
81 schema:url https://doi.org/10.1007/11519645_70
82 sgo:license sg:explorer/license/
83 sgo:sdDataset chapters
84 rdf:type schema:Chapter
85 N077d252fbeaf4c8eba847fb8b2ee562b schema:familyName Gonzalo
86 schema:givenName Julio
87 rdf:type schema:Person
88 N1413f784ff1846608e189a3c50edcbf5 schema:name Springer Nature
89 rdf:type schema:Organisation
90 N1614e6b7467d424caa1aae03c07b17ee schema:familyName Peters
91 schema:givenName Carol
92 rdf:type schema:Person
93 N2e7476bca71b47c49b31a85f00dc13df schema:familyName Kluck
94 schema:givenName Michael
95 rdf:type schema:Person
96 N52e9baadc25a4ff7adda7f9e0bf814b2 schema:isbn 978-3-540-27420-9
97 978-3-540-32051-7
98 schema:name Multilingual Information Access for Text, Speech and Images
99 rdf:type schema:Book
100 N907f5cac692f41f1977933424c8def8b schema:name dimensions_id
101 schema:value pub.1040886757
102 rdf:type schema:PropertyValue
103 N912d322328ec44a4ae44b85b15c8b8df rdf:first N97c501079c1542c29ed7645aa5890bbb
104 rdf:rest Nda467d79d2164b2c9fd47f08750d55f9
105 N97c501079c1542c29ed7645aa5890bbb schema:familyName Clough
106 schema:givenName Paul
107 rdf:type schema:Person
108 N991227e1af634025b88e8e8404335c7a rdf:first N1614e6b7467d424caa1aae03c07b17ee
109 rdf:rest N912d322328ec44a4ae44b85b15c8b8df
110 Nabb693dcbc354bb59280879386a682f3 schema:name doi
111 schema:value 10.1007/11519645_70
112 rdf:type schema:PropertyValue
113 Nad185803b16945bcb2557df5bfd74dc6 rdf:first N2e7476bca71b47c49b31a85f00dc13df
114 rdf:rest Ncbb91da26e0b44829e3de2e783615993
115 Nb2257853f32f4bdf8152463d903cdb19 rdf:first Ncfafcf96a95e4edf8b224b5286212821
116 rdf:rest Nad185803b16945bcb2557df5bfd74dc6
117 Nbf8d78e2cedc482e9684fd2363a79ffb rdf:first sg:person.0600360343.20
118 rdf:rest Ne0feb31233bf48cc89985dc157986560
119 Ncbb91da26e0b44829e3de2e783615993 rdf:first Nf72244d74e9540bd891e101d0ba294fa
120 rdf:rest rdf:nil
121 Ncfafcf96a95e4edf8b224b5286212821 schema:familyName Jones
122 schema:givenName Gareth J. F.
123 rdf:type schema:Person
124 Nda467d79d2164b2c9fd47f08750d55f9 rdf:first N077d252fbeaf4c8eba847fb8b2ee562b
125 rdf:rest Nb2257853f32f4bdf8152463d903cdb19
126 Ndb68fc7994b445fc8255e1b502c8c0d3 schema:name Springer Nature - SN SciGraph project
127 rdf:type schema:Organization
128 Ne0feb31233bf48cc89985dc157986560 rdf:first sg:person.016176475704.89
129 rdf:rest rdf:nil
130 Nf72244d74e9540bd891e101d0ba294fa schema:familyName Magnini
131 schema:givenName Bernardo
132 rdf:type schema:Person
133 Nf86512088a9240a88b04660d069106c8 rdf:first sg:person.07552063233.67
134 rdf:rest Nbf8d78e2cedc482e9684fd2363a79ffb
135 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
136 schema:name Information and Computing Sciences
137 rdf:type schema:DefinedTerm
138 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
139 schema:name Artificial Intelligence and Image Processing
140 rdf:type schema:DefinedTerm
141 sg:person.016176475704.89 schema:affiliation grid-institutes:grid.5801.c
142 schema:familyName Ruch
143 schema:givenName Patrick
144 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016176475704.89
145 rdf:type schema:Person
146 sg:person.0600360343.20 schema:affiliation grid-institutes:grid.150338.c
147 schema:familyName Geissbühler
148 schema:givenName Antoine
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0600360343.20
150 rdf:type schema:Person
151 sg:person.07552063233.67 schema:affiliation grid-institutes:grid.150338.c
152 schema:familyName Müller
153 schema:givenName Henning
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07552063233.67
155 rdf:type schema:Person
156 grid-institutes:grid.150338.c schema:alternateName Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland
157 schema:name Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland
158 rdf:type schema:Organization
159 grid-institutes:grid.5801.c schema:alternateName Swiss Federal Institute of Technology, LITH, IN-Ecublens, CH-1015, Lausanne, Switzerland
160 schema:name Service of Medical Informatics, University and University Hospitals of Geneva, 21 Rue Micheli-du-Crest, CH-1211, Geneva 4, Switzerland
161 Swiss Federal Institute of Technology, LITH, IN-Ecublens, CH-1015, Lausanne, Switzerland
162 rdf:type schema:Organization
 




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


...