Multiple sclerosis lesion detection with local multimodal Markovian analysis and cellular automata ‘GrowCut’ View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2014-01-10

AUTHORS

Daniel Biediger, Christophe Collet, Jean‐Paul Armspach

ABSTRACT

Multiple sclerosis affect over 2.5 million people world‐wide. This autoimmune disease of the central nervous system causes damage to the insulating myelin sheaths around the axons in the brain. The disease progresses at different rates in different people and can have periods of remission and relapse. A fast and accurate method for evaluating the number and size of MS lesions in the brain is a key component in evaluating the progress of the disease and the efficacy of treatments. Manual segmentation is slow and difficult and the results can be somewhat subjective. It requires a physician to consider several MRI slices across multiple modalities. The power and speed of computer systems provide an obvious avenue to help. While many automated methods exist, they have not reached human‐level accuracy of the segmentation results. There exists a need for a robust, fast and accurate method to improve the results of automatic MS lesion segmentation methods. We propose a post‐processing stage to improve the segmentation results of an existing system. It uses two different strategies to improve the segmentation results of an automated system based on whole‐brain tissue classification and lesion detection. The first strategy leverages the current processing system at a granularity finer than the whole brain to detect lesions at a local level. This reflects the way that a physician considers only a part of the brain at a time. It then combines the series of local results to produce a whole‐brain segmentation. This approach better captures the local lesion properties and produces encouraging results, with a general improvement in the detection rate of lesions. The second method dives deeper and looks at the individual voxel level. Just as a physician might look more closely at a lesion, it considers the local neighborhood around a lesion detection. The method selects seed points from the existing results and uses a region growing method based on cellular automata. It grows the lesion areas based on a local neighborhood similarity in intensity. Over the eleven patients examined, some results improved over the base case and show the efficiency of the proposed approach. More... »

PAGES

3

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1186/2194-3990-1-3

DOI

http://dx.doi.org/10.1186/2194-3990-1-3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1046415098


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/2008/11", 
        "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/2008/1109", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Neurosciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Computer Sciences Department, University of Houston, PGH 550E, 77204\u20103010, Houston, TX, USA", 
          "id": "http://www.grid.ac/institutes/grid.266436.3", 
          "name": [
            "iCube Lab \u2010 Universit\u00e9 de Strasbourg \u2010 CNRS UMR 7357, 300 Bd S\u00e9bastien Brant, CS 10413, 67412, Illkirch Cedex, France", 
            "Computer Sciences Department, University of Houston, PGH 550E, 77204\u20103010, Houston, TX, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Biediger", 
        "givenName": "Daniel", 
        "id": "sg:person.012771476567.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012771476567.25"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "iCube Lab \u2010 Universit\u00e9 de Strasbourg \u2010 CNRS UMR 7357, 300 Bd S\u00e9bastien Brant, CS 10413, 67412, Illkirch Cedex, France", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "iCube Lab \u2010 Universit\u00e9 de Strasbourg \u2010 CNRS UMR 7357, 300 Bd S\u00e9bastien Brant, CS 10413, 67412, Illkirch Cedex, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Collet", 
        "givenName": "Christophe", 
        "id": "sg:person.016514261355.97", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016514261355.97"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "iCube Lab \u2010 Universit\u00e9 de Strasbourg \u2010 CNRS UMR 7357, 300 Bd S\u00e9bastien Brant, CS 10413, 67412, Illkirch Cedex, France", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "iCube Lab \u2010 Universit\u00e9 de Strasbourg \u2010 CNRS UMR 7357, 300 Bd S\u00e9bastien Brant, CS 10413, 67412, Illkirch Cedex, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Armspach", 
        "givenName": "Jean\u2010Paul", 
        "id": "sg:person.01063426463.53", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01063426463.53"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s00234-011-0886-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048776620", 
          "https://doi.org/10.1007/s00234-011-0886-7"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2014-01-10", 
    "datePublishedReg": "2014-01-10", 
    "description": "Multiple sclerosis affect over 2.5 million people world\u2010wide. This autoimmune disease of the central nervous system causes damage to the insulating myelin sheaths around the axons in the brain. The disease progresses at different rates in different people and can have periods of remission and relapse. A fast and accurate method for evaluating the number and size of MS lesions in the brain is a key component in evaluating the progress of the disease and the efficacy of treatments. Manual segmentation is slow and difficult and the results can be somewhat subjective. It requires a physician to consider several MRI slices across multiple modalities. The power and speed of computer systems provide an obvious avenue to help. While many automated methods exist, they have not reached human\u2010level accuracy of the segmentation results. There exists a need for a robust, fast and accurate method to improve the results of automatic MS lesion segmentation methods. We propose a post\u2010processing stage to improve the segmentation results of an existing system. It uses two different strategies to improve the segmentation results of an automated system based on whole\u2010brain tissue classification and lesion detection. The first strategy leverages the current processing system at a granularity finer than the whole brain to detect lesions at a local level. This reflects the way that a physician considers only a part of the brain at a time. It then combines the series of local results to produce a whole\u2010brain segmentation. This approach better captures the local lesion properties and produces encouraging results, with a general improvement in the detection rate of lesions. The second method dives deeper and looks at the individual voxel level. Just as a physician might look more closely at a lesion, it considers the local neighborhood around a lesion detection. The method selects seed points from the existing results and uses a region growing method based on cellular automata. It grows the lesion areas based on a local neighborhood similarity in intensity. Over the eleven patients examined, some results improved over the base case and show the efficiency of the proposed approach.", 
    "genre": "article", 
    "id": "sg:pub.10.1186/2194-3990-1-3", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1052069", 
        "issn": [
          "2194-3990"
        ], 
        "name": "Journal of Computational Surgery", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "1"
      }
    ], 
    "keywords": [
      "periods of remission", 
      "efficacy of treatment", 
      "lesion detection", 
      "central nervous system", 
      "multiple sclerosis", 
      "autoimmune diseases", 
      "MS lesions", 
      "whole brain", 
      "nervous system", 
      "lesion area", 
      "lesions", 
      "whole-brain segmentation", 
      "myelin sheath", 
      "brain", 
      "disease", 
      "physicians", 
      "people world", 
      "lesion properties", 
      "Multiple Sclerosis Lesion Detection", 
      "MS lesion segmentation methods", 
      "detection rate", 
      "MRI slices", 
      "voxel level", 
      "individual voxel level", 
      "general improvement", 
      "encouraging results", 
      "remission", 
      "relapse", 
      "sclerosis", 
      "patients", 
      "axons", 
      "accurate method", 
      "multiple modalities", 
      "efficacy", 
      "modalities", 
      "treatment", 
      "levels", 
      "rate", 
      "lesion segmentation methods", 
      "slices", 
      "damage", 
      "manual segmentation", 
      "obvious avenue", 
      "sheath", 
      "period", 
      "detection", 
      "results", 
      "key component", 
      "strategies", 
      "cases", 
      "different rates", 
      "improvement", 
      "base case", 
      "people", 
      "different strategies", 
      "need", 
      "stage", 
      "method", 
      "classification", 
      "number", 
      "time", 
      "tissue classification", 
      "area", 
      "avenues", 
      "series", 
      "analysis", 
      "progress", 
      "system", 
      "local level", 
      "part", 
      "approach", 
      "intensity", 
      "region", 
      "components", 
      "first strategy", 
      "size", 
      "point", 
      "local results", 
      "similarity", 
      "different people", 
      "world", 
      "accuracy", 
      "way", 
      "neighborhood", 
      "properties", 
      "segmentation", 
      "seed points", 
      "human-level accuracy", 
      "speed", 
      "segmentation results", 
      "segmentation method", 
      "computer systems", 
      "Markovian analysis", 
      "power", 
      "post-processing stage", 
      "efficiency", 
      "GrowCut", 
      "second method", 
      "neighborhood similarity", 
      "processing system", 
      "local neighborhood", 
      "cellular automata", 
      "granularity", 
      "automata", 
      "automatic MS lesion segmentation methods", 
      "whole\u2010brain tissue classification", 
      "current processing system", 
      "local lesion properties", 
      "local neighborhood similarity", 
      "sclerosis lesion detection", 
      "local multimodal Markovian analysis", 
      "multimodal Markovian analysis"
    ], 
    "name": "Multiple sclerosis lesion detection with local multimodal Markovian analysis and cellular automata \u2018GrowCut\u2019", 
    "pagination": "3", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1046415098"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1186/2194-3990-1-3"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1186/2194-3990-1-3", 
      "https://app.dimensions.ai/details/publication/pub.1046415098"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2021-11-01T18:23", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/article/article_649.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1186/2194-3990-1-3"
  }
]
 

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.10.1186/2194-3990-1-3'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/2194-3990-1-3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/2194-3990-1-3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/2194-3990-1-3'


 

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

191 TRIPLES      22 PREDICATES      138 URIs      129 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1186/2194-3990-1-3 schema:about anzsrc-for:11
2 anzsrc-for:1109
3 schema:author N6a46e8c21fae4e3ca6d8623bff3e5994
4 schema:citation sg:pub.10.1007/s00234-011-0886-7
5 schema:datePublished 2014-01-10
6 schema:datePublishedReg 2014-01-10
7 schema:description Multiple sclerosis affect over 2.5 million people world‐wide. This autoimmune disease of the central nervous system causes damage to the insulating myelin sheaths around the axons in the brain. The disease progresses at different rates in different people and can have periods of remission and relapse. A fast and accurate method for evaluating the number and size of MS lesions in the brain is a key component in evaluating the progress of the disease and the efficacy of treatments. Manual segmentation is slow and difficult and the results can be somewhat subjective. It requires a physician to consider several MRI slices across multiple modalities. The power and speed of computer systems provide an obvious avenue to help. While many automated methods exist, they have not reached human‐level accuracy of the segmentation results. There exists a need for a robust, fast and accurate method to improve the results of automatic MS lesion segmentation methods. We propose a post‐processing stage to improve the segmentation results of an existing system. It uses two different strategies to improve the segmentation results of an automated system based on whole‐brain tissue classification and lesion detection. The first strategy leverages the current processing system at a granularity finer than the whole brain to detect lesions at a local level. This reflects the way that a physician considers only a part of the brain at a time. It then combines the series of local results to produce a whole‐brain segmentation. This approach better captures the local lesion properties and produces encouraging results, with a general improvement in the detection rate of lesions. The second method dives deeper and looks at the individual voxel level. Just as a physician might look more closely at a lesion, it considers the local neighborhood around a lesion detection. The method selects seed points from the existing results and uses a region growing method based on cellular automata. It grows the lesion areas based on a local neighborhood similarity in intensity. Over the eleven patients examined, some results improved over the base case and show the efficiency of the proposed approach.
8 schema:genre article
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N27f8d657731e4c73bac33be9d2db32ac
12 N5c66abd9bccc4e20a42494a7c02cd947
13 sg:journal.1052069
14 schema:keywords GrowCut
15 MRI slices
16 MS lesion segmentation methods
17 MS lesions
18 Markovian analysis
19 Multiple Sclerosis Lesion Detection
20 accuracy
21 accurate method
22 analysis
23 approach
24 area
25 autoimmune diseases
26 automata
27 automatic MS lesion segmentation methods
28 avenues
29 axons
30 base case
31 brain
32 cases
33 cellular automata
34 central nervous system
35 classification
36 components
37 computer systems
38 current processing system
39 damage
40 detection
41 detection rate
42 different people
43 different rates
44 different strategies
45 disease
46 efficacy
47 efficacy of treatment
48 efficiency
49 encouraging results
50 first strategy
51 general improvement
52 granularity
53 human-level accuracy
54 improvement
55 individual voxel level
56 intensity
57 key component
58 lesion area
59 lesion detection
60 lesion properties
61 lesion segmentation methods
62 lesions
63 levels
64 local lesion properties
65 local level
66 local multimodal Markovian analysis
67 local neighborhood
68 local neighborhood similarity
69 local results
70 manual segmentation
71 method
72 modalities
73 multimodal Markovian analysis
74 multiple modalities
75 multiple sclerosis
76 myelin sheath
77 need
78 neighborhood
79 neighborhood similarity
80 nervous system
81 number
82 obvious avenue
83 part
84 patients
85 people
86 people world
87 period
88 periods of remission
89 physicians
90 point
91 post-processing stage
92 power
93 processing system
94 progress
95 properties
96 rate
97 region
98 relapse
99 remission
100 results
101 sclerosis
102 sclerosis lesion detection
103 second method
104 seed points
105 segmentation
106 segmentation method
107 segmentation results
108 series
109 sheath
110 similarity
111 size
112 slices
113 speed
114 stage
115 strategies
116 system
117 time
118 tissue classification
119 treatment
120 voxel level
121 way
122 whole brain
123 whole-brain segmentation
124 whole‐brain tissue classification
125 world
126 schema:name Multiple sclerosis lesion detection with local multimodal Markovian analysis and cellular automata ‘GrowCut’
127 schema:pagination 3
128 schema:productId N026b7e879cf647be9fe8884c22272e73
129 N07fc790d0ac64d449889798c260e2564
130 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046415098
131 https://doi.org/10.1186/2194-3990-1-3
132 schema:sdDatePublished 2021-11-01T18:23
133 schema:sdLicense https://scigraph.springernature.com/explorer/license/
134 schema:sdPublisher Nca045c2825b447f3a21ce8c9e46654a0
135 schema:url https://doi.org/10.1186/2194-3990-1-3
136 sgo:license sg:explorer/license/
137 sgo:sdDataset articles
138 rdf:type schema:ScholarlyArticle
139 N026b7e879cf647be9fe8884c22272e73 schema:name doi
140 schema:value 10.1186/2194-3990-1-3
141 rdf:type schema:PropertyValue
142 N07fc790d0ac64d449889798c260e2564 schema:name dimensions_id
143 schema:value pub.1046415098
144 rdf:type schema:PropertyValue
145 N27f8d657731e4c73bac33be9d2db32ac schema:volumeNumber 1
146 rdf:type schema:PublicationVolume
147 N5c66abd9bccc4e20a42494a7c02cd947 schema:issueNumber 1
148 rdf:type schema:PublicationIssue
149 N6a46e8c21fae4e3ca6d8623bff3e5994 rdf:first sg:person.012771476567.25
150 rdf:rest N943a0224659e4f7fb81017f4bc929af0
151 N8def889f3c43403bb86e7ebca5f3d1e8 rdf:first sg:person.01063426463.53
152 rdf:rest rdf:nil
153 N943a0224659e4f7fb81017f4bc929af0 rdf:first sg:person.016514261355.97
154 rdf:rest N8def889f3c43403bb86e7ebca5f3d1e8
155 Nca045c2825b447f3a21ce8c9e46654a0 schema:name Springer Nature - SN SciGraph project
156 rdf:type schema:Organization
157 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
158 schema:name Medical and Health Sciences
159 rdf:type schema:DefinedTerm
160 anzsrc-for:1109 schema:inDefinedTermSet anzsrc-for:
161 schema:name Neurosciences
162 rdf:type schema:DefinedTerm
163 sg:journal.1052069 schema:issn 2194-3990
164 schema:name Journal of Computational Surgery
165 schema:publisher Springer Nature
166 rdf:type schema:Periodical
167 sg:person.01063426463.53 schema:affiliation grid-institutes:None
168 schema:familyName Armspach
169 schema:givenName Jean‐Paul
170 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01063426463.53
171 rdf:type schema:Person
172 sg:person.012771476567.25 schema:affiliation grid-institutes:grid.266436.3
173 schema:familyName Biediger
174 schema:givenName Daniel
175 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012771476567.25
176 rdf:type schema:Person
177 sg:person.016514261355.97 schema:affiliation grid-institutes:None
178 schema:familyName Collet
179 schema:givenName Christophe
180 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016514261355.97
181 rdf:type schema:Person
182 sg:pub.10.1007/s00234-011-0886-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048776620
183 https://doi.org/10.1007/s00234-011-0886-7
184 rdf:type schema:CreativeWork
185 grid-institutes:None schema:alternateName iCube Lab ‐ Université de Strasbourg ‐ CNRS UMR 7357, 300 Bd Sébastien Brant, CS 10413, 67412, Illkirch Cedex, France
186 schema:name iCube Lab ‐ Université de Strasbourg ‐ CNRS UMR 7357, 300 Bd Sébastien Brant, CS 10413, 67412, Illkirch Cedex, France
187 rdf:type schema:Organization
188 grid-institutes:grid.266436.3 schema:alternateName Computer Sciences Department, University of Houston, PGH 550E, 77204‐3010, Houston, TX, USA
189 schema:name Computer Sciences Department, University of Houston, PGH 550E, 77204‐3010, Houston, TX, USA
190 iCube Lab ‐ Université de Strasbourg ‐ CNRS UMR 7357, 300 Bd Sébastien Brant, CS 10413, 67412, Illkirch Cedex, France
191 rdf:type schema:Organization
 




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


...