3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2016-10-02

AUTHORS

Özgün Çiçek , Ahmed Abdulkadir , Soeren S. Lienkamp , Thomas Brox , Olaf Ronneberger

ABSTRACT

This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the volume to be segmented. The network learns from these sparse annotations and provides a dense 3D segmentation. (2) In a fully-automated setup, we assume that a representative, sparsely annotated training set exists. Trained on this data set, the network densely segments new volumetric images. The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts. The implementation performs on-the-fly elastic deformations for efficient data augmentation during training. It is trained end-to-end from scratch, i.e., no pre-trained network is required. We test the performance of the proposed method on a complex, highly variable 3D structure, the Xenopus kidney, and achieve good results for both use cases. More... »

PAGES

424-432

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-46723-8_49

DOI

http://dx.doi.org/10.1007/978-3-319-46723-8_49

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1084908686


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": "BIOSS Centre for Biological Signalling Studies, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Computer Science Department, University of Freiburg, Freiburg, Germany", 
            "BIOSS Centre for Biological Signalling Studies, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "\u00c7i\u00e7ek", 
        "givenName": "\u00d6zg\u00fcn", 
        "id": "sg:person.016314276446.01", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016314276446.01"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Psychiatry and Psychotherapy, University Medical Center Freiburg, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.7708.8", 
          "name": [
            "Computer Science Department, University of Freiburg, Freiburg, Germany", 
            "Department of Psychiatry and Psychotherapy, University Medical Center Freiburg, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Abdulkadir", 
        "givenName": "Ahmed", 
        "id": "sg:person.0623123342.36", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0623123342.36"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University Hospital Freiburg, Renal Division, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "BIOSS Centre for Biological Signalling Studies, Freiburg, Germany", 
            "University Hospital Freiburg, Renal Division, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lienkamp", 
        "givenName": "Soeren S.", 
        "id": "sg:person.01235033065.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01235033065.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "BIOSS Centre for Biological Signalling Studies, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Computer Science Department, University of Freiburg, Freiburg, Germany", 
            "BIOSS Centre for Biological Signalling Studies, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Brox", 
        "givenName": "Thomas", 
        "id": "sg:person.012443225372.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Google DeepMind, London, UK", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Computer Science Department, University of Freiburg, Freiburg, Germany", 
            "BIOSS Centre for Biological Signalling Studies, Freiburg, Germany", 
            "Google DeepMind, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ronneberger", 
        "givenName": "Olaf", 
        "id": "sg:person.0625370723.52", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0625370723.52"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2016-10-02", 
    "datePublishedReg": "2016-10-02", 
    "description": "This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the volume to be segmented. The network learns from these sparse annotations and provides a dense 3D segmentation. (2) In a fully-automated setup, we assume that a representative, sparsely annotated training set exists. Trained on this data set, the network densely segments new volumetric images. The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts. The implementation performs on-the-fly elastic deformations for efficient data augmentation during training. It is trained end-to-end from scratch, i.e., no pre-trained network is required. We test the performance of the proposed method on a complex, highly variable 3D structure, the Xenopus kidney, and achieve good results for both use cases.", 
    "editor": [
      {
        "familyName": "Ourselin", 
        "givenName": "Sebastien", 
        "type": "Person"
      }, 
      {
        "familyName": "Joskowicz", 
        "givenName": "Leo", 
        "type": "Person"
      }, 
      {
        "familyName": "Sabuncu", 
        "givenName": "Mert R.", 
        "type": "Person"
      }, 
      {
        "familyName": "Unal", 
        "givenName": "Gozde", 
        "type": "Person"
      }, 
      {
        "familyName": "Wells", 
        "givenName": "William", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-46723-8_49", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-46722-1", 
        "978-3-319-46723-8"
      ], 
      "name": "Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2016", 
      "type": "Book"
    }, 
    "keywords": [
      "use cases", 
      "sparse annotations", 
      "volumetric segmentation", 
      "volumetric images", 
      "pre-trained network", 
      "efficient data augmentation", 
      "attractive use cases", 
      "data augmentation", 
      "Net architecture", 
      "U-Net", 
      "segmentation", 
      "network", 
      "data sets", 
      "annotation", 
      "images", 
      "set exists", 
      "better results", 
      "users", 
      "architecture", 
      "scratch", 
      "implementation", 
      "setup", 
      "set", 
      "method", 
      "performance", 
      "operation", 
      "training", 
      "end", 
      "augmentation", 
      "slices", 
      "et al", 
      "results", 
      "cases", 
      "Xenopus kidney", 
      "structure", 
      "exists", 
      "counterparts", 
      "volume", 
      "representatives", 
      "al", 
      "elastic deformation", 
      "deformation", 
      "paper", 
      "kidney"
    ], 
    "name": "3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation", 
    "pagination": "424-432", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1084908686"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-46723-8_49"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-46723-8_49", 
      "https://app.dimensions.ai/details/publication/pub.1084908686"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:50", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_30.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-46723-8_49"
  }
]
 

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.10.1007/978-3-319-46723-8_49'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46723-8_49'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46723-8_49'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46723-8_49'


 

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

163 TRIPLES      22 PREDICATES      68 URIs      61 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-46723-8_49 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nd7b725ac3cad43e2b140ef029f57ea5d
4 schema:datePublished 2016-10-02
5 schema:datePublishedReg 2016-10-02
6 schema:description This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the volume to be segmented. The network learns from these sparse annotations and provides a dense 3D segmentation. (2) In a fully-automated setup, we assume that a representative, sparsely annotated training set exists. Trained on this data set, the network densely segments new volumetric images. The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts. The implementation performs on-the-fly elastic deformations for efficient data augmentation during training. It is trained end-to-end from scratch, i.e., no pre-trained network is required. We test the performance of the proposed method on a complex, highly variable 3D structure, the Xenopus kidney, and achieve good results for both use cases.
7 schema:editor N3840dd5f8e6e4f79a4f29b14c128faac
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N6325dce2ae6e42738cf7421ca169dcf5
11 schema:keywords Net architecture
12 U-Net
13 Xenopus kidney
14 al
15 annotation
16 architecture
17 attractive use cases
18 augmentation
19 better results
20 cases
21 counterparts
22 data augmentation
23 data sets
24 deformation
25 efficient data augmentation
26 elastic deformation
27 end
28 et al
29 exists
30 images
31 implementation
32 kidney
33 method
34 network
35 operation
36 paper
37 performance
38 pre-trained network
39 representatives
40 results
41 scratch
42 segmentation
43 set
44 set exists
45 setup
46 slices
47 sparse annotations
48 structure
49 training
50 use cases
51 users
52 volume
53 volumetric images
54 volumetric segmentation
55 schema:name 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
56 schema:pagination 424-432
57 schema:productId Nd6036f7746904d70958fe176581defe8
58 Nfd3c4e59ce7a4d5b83daf9f5847ff6b9
59 schema:publisher N368c93a73c844c8cb64b44b69f70dec3
60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084908686
61 https://doi.org/10.1007/978-3-319-46723-8_49
62 schema:sdDatePublished 2022-12-01T06:50
63 schema:sdLicense https://scigraph.springernature.com/explorer/license/
64 schema:sdPublisher Na617de757e9c4db1903f6b21b12c98f9
65 schema:url https://doi.org/10.1007/978-3-319-46723-8_49
66 sgo:license sg:explorer/license/
67 sgo:sdDataset chapters
68 rdf:type schema:Chapter
69 N368c93a73c844c8cb64b44b69f70dec3 schema:name Springer Nature
70 rdf:type schema:Organisation
71 N3840dd5f8e6e4f79a4f29b14c128faac rdf:first Nea668120fe6b463c9ce30f43bdddee8b
72 rdf:rest N50c78048ffca408cbc20076ae0a7b350
73 N4136f79816f24978b0999a8019e8fdde rdf:first sg:person.0625370723.52
74 rdf:rest rdf:nil
75 N50c78048ffca408cbc20076ae0a7b350 rdf:first N6bf1ed6970cb4a579d6cdada7dc8eb16
76 rdf:rest Nc2607a0da4784175a700584a5143abfc
77 N6325dce2ae6e42738cf7421ca169dcf5 schema:isbn 978-3-319-46722-1
78 978-3-319-46723-8
79 schema:name Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016
80 rdf:type schema:Book
81 N6bf1ed6970cb4a579d6cdada7dc8eb16 schema:familyName Joskowicz
82 schema:givenName Leo
83 rdf:type schema:Person
84 N7bab0ae1b62f42d49c4489535b9e2104 rdf:first sg:person.0623123342.36
85 rdf:rest Nb6cb93abce90419a963e868a938b7d55
86 N8421acc3aec84b93af2090dbc8cd0c85 rdf:first Nfe618165b2d74fba85d48b23d2e9c957
87 rdf:rest rdf:nil
88 N8cbf86c0ad8f4993a1406a0db84dc54f rdf:first sg:person.012443225372.65
89 rdf:rest N4136f79816f24978b0999a8019e8fdde
90 Na617de757e9c4db1903f6b21b12c98f9 schema:name Springer Nature - SN SciGraph project
91 rdf:type schema:Organization
92 Naa310036896e4593bfbd13957e4d1be4 rdf:first Nb710e0d8d2214b6ba32b83e20ebd8bbd
93 rdf:rest N8421acc3aec84b93af2090dbc8cd0c85
94 Nb527e4a45a4f4d409e5d6bfb0d5f9281 schema:familyName Sabuncu
95 schema:givenName Mert R.
96 rdf:type schema:Person
97 Nb6cb93abce90419a963e868a938b7d55 rdf:first sg:person.01235033065.65
98 rdf:rest N8cbf86c0ad8f4993a1406a0db84dc54f
99 Nb710e0d8d2214b6ba32b83e20ebd8bbd schema:familyName Unal
100 schema:givenName Gozde
101 rdf:type schema:Person
102 Nc2607a0da4784175a700584a5143abfc rdf:first Nb527e4a45a4f4d409e5d6bfb0d5f9281
103 rdf:rest Naa310036896e4593bfbd13957e4d1be4
104 Nd6036f7746904d70958fe176581defe8 schema:name dimensions_id
105 schema:value pub.1084908686
106 rdf:type schema:PropertyValue
107 Nd7b725ac3cad43e2b140ef029f57ea5d rdf:first sg:person.016314276446.01
108 rdf:rest N7bab0ae1b62f42d49c4489535b9e2104
109 Nea668120fe6b463c9ce30f43bdddee8b schema:familyName Ourselin
110 schema:givenName Sebastien
111 rdf:type schema:Person
112 Nfd3c4e59ce7a4d5b83daf9f5847ff6b9 schema:name doi
113 schema:value 10.1007/978-3-319-46723-8_49
114 rdf:type schema:PropertyValue
115 Nfe618165b2d74fba85d48b23d2e9c957 schema:familyName Wells
116 schema:givenName William
117 rdf:type schema:Person
118 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
119 schema:name Information and Computing Sciences
120 rdf:type schema:DefinedTerm
121 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
122 schema:name Artificial Intelligence and Image Processing
123 rdf:type schema:DefinedTerm
124 sg:person.01235033065.65 schema:affiliation grid-institutes:grid.5963.9
125 schema:familyName Lienkamp
126 schema:givenName Soeren S.
127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01235033065.65
128 rdf:type schema:Person
129 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
130 schema:familyName Brox
131 schema:givenName Thomas
132 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
133 rdf:type schema:Person
134 sg:person.016314276446.01 schema:affiliation grid-institutes:grid.5963.9
135 schema:familyName Çiçek
136 schema:givenName Özgün
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016314276446.01
138 rdf:type schema:Person
139 sg:person.0623123342.36 schema:affiliation grid-institutes:grid.7708.8
140 schema:familyName Abdulkadir
141 schema:givenName Ahmed
142 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0623123342.36
143 rdf:type schema:Person
144 sg:person.0625370723.52 schema:affiliation grid-institutes:None
145 schema:familyName Ronneberger
146 schema:givenName Olaf
147 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0625370723.52
148 rdf:type schema:Person
149 grid-institutes:None schema:alternateName Google DeepMind, London, UK
150 schema:name BIOSS Centre for Biological Signalling Studies, Freiburg, Germany
151 Computer Science Department, University of Freiburg, Freiburg, Germany
152 Google DeepMind, London, UK
153 rdf:type schema:Organization
154 grid-institutes:grid.5963.9 schema:alternateName BIOSS Centre for Biological Signalling Studies, Freiburg, Germany
155 University Hospital Freiburg, Renal Division, Faculty of Medicine, University of Freiburg, Freiburg, Germany
156 schema:name BIOSS Centre for Biological Signalling Studies, Freiburg, Germany
157 Computer Science Department, University of Freiburg, Freiburg, Germany
158 University Hospital Freiburg, Renal Division, Faculty of Medicine, University of Freiburg, Freiburg, Germany
159 rdf:type schema:Organization
160 grid-institutes:grid.7708.8 schema:alternateName Department of Psychiatry and Psychotherapy, University Medical Center Freiburg, Freiburg, Germany
161 schema:name Computer Science Department, University of Freiburg, Freiburg, Germany
162 Department of Psychiatry and Psychotherapy, University Medical Center Freiburg, Freiburg, Germany
163 rdf:type schema:Organization
 




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


...