Deep Learning Based Automatic Segmentation of Pathological Kidney in CT: Local Versus Global Image Context View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2017-07-14

AUTHORS

Yefeng Zheng , David Liu , Bogdan Georgescu , Daguang Xu , Dorin Comaniciu

ABSTRACT

Chronickidneydiseaseaffectsone of every ten adults in USA (over 20 million). Computed tomography (CT) is a widely used imaging modality for kidney disease diagnosis and quantification. However, automatic pathological kidney segmentation is still a challenging task due to large variations in contrast phase, scanning range, pathology, and position in the abdomen, etc. Methods based on global image context (e.g., atlas- or regression-based approaches) do not work well. In this work, we propose to combine deep learning and marginal space learning (MSL), both using local context, for robust kidney detection and segmentation. Here, deep learning is exploited to roughly estimate the kidney center. Instead of performing a whole axial slice classification (i.e., whether it contains a kidney), we detect local image patches containing a kidney. The detected patches are aggregated to generate an estimate of the kidney center. Afterwards, we apply MSL to further refine the pose estimate by constraining the position search to a neighborhood around the initial center. The kidney is then segmented using a discriminative active shape model. The proposed method has been trained on 370 CT scans and tested on 78 unseen cases. It achieves a mean segmentation error of 2.6 and 1.7 mm for the left and right kidney, respectively. Furthermore, it eliminates all gross failures (i.e., segmentation is totally off) in a direct application of MSL. More... »

PAGES

241-255

Book

TITLE

Deep Learning and Convolutional Neural Networks for Medical Image Computing

ISBN

978-3-319-42998-4
978-3-319-42999-1

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-42999-1_14

DOI

http://dx.doi.org/10.1007/978-3-319-42999-1_14

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1090665949


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/2008/11", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Medical and Health 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"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1103", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Clinical Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zheng", 
        "givenName": "Yefeng", 
        "id": "sg:person.0767211426.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0767211426.21"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Liu", 
        "givenName": "David", 
        "id": "sg:person.0673243411.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0673243411.05"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthcare, 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 Healthcare, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Xu", 
        "givenName": "Daguang", 
        "id": "sg:person.016547172265.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016547172265.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthcare, 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": "2017-07-14", 
    "datePublishedReg": "2017-07-14", 
    "description": "Chronickidneydiseaseaffectsone of every ten adults in USA (over 20 million). Computed tomography (CT) is a widely used imaging modality for kidney disease diagnosis and quantification. However, automatic pathological kidney segmentation is still a challenging task due to large variations in contrast phase, scanning range, pathology, and position in the abdomen, etc. Methods based on global image context (e.g., atlas- or regression-based approaches) do not work well. In this work, we propose to combine deep learning and marginal space learning (MSL), both using local context, for robust kidney detection and segmentation. Here, deep learning is exploited to roughly estimate the kidney center. Instead of performing a whole axial slice classification (i.e., whether it contains a kidney), we detect local image patches containing a kidney. The detected patches are aggregated to generate an estimate of the kidney center. Afterwards, we apply MSL to further refine the pose estimate by constraining the position search to a neighborhood around the initial center. The kidney is then segmented using a discriminative active shape model. The proposed method has been trained on 370 CT scans and tested on 78 unseen cases. It achieves a mean segmentation error of 2.6 and 1.7\u00a0mm for the left and right kidney, respectively. Furthermore, it eliminates all gross failures (i.e., segmentation is totally off) in a direct application of MSL.", 
    "editor": [
      {
        "familyName": "Lu", 
        "givenName": "Le", 
        "type": "Person"
      }, 
      {
        "familyName": "Zheng", 
        "givenName": "Yefeng", 
        "type": "Person"
      }, 
      {
        "familyName": "Carneiro", 
        "givenName": "Gustavo", 
        "type": "Person"
      }, 
      {
        "familyName": "Yang", 
        "givenName": "Lin", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-42999-1_14", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-42998-4", 
        "978-3-319-42999-1"
      ], 
      "name": "Deep Learning and Convolutional Neural Networks for Medical Image Computing", 
      "type": "Book"
    }, 
    "keywords": [
      "marginal space learning", 
      "global image context", 
      "deep learning", 
      "image context", 
      "mean segmentation error", 
      "local image patches", 
      "Active Shape Model", 
      "slice classification", 
      "kidney detection", 
      "pose estimates", 
      "position search", 
      "space learning", 
      "kidney segmentation", 
      "image patches", 
      "automatic segmentation", 
      "segmentation errors", 
      "initial centers", 
      "unseen cases", 
      "challenging task", 
      "shape model", 
      "segmentation", 
      "kidney disease diagnosis", 
      "learning", 
      "disease diagnosis", 
      "contrast phases", 
      "pathological kidney", 
      "direct application", 
      "task", 
      "context", 
      "classification", 
      "search", 
      "applications", 
      "method", 
      "error", 
      "detection", 
      "imaging modalities", 
      "local context", 
      "work", 
      "neighborhood", 
      "computed tomography", 
      "patches", 
      "model", 
      "Kidney Center", 
      "center", 
      "position", 
      "right kidney", 
      "large variation", 
      "CT scan", 
      "estimates", 
      "kidney", 
      "locals", 
      "modalities", 
      "gross failure", 
      "scans", 
      "cases", 
      "failure", 
      "scanning range", 
      "phase", 
      "abdomen", 
      "diagnosis", 
      "pathology", 
      "tomography", 
      "adults", 
      "range", 
      "quantification", 
      "variation", 
      "USA", 
      "automatic pathological kidney segmentation", 
      "pathological kidney segmentation", 
      "robust kidney detection", 
      "whole axial slice classification", 
      "axial slice classification", 
      "discriminative active shape model"
    ], 
    "name": "Deep Learning Based Automatic Segmentation of Pathological Kidney in CT: Local Versus Global Image Context", 
    "pagination": "241-255", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1090665949"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-42999-1_14"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-42999-1_14", 
      "https://app.dimensions.ai/details/publication/pub.1090665949"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:17", 
    "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_296.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-42999-1_14"
  }
]
 

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.10.1007/978-3-319-42999-1_14'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-42999-1_14'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-42999-1_14'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-42999-1_14'


 

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

184 TRIPLES      23 PREDICATES      100 URIs      91 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-42999-1_14 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:11
4 anzsrc-for:1103
5 schema:author N02d3fe72e5d44e7994481779af617e57
6 schema:datePublished 2017-07-14
7 schema:datePublishedReg 2017-07-14
8 schema:description Chronickidneydiseaseaffectsone of every ten adults in USA (over 20 million). Computed tomography (CT) is a widely used imaging modality for kidney disease diagnosis and quantification. However, automatic pathological kidney segmentation is still a challenging task due to large variations in contrast phase, scanning range, pathology, and position in the abdomen, etc. Methods based on global image context (e.g., atlas- or regression-based approaches) do not work well. In this work, we propose to combine deep learning and marginal space learning (MSL), both using local context, for robust kidney detection and segmentation. Here, deep learning is exploited to roughly estimate the kidney center. Instead of performing a whole axial slice classification (i.e., whether it contains a kidney), we detect local image patches containing a kidney. The detected patches are aggregated to generate an estimate of the kidney center. Afterwards, we apply MSL to further refine the pose estimate by constraining the position search to a neighborhood around the initial center. The kidney is then segmented using a discriminative active shape model. The proposed method has been trained on 370 CT scans and tested on 78 unseen cases. It achieves a mean segmentation error of 2.6 and 1.7 mm for the left and right kidney, respectively. Furthermore, it eliminates all gross failures (i.e., segmentation is totally off) in a direct application of MSL.
9 schema:editor N41f610e69f064ffebb06db5b072b52c4
10 schema:genre chapter
11 schema:inLanguage en
12 schema:isAccessibleForFree false
13 schema:isPartOf N65523baa38d6491ab86c14ab5414d284
14 schema:keywords Active Shape Model
15 CT scan
16 Kidney Center
17 USA
18 abdomen
19 adults
20 applications
21 automatic pathological kidney segmentation
22 automatic segmentation
23 axial slice classification
24 cases
25 center
26 challenging task
27 classification
28 computed tomography
29 context
30 contrast phases
31 deep learning
32 detection
33 diagnosis
34 direct application
35 discriminative active shape model
36 disease diagnosis
37 error
38 estimates
39 failure
40 global image context
41 gross failure
42 image context
43 image patches
44 imaging modalities
45 initial centers
46 kidney
47 kidney detection
48 kidney disease diagnosis
49 kidney segmentation
50 large variation
51 learning
52 local context
53 local image patches
54 locals
55 marginal space learning
56 mean segmentation error
57 method
58 modalities
59 model
60 neighborhood
61 patches
62 pathological kidney
63 pathological kidney segmentation
64 pathology
65 phase
66 pose estimates
67 position
68 position search
69 quantification
70 range
71 right kidney
72 robust kidney detection
73 scanning range
74 scans
75 search
76 segmentation
77 segmentation errors
78 shape model
79 slice classification
80 space learning
81 task
82 tomography
83 unseen cases
84 variation
85 whole axial slice classification
86 work
87 schema:name Deep Learning Based Automatic Segmentation of Pathological Kidney in CT: Local Versus Global Image Context
88 schema:pagination 241-255
89 schema:productId N54e948fb605d468f89c9ed07077b9f6f
90 N9b71f6199f6d4091900e9bd7aaa7d6eb
91 schema:publisher N1da5164e14614d9b97afc083a36249ae
92 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090665949
93 https://doi.org/10.1007/978-3-319-42999-1_14
94 schema:sdDatePublished 2022-01-01T19:17
95 schema:sdLicense https://scigraph.springernature.com/explorer/license/
96 schema:sdPublisher Nf41167392a58445e9ef3d1a57ff5eb32
97 schema:url https://doi.org/10.1007/978-3-319-42999-1_14
98 sgo:license sg:explorer/license/
99 sgo:sdDataset chapters
100 rdf:type schema:Chapter
101 N02d3fe72e5d44e7994481779af617e57 rdf:first sg:person.0767211426.21
102 rdf:rest N88a62564a86c4309a7dd4cc7ff4e6749
103 N1da5164e14614d9b97afc083a36249ae schema:name Springer Nature
104 rdf:type schema:Organisation
105 N24debb6e0b974560a8791415a2a3ef80 rdf:first sg:person.01066111014.77
106 rdf:rest rdf:nil
107 N3778f0ba46a24f9a844a81eb0157d977 schema:familyName Lu
108 schema:givenName Le
109 rdf:type schema:Person
110 N41f610e69f064ffebb06db5b072b52c4 rdf:first N3778f0ba46a24f9a844a81eb0157d977
111 rdf:rest N6b845334f5f24bab9186b4ba6c3feb99
112 N54e948fb605d468f89c9ed07077b9f6f schema:name dimensions_id
113 schema:value pub.1090665949
114 rdf:type schema:PropertyValue
115 N65523baa38d6491ab86c14ab5414d284 schema:isbn 978-3-319-42998-4
116 978-3-319-42999-1
117 schema:name Deep Learning and Convolutional Neural Networks for Medical Image Computing
118 rdf:type schema:Book
119 N6b845334f5f24bab9186b4ba6c3feb99 rdf:first Na9056f32d2504d5589d7c0bf886f4b50
120 rdf:rest Nf5bde2079d664974bb436fb72961b2cf
121 N8344bcedafba4fe1aec607490eed53c8 schema:familyName Carneiro
122 schema:givenName Gustavo
123 rdf:type schema:Person
124 N8669b3056c19432bb22c911591aa0c49 rdf:first sg:person.016547172265.81
125 rdf:rest N24debb6e0b974560a8791415a2a3ef80
126 N88a62564a86c4309a7dd4cc7ff4e6749 rdf:first sg:person.0673243411.05
127 rdf:rest Nbf51bb92547d4b84b085af18ae27d9ae
128 N9b71f6199f6d4091900e9bd7aaa7d6eb schema:name doi
129 schema:value 10.1007/978-3-319-42999-1_14
130 rdf:type schema:PropertyValue
131 Na9056f32d2504d5589d7c0bf886f4b50 schema:familyName Zheng
132 schema:givenName Yefeng
133 rdf:type schema:Person
134 Nbf51bb92547d4b84b085af18ae27d9ae rdf:first sg:person.0703547214.37
135 rdf:rest N8669b3056c19432bb22c911591aa0c49
136 Nc786863edd374d0f8106fa6642700ccd schema:familyName Yang
137 schema:givenName Lin
138 rdf:type schema:Person
139 Ne359d524aaca49018045cb7912392982 rdf:first Nc786863edd374d0f8106fa6642700ccd
140 rdf:rest rdf:nil
141 Nf41167392a58445e9ef3d1a57ff5eb32 schema:name Springer Nature - SN SciGraph project
142 rdf:type schema:Organization
143 Nf5bde2079d664974bb436fb72961b2cf rdf:first N8344bcedafba4fe1aec607490eed53c8
144 rdf:rest Ne359d524aaca49018045cb7912392982
145 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
146 schema:name Information and Computing Sciences
147 rdf:type schema:DefinedTerm
148 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
149 schema:name Artificial Intelligence and Image Processing
150 rdf:type schema:DefinedTerm
151 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
152 schema:name Medical and Health Sciences
153 rdf:type schema:DefinedTerm
154 anzsrc-for:1103 schema:inDefinedTermSet anzsrc-for:
155 schema:name Clinical Sciences
156 rdf:type schema:DefinedTerm
157 sg:person.01066111014.77 schema:affiliation grid-institutes:grid.415886.6
158 schema:familyName Comaniciu
159 schema:givenName Dorin
160 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066111014.77
161 rdf:type schema:Person
162 sg:person.016547172265.81 schema:affiliation grid-institutes:grid.415886.6
163 schema:familyName Xu
164 schema:givenName Daguang
165 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016547172265.81
166 rdf:type schema:Person
167 sg:person.0673243411.05 schema:affiliation grid-institutes:grid.415886.6
168 schema:familyName Liu
169 schema:givenName David
170 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0673243411.05
171 rdf:type schema:Person
172 sg:person.0703547214.37 schema:affiliation grid-institutes:grid.415886.6
173 schema:familyName Georgescu
174 schema:givenName Bogdan
175 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703547214.37
176 rdf:type schema:Person
177 sg:person.0767211426.21 schema:affiliation grid-institutes:grid.415886.6
178 schema:familyName Zheng
179 schema:givenName Yefeng
180 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0767211426.21
181 rdf:type schema:Person
182 grid-institutes:grid.415886.6 schema:alternateName Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA
183 schema:name Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ, USA
184 rdf:type schema:Organization
 




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


...