A Combined Radio-Histological Approach for Classification of Low Grade Gliomas View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2019-01-26

AUTHORS

Aditya Bagari , Ashish Kumar , Avinash Kori , Mahendra Khened , Ganapathy Krishnamurthi

ABSTRACT

Deep learning based techniques have shown to be beneficial for automating various medical image tasks like segmentation of lesions and automation of disease diagnosis. In this work, we demonstrate the utility of deep learning and radiomics features for classification of low grade gliomas (LGG) into astrocytoma and oligodendroglioma. In this study the objective is to use whole-slide H&E stained images and Magnetic Resonance (MR) images of the brain to make a prediction about the class of the glioma. We treat both the pathology and radiology datasets separately for in-depth analysis and then combine the predictions made by the individual models to get the final class label for a patient. The pre-processing of the whole slide images involved region of interest detection, stain normalization and patch extraction. An autoencoder was trained to extract features from each patch and these features are then used to find anomaly patches among the entire set of patches for a single Whole Slide Image. These anomaly patches from all the training slides form the dataset for training the classification model. A deep neural network based classification model was used to classify individual patches among the two classes. For the radiology dataset based analysis, each MRI scan was fed into a pre-processing pipeline which involved skull-stripping, co-registration of MR sequences to T1c, re-sampling of MR volumes to isotropic voxels and segmentation of brain lesion. The lesions in the MR volumes were automatically segmented using a fully convolutional Neural Network (CNN) trained on BraTS-2018 segmentation challenge dataset. From the segmentation maps 64×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\,\times \,$$\end{document}64×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\,\times \,$$\end{document}64 cube patches centered around the tumor were extracted from the T1 MR images for extraction of high level radiomic features. These features were then used to train a logistic regression classifier. After developing the two models, we used a confidence based prediction methodology to get the final class labels for each patient. This combined approach achieved a classification accuracy of 90% on the challenge test set (n = 20). These results showcase the emerging role of deep learning and radiomics in analyzing whole-slide images and MR scans for lesion characterization. More... »

PAGES

416-427

Book

TITLE

Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries

ISBN

978-3-030-11722-1
978-3-030-11723-8

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-11723-8_42

DOI

http://dx.doi.org/10.1007/978-3-030-11723-8_42

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1111721756


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": "Indian Institute of Technology Madras, 600036, Chennai, India", 
          "id": "http://www.grid.ac/institutes/grid.417969.4", 
          "name": [
            "Indian Institute of Technology Madras, 600036, Chennai, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bagari", 
        "givenName": "Aditya", 
        "id": "sg:person.07507664273.80", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07507664273.80"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Indian Institute of Technology Madras, 600036, Chennai, India", 
          "id": "http://www.grid.ac/institutes/grid.417969.4", 
          "name": [
            "Indian Institute of Technology Madras, 600036, Chennai, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kumar", 
        "givenName": "Ashish", 
        "id": "sg:person.011102625273.22", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011102625273.22"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Indian Institute of Technology Madras, 600036, Chennai, India", 
          "id": "http://www.grid.ac/institutes/grid.417969.4", 
          "name": [
            "Indian Institute of Technology Madras, 600036, Chennai, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kori", 
        "givenName": "Avinash", 
        "id": "sg:person.014412245123.13", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014412245123.13"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Indian Institute of Technology Madras, 600036, Chennai, India", 
          "id": "http://www.grid.ac/institutes/grid.417969.4", 
          "name": [
            "Indian Institute of Technology Madras, 600036, Chennai, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Khened", 
        "givenName": "Mahendra", 
        "id": "sg:person.07732256514.56", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07732256514.56"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Indian Institute of Technology Madras, 600036, Chennai, India", 
          "id": "http://www.grid.ac/institutes/grid.417969.4", 
          "name": [
            "Indian Institute of Technology Madras, 600036, Chennai, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Krishnamurthi", 
        "givenName": "Ganapathy", 
        "id": "sg:person.013774661125.64", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013774661125.64"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2019-01-26", 
    "datePublishedReg": "2019-01-26", 
    "description": "Deep learning based techniques have shown to be beneficial for automating various medical image tasks like segmentation of lesions and automation of disease diagnosis. In this work, we demonstrate the utility of deep learning and radiomics features for classification of low grade gliomas (LGG) into astrocytoma and oligodendroglioma. In this study the objective is to use whole-slide H&E stained images and Magnetic Resonance (MR) images of the brain\u00a0to make a prediction about the class of the glioma. We treat both the pathology and radiology datasets separately for in-depth analysis and then combine the predictions made by the individual models to get the final class label for a patient. The pre-processing of the whole slide images involved region of interest detection, stain normalization and patch extraction. An autoencoder was trained to extract features from each patch and these features are then used to find anomaly patches among the entire set of patches for a single Whole Slide Image. These anomaly patches from all the training slides form the dataset for training the classification model. A deep neural network based classification model was used to classify individual patches among the two classes. For the radiology dataset based analysis, each MRI scan was fed into a pre-processing pipeline which involved skull-stripping, co-registration of MR sequences to T1c, re-sampling of MR volumes to isotropic voxels and segmentation of brain lesion. The lesions in the MR volumes were automatically segmented using a fully convolutional Neural Network (CNN) trained on BraTS-2018 segmentation challenge dataset. From the segmentation maps 64\u00d7\\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym}\n\t\t\t\t\\usepackage{amsfonts}\n\t\t\t\t\\usepackage{amssymb}\n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$$\\,\\times \\,$$\\end{document}64\u00d7\\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym}\n\t\t\t\t\\usepackage{amsfonts}\n\t\t\t\t\\usepackage{amssymb}\n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$$\\,\\times \\,$$\\end{document}64 cube patches centered around the tumor were extracted from the T1 MR images for extraction of high level radiomic features. These features were then used to train a logistic regression classifier. After developing the two models, we used a confidence based prediction methodology to get the final class labels for each patient. This combined approach achieved a classification accuracy of 90% on the challenge test set (n\u00a0=\u00a020). These results showcase the emerging role of deep learning and radiomics in analyzing whole-slide images and MR scans for lesion characterization.", 
    "editor": [
      {
        "familyName": "Crimi", 
        "givenName": "Alessandro", 
        "type": "Person"
      }, 
      {
        "familyName": "Bakas", 
        "givenName": "Spyridon", 
        "type": "Person"
      }, 
      {
        "familyName": "Kuijf", 
        "givenName": "Hugo", 
        "type": "Person"
      }, 
      {
        "familyName": "Keyvan", 
        "givenName": "Farahani", 
        "type": "Person"
      }, 
      {
        "familyName": "Reyes", 
        "givenName": "Mauricio", 
        "type": "Person"
      }, 
      {
        "familyName": "van Walsum", 
        "givenName": "Theo", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-11723-8_42", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-030-11722-1", 
        "978-3-030-11723-8"
      ], 
      "name": "Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries", 
      "type": "Book"
    }, 
    "keywords": [
      "convolutional neural network", 
      "final class label", 
      "deep learning", 
      "whole slide images", 
      "neural network", 
      "class labels", 
      "single whole slide image", 
      "slide images", 
      "classification model", 
      "MR volumes", 
      "medical image tasks", 
      "deep neural networks", 
      "segmentation of lesions", 
      "whole-slide images", 
      "pre-processing pipeline", 
      "challenge test set", 
      "logistic regression classifier", 
      "interest detection", 
      "patch extraction", 
      "challenge dataset", 
      "segmentation map", 
      "stain normalization", 
      "image tasks", 
      "classification accuracy", 
      "regression classifier", 
      "radiomic features", 
      "datasets", 
      "T1 MR images", 
      "segmentation", 
      "test set", 
      "images", 
      "magnetic resonance images", 
      "network", 
      "learning", 
      "individual models", 
      "MR images", 
      "prediction methodology", 
      "entire set", 
      "training slides", 
      "resonance images", 
      "autoencoder", 
      "classification", 
      "disease diagnosis", 
      "classifier", 
      "set", 
      "automation", 
      "features", 
      "depth analysis", 
      "isotropic voxels", 
      "labels", 
      "individual patches", 
      "extraction", 
      "task", 
      "MR sequences", 
      "pipeline", 
      "combined approach", 
      "model", 
      "MR scans", 
      "accuracy", 
      "voxels", 
      "class", 
      "maps", 
      "methodology", 
      "detection", 
      "prediction", 
      "technique", 
      "patches", 
      "work", 
      "low grade gliomas", 
      "confidence", 
      "utility", 
      "normalization", 
      "objective", 
      "sequence", 
      "analysis", 
      "MRI scans", 
      "results", 
      "lesion characterization", 
      "grade gliomas", 
      "scans", 
      "volume", 
      "brain lesions", 
      "lesions", 
      "gliomas", 
      "patients", 
      "slides", 
      "anomalies", 
      "astrocytomas", 
      "tumors", 
      "diagnosis", 
      "pathology", 
      "brain", 
      "T1c", 
      "region", 
      "role", 
      "study", 
      "approach", 
      "characterization", 
      "radiology datasets", 
      "anomaly patches", 
      "segmentation challenge dataset", 
      "cube patches", 
      "high level radiomic features", 
      "level radiomic features", 
      "Combined Radio-Histological Approach", 
      "Radio-Histological Approach"
    ], 
    "name": "A Combined Radio-Histological Approach for Classification of Low Grade Gliomas", 
    "pagination": "416-427", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1111721756"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-11723-8_42"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-11723-8_42", 
      "https://app.dimensions.ai/details/publication/pub.1111721756"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-11-01T19:00", 
    "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/chapter/chapter_418.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-11723-8_42"
  }
]
 

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.10.1007/978-3-030-11723-8_42'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-11723-8_42'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-11723-8_42'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-11723-8_42'


 

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

219 TRIPLES      23 PREDICATES      131 URIs      124 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-11723-8_42 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N66489db7a7f7443b8934f5ad3f788994
4 schema:datePublished 2019-01-26
5 schema:datePublishedReg 2019-01-26
6 schema:description Deep learning based techniques have shown to be beneficial for automating various medical image tasks like segmentation of lesions and automation of disease diagnosis. In this work, we demonstrate the utility of deep learning and radiomics features for classification of low grade gliomas (LGG) into astrocytoma and oligodendroglioma. In this study the objective is to use whole-slide H&E stained images and Magnetic Resonance (MR) images of the brain to make a prediction about the class of the glioma. We treat both the pathology and radiology datasets separately for in-depth analysis and then combine the predictions made by the individual models to get the final class label for a patient. The pre-processing of the whole slide images involved region of interest detection, stain normalization and patch extraction. An autoencoder was trained to extract features from each patch and these features are then used to find anomaly patches among the entire set of patches for a single Whole Slide Image. These anomaly patches from all the training slides form the dataset for training the classification model. A deep neural network based classification model was used to classify individual patches among the two classes. For the radiology dataset based analysis, each MRI scan was fed into a pre-processing pipeline which involved skull-stripping, co-registration of MR sequences to T1c, re-sampling of MR volumes to isotropic voxels and segmentation of brain lesion. The lesions in the MR volumes were automatically segmented using a fully convolutional Neural Network (CNN) trained on BraTS-2018 segmentation challenge dataset. From the segmentation maps 64×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\,\times \,$$\end{document}64×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\,\times \,$$\end{document}64 cube patches centered around the tumor were extracted from the T1 MR images for extraction of high level radiomic features. These features were then used to train a logistic regression classifier. After developing the two models, we used a confidence based prediction methodology to get the final class labels for each patient. This combined approach achieved a classification accuracy of 90% on the challenge test set (n = 20). These results showcase the emerging role of deep learning and radiomics in analyzing whole-slide images and MR scans for lesion characterization.
7 schema:editor Nbe0b10dcb7c449839627456544ca6cd5
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N5a2b957a90d54d54a5a884301939ae04
12 schema:keywords Combined Radio-Histological Approach
13 MR images
14 MR scans
15 MR sequences
16 MR volumes
17 MRI scans
18 Radio-Histological Approach
19 T1 MR images
20 T1c
21 accuracy
22 analysis
23 anomalies
24 anomaly patches
25 approach
26 astrocytomas
27 autoencoder
28 automation
29 brain
30 brain lesions
31 challenge dataset
32 challenge test set
33 characterization
34 class
35 class labels
36 classification
37 classification accuracy
38 classification model
39 classifier
40 combined approach
41 confidence
42 convolutional neural network
43 cube patches
44 datasets
45 deep learning
46 deep neural networks
47 depth analysis
48 detection
49 diagnosis
50 disease diagnosis
51 entire set
52 extraction
53 features
54 final class label
55 gliomas
56 grade gliomas
57 high level radiomic features
58 image tasks
59 images
60 individual models
61 individual patches
62 interest detection
63 isotropic voxels
64 labels
65 learning
66 lesion characterization
67 lesions
68 level radiomic features
69 logistic regression classifier
70 low grade gliomas
71 magnetic resonance images
72 maps
73 medical image tasks
74 methodology
75 model
76 network
77 neural network
78 normalization
79 objective
80 patch extraction
81 patches
82 pathology
83 patients
84 pipeline
85 pre-processing pipeline
86 prediction
87 prediction methodology
88 radiology datasets
89 radiomic features
90 region
91 regression classifier
92 resonance images
93 results
94 role
95 scans
96 segmentation
97 segmentation challenge dataset
98 segmentation map
99 segmentation of lesions
100 sequence
101 set
102 single whole slide image
103 slide images
104 slides
105 stain normalization
106 study
107 task
108 technique
109 test set
110 training slides
111 tumors
112 utility
113 volume
114 voxels
115 whole slide images
116 whole-slide images
117 work
118 schema:name A Combined Radio-Histological Approach for Classification of Low Grade Gliomas
119 schema:pagination 416-427
120 schema:productId N544d7c2989a84f34bdb3214c26adcef3
121 N9eeb370eae2f471c9abb4a227f1514a1
122 schema:publisher N7394528dcf4843c1876ec9fc35a17ced
123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111721756
124 https://doi.org/10.1007/978-3-030-11723-8_42
125 schema:sdDatePublished 2021-11-01T19:00
126 schema:sdLicense https://scigraph.springernature.com/explorer/license/
127 schema:sdPublisher Nac5cf334489d4b9a8ab67157bcc7abda
128 schema:url https://doi.org/10.1007/978-3-030-11723-8_42
129 sgo:license sg:explorer/license/
130 sgo:sdDataset chapters
131 rdf:type schema:Chapter
132 N2991669cc73d4c339d330669c9fb71ab rdf:first sg:person.013774661125.64
133 rdf:rest rdf:nil
134 N3cf5ad27a8794b49aefcfcb640216ffa rdf:first sg:person.011102625273.22
135 rdf:rest Nb83736c8e8724254a3dc9fe85c3ac2df
136 N544d7c2989a84f34bdb3214c26adcef3 schema:name doi
137 schema:value 10.1007/978-3-030-11723-8_42
138 rdf:type schema:PropertyValue
139 N561d0b8d13414e64ab4b144ee0d6e6e9 rdf:first N9d7f1fb3efb94dac8e47869ded1703b1
140 rdf:rest rdf:nil
141 N58c96f6c6e5040fe9bfe528fe4021e14 schema:familyName Crimi
142 schema:givenName Alessandro
143 rdf:type schema:Person
144 N5a2b957a90d54d54a5a884301939ae04 schema:isbn 978-3-030-11722-1
145 978-3-030-11723-8
146 schema:name Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
147 rdf:type schema:Book
148 N66489db7a7f7443b8934f5ad3f788994 rdf:first sg:person.07507664273.80
149 rdf:rest N3cf5ad27a8794b49aefcfcb640216ffa
150 N68fcac14defb4bab9d5c1b02d6a8fe53 rdf:first Ne368ade841064b959e4cb4b2ad4d6ea0
151 rdf:rest Ndefb3c3bbee743c58e0c3bc023f5ef11
152 N7394528dcf4843c1876ec9fc35a17ced schema:name Springer Nature
153 rdf:type schema:Organisation
154 N7926c1ed49634161a196ef78dfa7d060 rdf:first Nd83640d25eaf493e880599073e1fe52a
155 rdf:rest N68fcac14defb4bab9d5c1b02d6a8fe53
156 N7a50bdeffb614c36bae6a89e80769207 schema:familyName Keyvan
157 schema:givenName Farahani
158 rdf:type schema:Person
159 N9d7f1fb3efb94dac8e47869ded1703b1 schema:familyName van Walsum
160 schema:givenName Theo
161 rdf:type schema:Person
162 N9eeb370eae2f471c9abb4a227f1514a1 schema:name dimensions_id
163 schema:value pub.1111721756
164 rdf:type schema:PropertyValue
165 Nac5cf334489d4b9a8ab67157bcc7abda schema:name Springer Nature - SN SciGraph project
166 rdf:type schema:Organization
167 Nade1466a84fb4e10b8706dc90ee2fcdd schema:familyName Reyes
168 schema:givenName Mauricio
169 rdf:type schema:Person
170 Nb83736c8e8724254a3dc9fe85c3ac2df rdf:first sg:person.014412245123.13
171 rdf:rest Ne3056a0724904529ba64c639bfdecdd2
172 Nbe0b10dcb7c449839627456544ca6cd5 rdf:first N58c96f6c6e5040fe9bfe528fe4021e14
173 rdf:rest N7926c1ed49634161a196ef78dfa7d060
174 Nd83640d25eaf493e880599073e1fe52a schema:familyName Bakas
175 schema:givenName Spyridon
176 rdf:type schema:Person
177 Ndae758c78dd34b79acb177279a0ede01 rdf:first Nade1466a84fb4e10b8706dc90ee2fcdd
178 rdf:rest N561d0b8d13414e64ab4b144ee0d6e6e9
179 Ndefb3c3bbee743c58e0c3bc023f5ef11 rdf:first N7a50bdeffb614c36bae6a89e80769207
180 rdf:rest Ndae758c78dd34b79acb177279a0ede01
181 Ne3056a0724904529ba64c639bfdecdd2 rdf:first sg:person.07732256514.56
182 rdf:rest N2991669cc73d4c339d330669c9fb71ab
183 Ne368ade841064b959e4cb4b2ad4d6ea0 schema:familyName Kuijf
184 schema:givenName Hugo
185 rdf:type schema:Person
186 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
187 schema:name Information and Computing Sciences
188 rdf:type schema:DefinedTerm
189 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
190 schema:name Artificial Intelligence and Image Processing
191 rdf:type schema:DefinedTerm
192 sg:person.011102625273.22 schema:affiliation grid-institutes:grid.417969.4
193 schema:familyName Kumar
194 schema:givenName Ashish
195 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011102625273.22
196 rdf:type schema:Person
197 sg:person.013774661125.64 schema:affiliation grid-institutes:grid.417969.4
198 schema:familyName Krishnamurthi
199 schema:givenName Ganapathy
200 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013774661125.64
201 rdf:type schema:Person
202 sg:person.014412245123.13 schema:affiliation grid-institutes:grid.417969.4
203 schema:familyName Kori
204 schema:givenName Avinash
205 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014412245123.13
206 rdf:type schema:Person
207 sg:person.07507664273.80 schema:affiliation grid-institutes:grid.417969.4
208 schema:familyName Bagari
209 schema:givenName Aditya
210 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07507664273.80
211 rdf:type schema:Person
212 sg:person.07732256514.56 schema:affiliation grid-institutes:grid.417969.4
213 schema:familyName Khened
214 schema:givenName Mahendra
215 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07732256514.56
216 rdf:type schema:Person
217 grid-institutes:grid.417969.4 schema:alternateName Indian Institute of Technology Madras, 600036, Chennai, India
218 schema:name Indian Institute of Technology Madras, 600036, Chennai, India
219 rdf:type schema:Organization
 




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


...