Deep Active Lesion Segmentation View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2019-10-10

AUTHORS

Ali Hatamizadeh , Assaf Hoogi , Debleena Sengupta , Wuyue Lu , Brian Wilcox , Daniel Rubin , Demetri Terzopoulos

ABSTRACT

Lesion segmentation is an important problem in computer-assisted diagnosis that remains challenging due to the prevalence of low contrast, irregular boundaries that are unamenable to shape priors. We introduce Deep Active Lesion Segmentation (DALS), a fully automated segmentation framework that leverages the powerful nonlinear feature extraction abilities of fully Convolutional Neural Networks (CNNs) and the precise boundary delineation abilities of Active Contour Models (ACMs). Our DALS framework benefits from an improved level-set ACM formulation with a per-pixel-parameterized energy functional and a novel multiscale encoder-decoder CNN that learns an initialization probability map along with parameter maps for the ACM. We evaluate our lesion segmentation model on a new Multiorgan Lesion Segmentation (MLS) dataset that contains images of various organs, including brain, liver, and lung, across different imaging modalities—MR and CT. Our results demonstrate favorable performance compared to competing methods, especially for small training datasets. More... »

PAGES

98-105

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_12

DOI

http://dx.doi.org/10.1007/978-3-030-32692-0_12

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1121623477


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": "Computer Science Department, University of California, Los Angeles, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.19006.3e", 
          "name": [
            "Computer Science Department, University of California, Los Angeles, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hatamizadeh", 
        "givenName": "Ali", 
        "id": "sg:person.015555505250.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015555505250.21"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Biomedical Data Science, Stanford University, Stanford, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.168010.e", 
          "name": [
            "Department of Biomedical Data Science, Stanford University, Stanford, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hoogi", 
        "givenName": "Assaf", 
        "id": "sg:person.01066717720.27", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066717720.27"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Department, University of California, Los Angeles, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.19006.3e", 
          "name": [
            "Computer Science Department, University of California, Los Angeles, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sengupta", 
        "givenName": "Debleena", 
        "id": "sg:person.07635752745.18", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07635752745.18"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Department, University of California, Los Angeles, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.19006.3e", 
          "name": [
            "Computer Science Department, University of California, Los Angeles, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lu", 
        "givenName": "Wuyue", 
        "id": "sg:person.010433333345.19", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010433333345.19"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Biomedical Data Science, Stanford University, Stanford, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.168010.e", 
          "name": [
            "Department of Biomedical Data Science, Stanford University, Stanford, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wilcox", 
        "givenName": "Brian", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Biomedical Data Science, Stanford University, Stanford, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.168010.e", 
          "name": [
            "Department of Biomedical Data Science, Stanford University, Stanford, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Rubin", 
        "givenName": "Daniel", 
        "id": "sg:person.01037031400.36", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01037031400.36"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Department, University of California, Los Angeles, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.19006.3e", 
          "name": [
            "Computer Science Department, University of California, Los Angeles, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Terzopoulos", 
        "givenName": "Demetri", 
        "id": "sg:person.016347323445.35", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016347323445.35"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2019-10-10", 
    "datePublishedReg": "2019-10-10", 
    "description": "Lesion segmentation is an important problem in computer-assisted diagnosis that remains challenging due to the prevalence of low contrast, irregular boundaries that are unamenable to shape priors. We introduce Deep Active Lesion Segmentation (DALS), a fully automated segmentation framework that leverages the powerful nonlinear feature extraction abilities of fully Convolutional Neural Networks (CNNs) and the precise boundary delineation abilities of Active Contour Models (ACMs). Our DALS framework benefits from an improved level-set ACM formulation with a per-pixel-parameterized energy functional and a novel multiscale encoder-decoder CNN that learns an initialization probability map along with parameter maps for the ACM. We evaluate our lesion segmentation model on a new Multiorgan Lesion Segmentation (MLS) dataset that contains images of various organs, including brain, liver, and lung, across different imaging modalities\u2014MR and CT. Our results demonstrate favorable performance compared to competing methods, especially for small training datasets.", 
    "editor": [
      {
        "familyName": "Suk", 
        "givenName": "Heung-Il", 
        "type": "Person"
      }, 
      {
        "familyName": "Liu", 
        "givenName": "Mingxia", 
        "type": "Person"
      }, 
      {
        "familyName": "Yan", 
        "givenName": "Pingkun", 
        "type": "Person"
      }, 
      {
        "familyName": "Lian", 
        "givenName": "Chunfeng", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-32692-0_12", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-030-32691-3", 
        "978-3-030-32692-0"
      ], 
      "name": "Machine Learning in Medical Imaging", 
      "type": "Book"
    }, 
    "keywords": [
      "convolutional neural network", 
      "active contour model", 
      "lesion segmentation", 
      "encoder-decoder convolutional neural network", 
      "feature extraction ability", 
      "small training dataset", 
      "computer-assisted diagnosis", 
      "segmentation dataset", 
      "segmentation framework", 
      "neural network", 
      "segmentation model", 
      "framework benefits", 
      "training dataset", 
      "contour model", 
      "segmentation", 
      "low contrast", 
      "important problem", 
      "probability maps", 
      "favorable performance", 
      "dataset", 
      "extraction ability", 
      "network", 
      "maps", 
      "images", 
      "framework", 
      "priors", 
      "irregular boundaries", 
      "parameter maps", 
      "model", 
      "performance", 
      "method", 
      "ability", 
      "benefits", 
      "results", 
      "boundaries", 
      "formulation", 
      "CT", 
      "energy", 
      "diagnosis", 
      "contrast", 
      "brain", 
      "lung", 
      "prevalence", 
      "liver", 
      "organs", 
      "problem", 
      "Deep Active Lesion Segmentation", 
      "Active Lesion Segmentation", 
      "powerful nonlinear feature extraction abilities", 
      "nonlinear feature extraction abilities", 
      "precise boundary delineation abilities", 
      "boundary delineation abilities", 
      "delineation abilities", 
      "DALS framework benefits", 
      "level-set ACM formulation", 
      "ACM formulation", 
      "pixel-parameterized energy", 
      "novel multiscale encoder-decoder CNN", 
      "multiscale encoder-decoder CNN", 
      "initialization probability map", 
      "lesion segmentation model", 
      "new Multiorgan Lesion Segmentation (MLS) dataset", 
      "Multiorgan Lesion Segmentation (MLS) dataset", 
      "Lesion Segmentation (MLS) dataset", 
      "different imaging modalities\u2014MR", 
      "imaging modalities\u2014MR", 
      "modalities\u2014MR"
    ], 
    "name": "Deep Active Lesion Segmentation", 
    "pagination": "98-105", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1121623477"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-32692-0_12"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-32692-0_12", 
      "https://app.dimensions.ai/details/publication/pub.1121623477"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:15", 
    "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_276.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-32692-0_12"
  }
]
 

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.10.1007/978-3-030-32692-0_12'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_12'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_12'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_12'


 

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

186 TRIPLES      23 PREDICATES      91 URIs      84 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-32692-0_12 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ne50c78d840964edf81c33f43c6fc8a8b
4 schema:datePublished 2019-10-10
5 schema:datePublishedReg 2019-10-10
6 schema:description Lesion segmentation is an important problem in computer-assisted diagnosis that remains challenging due to the prevalence of low contrast, irregular boundaries that are unamenable to shape priors. We introduce Deep Active Lesion Segmentation (DALS), a fully automated segmentation framework that leverages the powerful nonlinear feature extraction abilities of fully Convolutional Neural Networks (CNNs) and the precise boundary delineation abilities of Active Contour Models (ACMs). Our DALS framework benefits from an improved level-set ACM formulation with a per-pixel-parameterized energy functional and a novel multiscale encoder-decoder CNN that learns an initialization probability map along with parameter maps for the ACM. We evaluate our lesion segmentation model on a new Multiorgan Lesion Segmentation (MLS) dataset that contains images of various organs, including brain, liver, and lung, across different imaging modalities—MR and CT. Our results demonstrate favorable performance compared to competing methods, especially for small training datasets.
7 schema:editor Nbe344fa1ffb64656b1a4c59618139307
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf Nd9735c2a38054b78a8e54bccaf75fa5a
12 schema:keywords ACM formulation
13 Active Lesion Segmentation
14 CT
15 DALS framework benefits
16 Deep Active Lesion Segmentation
17 Lesion Segmentation (MLS) dataset
18 Multiorgan Lesion Segmentation (MLS) dataset
19 ability
20 active contour model
21 benefits
22 boundaries
23 boundary delineation abilities
24 brain
25 computer-assisted diagnosis
26 contour model
27 contrast
28 convolutional neural network
29 dataset
30 delineation abilities
31 diagnosis
32 different imaging modalities—MR
33 encoder-decoder convolutional neural network
34 energy
35 extraction ability
36 favorable performance
37 feature extraction ability
38 formulation
39 framework
40 framework benefits
41 images
42 imaging modalities—MR
43 important problem
44 initialization probability map
45 irregular boundaries
46 lesion segmentation
47 lesion segmentation model
48 level-set ACM formulation
49 liver
50 low contrast
51 lung
52 maps
53 method
54 modalities—MR
55 model
56 multiscale encoder-decoder CNN
57 network
58 neural network
59 new Multiorgan Lesion Segmentation (MLS) dataset
60 nonlinear feature extraction abilities
61 novel multiscale encoder-decoder CNN
62 organs
63 parameter maps
64 performance
65 pixel-parameterized energy
66 powerful nonlinear feature extraction abilities
67 precise boundary delineation abilities
68 prevalence
69 priors
70 probability maps
71 problem
72 results
73 segmentation
74 segmentation dataset
75 segmentation framework
76 segmentation model
77 small training dataset
78 training dataset
79 schema:name Deep Active Lesion Segmentation
80 schema:pagination 98-105
81 schema:productId N49bcb114e77349bc9e72ace24161d552
82 Nbeef12d5c4e645daa6d28170f81e6c35
83 schema:publisher Nd450672e216d410fa6c4a52f867bee18
84 schema:sameAs https://app.dimensions.ai/details/publication/pub.1121623477
85 https://doi.org/10.1007/978-3-030-32692-0_12
86 schema:sdDatePublished 2022-01-01T19:15
87 schema:sdLicense https://scigraph.springernature.com/explorer/license/
88 schema:sdPublisher N6149125777ec4f6d9c683bcb8713b24e
89 schema:url https://doi.org/10.1007/978-3-030-32692-0_12
90 sgo:license sg:explorer/license/
91 sgo:sdDataset chapters
92 rdf:type schema:Chapter
93 N0b161387603048298d83d8fee207164e rdf:first sg:person.01066717720.27
94 rdf:rest Nbcfd394e84e945b2b7fdc5d60f77ed42
95 N49bcb114e77349bc9e72ace24161d552 schema:name dimensions_id
96 schema:value pub.1121623477
97 rdf:type schema:PropertyValue
98 N4d6e3074f3bc43769c01d0814ca2e423 schema:familyName Lian
99 schema:givenName Chunfeng
100 rdf:type schema:Person
101 N6149125777ec4f6d9c683bcb8713b24e schema:name Springer Nature - SN SciGraph project
102 rdf:type schema:Organization
103 N69f789f16443459f9513595b6b0e5d82 rdf:first sg:person.01037031400.36
104 rdf:rest Nd63baf879aa84aa599b79817b02c3174
105 N76d25f8375244e2aa615b494694142e6 schema:familyName Yan
106 schema:givenName Pingkun
107 rdf:type schema:Person
108 N80194547f9684eb3ad63a8edd4275f9b schema:familyName Suk
109 schema:givenName Heung-Il
110 rdf:type schema:Person
111 Na2ad2caa5f6a4195ad5d11d801fa7a0b schema:familyName Liu
112 schema:givenName Mingxia
113 rdf:type schema:Person
114 Nab1c90c11f884ddbb5b824dece4293ef rdf:first Na2ad2caa5f6a4195ad5d11d801fa7a0b
115 rdf:rest Nb858ac844bae43c89cf3798b5cf1d520
116 Nb858ac844bae43c89cf3798b5cf1d520 rdf:first N76d25f8375244e2aa615b494694142e6
117 rdf:rest Nfe986f28fb6a416eba6ac50efd6acd89
118 Nbaf8058fdced46fdbbf2ec3e5fcd2b34 rdf:first sg:person.010433333345.19
119 rdf:rest Nbbd53b1fa2704f61903d4904d92056be
120 Nbbd53b1fa2704f61903d4904d92056be rdf:first Neea1bdb9bcde4fd08d8c68d313997fb9
121 rdf:rest N69f789f16443459f9513595b6b0e5d82
122 Nbcfd394e84e945b2b7fdc5d60f77ed42 rdf:first sg:person.07635752745.18
123 rdf:rest Nbaf8058fdced46fdbbf2ec3e5fcd2b34
124 Nbe344fa1ffb64656b1a4c59618139307 rdf:first N80194547f9684eb3ad63a8edd4275f9b
125 rdf:rest Nab1c90c11f884ddbb5b824dece4293ef
126 Nbeef12d5c4e645daa6d28170f81e6c35 schema:name doi
127 schema:value 10.1007/978-3-030-32692-0_12
128 rdf:type schema:PropertyValue
129 Nd450672e216d410fa6c4a52f867bee18 schema:name Springer Nature
130 rdf:type schema:Organisation
131 Nd63baf879aa84aa599b79817b02c3174 rdf:first sg:person.016347323445.35
132 rdf:rest rdf:nil
133 Nd9735c2a38054b78a8e54bccaf75fa5a schema:isbn 978-3-030-32691-3
134 978-3-030-32692-0
135 schema:name Machine Learning in Medical Imaging
136 rdf:type schema:Book
137 Ne50c78d840964edf81c33f43c6fc8a8b rdf:first sg:person.015555505250.21
138 rdf:rest N0b161387603048298d83d8fee207164e
139 Neea1bdb9bcde4fd08d8c68d313997fb9 schema:affiliation grid-institutes:grid.168010.e
140 schema:familyName Wilcox
141 schema:givenName Brian
142 rdf:type schema:Person
143 Nfe986f28fb6a416eba6ac50efd6acd89 rdf:first N4d6e3074f3bc43769c01d0814ca2e423
144 rdf:rest rdf:nil
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 sg:person.01037031400.36 schema:affiliation grid-institutes:grid.168010.e
152 schema:familyName Rubin
153 schema:givenName Daniel
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01037031400.36
155 rdf:type schema:Person
156 sg:person.010433333345.19 schema:affiliation grid-institutes:grid.19006.3e
157 schema:familyName Lu
158 schema:givenName Wuyue
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010433333345.19
160 rdf:type schema:Person
161 sg:person.01066717720.27 schema:affiliation grid-institutes:grid.168010.e
162 schema:familyName Hoogi
163 schema:givenName Assaf
164 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066717720.27
165 rdf:type schema:Person
166 sg:person.015555505250.21 schema:affiliation grid-institutes:grid.19006.3e
167 schema:familyName Hatamizadeh
168 schema:givenName Ali
169 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015555505250.21
170 rdf:type schema:Person
171 sg:person.016347323445.35 schema:affiliation grid-institutes:grid.19006.3e
172 schema:familyName Terzopoulos
173 schema:givenName Demetri
174 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016347323445.35
175 rdf:type schema:Person
176 sg:person.07635752745.18 schema:affiliation grid-institutes:grid.19006.3e
177 schema:familyName Sengupta
178 schema:givenName Debleena
179 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07635752745.18
180 rdf:type schema:Person
181 grid-institutes:grid.168010.e schema:alternateName Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
182 schema:name Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
183 rdf:type schema:Organization
184 grid-institutes:grid.19006.3e schema:alternateName Computer Science Department, University of California, Los Angeles, CA, USA
185 schema:name Computer Science Department, University of California, Los Angeles, CA, USA
186 rdf:type schema:Organization
 




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


...