Pilot Study on the Performance of a New System for Image Based Analysis of Peripheral Blood Smears on Normal Samples View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2017-05-26

AUTHORS

Preethi S. Chari, Sujay Prasad

ABSTRACT

Image analysis based automated systems aiming to automate the manual microscopic review of peripheral blood smears have gained popularity in recent times. In this paper, we evaluate a new blood smear analysis system based on artificial intelligence, Shonit™ by SigTuple Technologies Private Limited. One hundred normal samples with no flags from an automated haematology analyser were taken. Peripheral blood smear slides were prepared using the autostainer integrated with an automated haematology analyser and stained using May-Grunwald–Giemsa stain. These slides were analysed with Shonit™. The metrics for evaluation included (1) accuracy of white blood cell classification for the five normal white blood cell types, and (2) comparison of white blood cell differential count with the automated haematology analyser. In addition, we also explored the possibility of estimating the value of red blood cell and platelet indices via image analysis. Overall white blood cell classification specificity was greater than 97.90% and the precision was greater than 93.90% for all the five white blood cell classes. The correlation of the white blood cell differential count between the automated haematology analyser and Shonit™ was found to be within the known inter cell-counter variability. Shonit™ was found to show promise in terms of its ability to analyse peripheral blood smear images to derive quantifiable metrics useful for clinicians. Future enhancement should include the ability to analyse abnormal blood samples. More... »

PAGES

125-131

References to SciGraph publications

  • 2015-04-11. ImageNet Large Scale Visual Recognition Challenge in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2013. Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks in MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION – MICCAI 2013
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s12288-017-0835-7

    DOI

    http://dx.doi.org/10.1007/s12288-017-0835-7

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1085602976

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/29398811


    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/2008/1102", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Cardiorespiratory Medicine and Haematology", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Anand Diagnostic Laboratory, 54, Bowring Tower, Bowring Hospital Road, Shivajinagar, 560001, Bengaluru, Karnataka, India", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Anand Diagnostic Laboratory, 54, Bowring Tower, Bowring Hospital Road, Shivajinagar, 560001, Bengaluru, Karnataka, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chari", 
            "givenName": "Preethi S.", 
            "id": "sg:person.01023326355.34", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01023326355.34"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Anand Diagnostic Laboratory, 54, Bowring Tower, Bowring Hospital Road, Shivajinagar, 560001, Bengaluru, Karnataka, India", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Anand Diagnostic Laboratory, 54, Bowring Tower, Bowring Hospital Road, Shivajinagar, 560001, Bengaluru, Karnataka, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Prasad", 
            "givenName": "Sujay", 
            "id": "sg:person.013064167071.28", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013064167071.28"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-642-40763-5_51", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014968475", 
              "https://doi.org/10.1007/978-3-642-40763-5_51"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-015-0816-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009767488", 
              "https://doi.org/10.1007/s11263-015-0816-y"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2017-05-26", 
        "datePublishedReg": "2017-05-26", 
        "description": "Image analysis based automated systems aiming to automate the manual microscopic review of peripheral blood smears have gained popularity in recent times. In this paper, we evaluate a new blood smear analysis system based on artificial intelligence, Shonit\u2122 by SigTuple Technologies Private Limited. One hundred normal samples with no flags from an automated haematology analyser were taken. Peripheral blood smear slides were prepared using the autostainer integrated with an automated haematology analyser and stained using May-Grunwald\u2013Giemsa stain. These slides were analysed with Shonit\u2122. The metrics for evaluation included (1) accuracy of white blood cell classification for the five normal white blood cell types, and (2) comparison of white blood cell differential count with the automated haematology analyser. In addition, we also explored the possibility of estimating the value of red blood cell and platelet indices via image analysis. Overall white blood cell classification specificity was greater than 97.90% and the precision was greater than 93.90% for all the five white blood cell classes. The correlation of the white blood cell differential count between the automated haematology analyser and Shonit\u2122 was found to be within the known inter cell-counter variability. Shonit\u2122 was found to show promise in terms of its ability to analyse peripheral blood smear images to derive quantifiable metrics useful for clinicians. Future enhancement should include the ability to analyse abnormal blood samples.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s12288-017-0835-7", 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1107805", 
            "issn": [
              "0971-4502", 
              "0974-0449"
            ], 
            "name": "Indian Journal of Hematology and Blood Transfusion", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "34"
          }
        ], 
        "keywords": [
          "white blood cell differential count", 
          "peripheral blood smear", 
          "cell differential counts", 
          "automated haematology analyser", 
          "haematology analyser", 
          "peripheral blood smear slides", 
          "differential counts", 
          "blood smears", 
          "blood smear slides", 
          "red blood cells", 
          "normal samples", 
          "platelet indices", 
          "white blood cell types", 
          "blood samples", 
          "manual microscopic review", 
          "abnormal blood samples", 
          "microscopic review", 
          "Giemsa stain", 
          "pilot study", 
          "blood cells", 
          "May-Grunwald", 
          "cell classes", 
          "white blood cell classification", 
          "blood cell types", 
          "smears", 
          "cell types", 
          "blood cell classification", 
          "smear slides", 
          "count", 
          "clinicians", 
          "normal white blood cell types", 
          "autostainer", 
          "blood smear images", 
          "stain", 
          "slides", 
          "peripheral blood smear images", 
          "image analysis", 
          "cells", 
          "review", 
          "samples", 
          "specificity", 
          "analysis system", 
          "classification specificity", 
          "cell classification", 
          "index", 
          "ability", 
          "evaluation", 
          "smear images", 
          "analysis", 
          "study", 
          "correlation", 
          "promise", 
          "Image Based Analysis", 
          "addition", 
          "analyzer", 
          "classification", 
          "types", 
          "time", 
          "comparison", 
          "variability", 
          "flags", 
          "quantifiable metrics", 
          "system", 
          "possibility", 
          "values", 
          "enhancement", 
          "recent times", 
          "popularity", 
          "Private Limited", 
          "new system", 
          "terms", 
          "class", 
          "Based Analysis", 
          "images", 
          "accuracy", 
          "Limited", 
          "metrics", 
          "artificial intelligence", 
          "precision", 
          "future enhancements", 
          "performance", 
          "intelligence", 
          "paper"
        ], 
        "name": "Pilot Study on the Performance of a New System for Image Based Analysis of Peripheral Blood Smears on Normal Samples", 
        "pagination": "125-131", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1085602976"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s12288-017-0835-7"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "29398811"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s12288-017-0835-7", 
          "https://app.dimensions.ai/details/publication/pub.1085602976"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-08-04T17:06", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220804/entities/gbq_results/article/article_728.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s12288-017-0835-7"
      }
    ]
     

    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/s12288-017-0835-7'

    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/s12288-017-0835-7'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12288-017-0835-7'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12288-017-0835-7'


     

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

    159 TRIPLES      21 PREDICATES      110 URIs      100 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s12288-017-0835-7 schema:about anzsrc-for:11
    2 anzsrc-for:1102
    3 schema:author Nf9e59cbf0c3e44a68a9fc92b54b5126d
    4 schema:citation sg:pub.10.1007/978-3-642-40763-5_51
    5 sg:pub.10.1007/s11263-015-0816-y
    6 schema:datePublished 2017-05-26
    7 schema:datePublishedReg 2017-05-26
    8 schema:description Image analysis based automated systems aiming to automate the manual microscopic review of peripheral blood smears have gained popularity in recent times. In this paper, we evaluate a new blood smear analysis system based on artificial intelligence, Shonit™ by SigTuple Technologies Private Limited. One hundred normal samples with no flags from an automated haematology analyser were taken. Peripheral blood smear slides were prepared using the autostainer integrated with an automated haematology analyser and stained using May-Grunwald–Giemsa stain. These slides were analysed with Shonit™. The metrics for evaluation included (1) accuracy of white blood cell classification for the five normal white blood cell types, and (2) comparison of white blood cell differential count with the automated haematology analyser. In addition, we also explored the possibility of estimating the value of red blood cell and platelet indices via image analysis. Overall white blood cell classification specificity was greater than 97.90% and the precision was greater than 93.90% for all the five white blood cell classes. The correlation of the white blood cell differential count between the automated haematology analyser and Shonit™ was found to be within the known inter cell-counter variability. Shonit™ was found to show promise in terms of its ability to analyse peripheral blood smear images to derive quantifiable metrics useful for clinicians. Future enhancement should include the ability to analyse abnormal blood samples.
    9 schema:genre article
    10 schema:isAccessibleForFree true
    11 schema:isPartOf N2fbb81ba931b434aaf3dd05f5b7187f3
    12 Nb9114ea74e2d4706a03885ab198c7dcc
    13 sg:journal.1107805
    14 schema:keywords Based Analysis
    15 Giemsa stain
    16 Image Based Analysis
    17 Limited
    18 May-Grunwald
    19 Private Limited
    20 ability
    21 abnormal blood samples
    22 accuracy
    23 addition
    24 analysis
    25 analysis system
    26 analyzer
    27 artificial intelligence
    28 automated haematology analyser
    29 autostainer
    30 blood cell classification
    31 blood cell types
    32 blood cells
    33 blood samples
    34 blood smear images
    35 blood smear slides
    36 blood smears
    37 cell classes
    38 cell classification
    39 cell differential counts
    40 cell types
    41 cells
    42 class
    43 classification
    44 classification specificity
    45 clinicians
    46 comparison
    47 correlation
    48 count
    49 differential counts
    50 enhancement
    51 evaluation
    52 flags
    53 future enhancements
    54 haematology analyser
    55 image analysis
    56 images
    57 index
    58 intelligence
    59 manual microscopic review
    60 metrics
    61 microscopic review
    62 new system
    63 normal samples
    64 normal white blood cell types
    65 paper
    66 performance
    67 peripheral blood smear
    68 peripheral blood smear images
    69 peripheral blood smear slides
    70 pilot study
    71 platelet indices
    72 popularity
    73 possibility
    74 precision
    75 promise
    76 quantifiable metrics
    77 recent times
    78 red blood cells
    79 review
    80 samples
    81 slides
    82 smear images
    83 smear slides
    84 smears
    85 specificity
    86 stain
    87 study
    88 system
    89 terms
    90 time
    91 types
    92 values
    93 variability
    94 white blood cell classification
    95 white blood cell differential count
    96 white blood cell types
    97 schema:name Pilot Study on the Performance of a New System for Image Based Analysis of Peripheral Blood Smears on Normal Samples
    98 schema:pagination 125-131
    99 schema:productId Nb7911f159e2b47c9a2abb5bd1a23d242
    100 Ne73846c9fd80422abb2eb3d35e9f5a15
    101 Nf2ddc8484f0f4003b731755395258f23
    102 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085602976
    103 https://doi.org/10.1007/s12288-017-0835-7
    104 schema:sdDatePublished 2022-08-04T17:06
    105 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    106 schema:sdPublisher N36b67f119b6b444cb1c5765ec6d48fc3
    107 schema:url https://doi.org/10.1007/s12288-017-0835-7
    108 sgo:license sg:explorer/license/
    109 sgo:sdDataset articles
    110 rdf:type schema:ScholarlyArticle
    111 N2fbb81ba931b434aaf3dd05f5b7187f3 schema:issueNumber 1
    112 rdf:type schema:PublicationIssue
    113 N36b67f119b6b444cb1c5765ec6d48fc3 schema:name Springer Nature - SN SciGraph project
    114 rdf:type schema:Organization
    115 Nb7911f159e2b47c9a2abb5bd1a23d242 schema:name dimensions_id
    116 schema:value pub.1085602976
    117 rdf:type schema:PropertyValue
    118 Nb9114ea74e2d4706a03885ab198c7dcc schema:volumeNumber 34
    119 rdf:type schema:PublicationVolume
    120 Ne361502c4fc4488c99ea7be808f0b282 rdf:first sg:person.013064167071.28
    121 rdf:rest rdf:nil
    122 Ne73846c9fd80422abb2eb3d35e9f5a15 schema:name pubmed_id
    123 schema:value 29398811
    124 rdf:type schema:PropertyValue
    125 Nf2ddc8484f0f4003b731755395258f23 schema:name doi
    126 schema:value 10.1007/s12288-017-0835-7
    127 rdf:type schema:PropertyValue
    128 Nf9e59cbf0c3e44a68a9fc92b54b5126d rdf:first sg:person.01023326355.34
    129 rdf:rest Ne361502c4fc4488c99ea7be808f0b282
    130 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
    131 schema:name Medical and Health Sciences
    132 rdf:type schema:DefinedTerm
    133 anzsrc-for:1102 schema:inDefinedTermSet anzsrc-for:
    134 schema:name Cardiorespiratory Medicine and Haematology
    135 rdf:type schema:DefinedTerm
    136 sg:journal.1107805 schema:issn 0971-4502
    137 0974-0449
    138 schema:name Indian Journal of Hematology and Blood Transfusion
    139 schema:publisher Springer Nature
    140 rdf:type schema:Periodical
    141 sg:person.01023326355.34 schema:affiliation grid-institutes:None
    142 schema:familyName Chari
    143 schema:givenName Preethi S.
    144 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01023326355.34
    145 rdf:type schema:Person
    146 sg:person.013064167071.28 schema:affiliation grid-institutes:None
    147 schema:familyName Prasad
    148 schema:givenName Sujay
    149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013064167071.28
    150 rdf:type schema:Person
    151 sg:pub.10.1007/978-3-642-40763-5_51 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014968475
    152 https://doi.org/10.1007/978-3-642-40763-5_51
    153 rdf:type schema:CreativeWork
    154 sg:pub.10.1007/s11263-015-0816-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1009767488
    155 https://doi.org/10.1007/s11263-015-0816-y
    156 rdf:type schema:CreativeWork
    157 grid-institutes:None schema:alternateName Anand Diagnostic Laboratory, 54, Bowring Tower, Bowring Hospital Road, Shivajinagar, 560001, Bengaluru, Karnataka, India
    158 schema:name Anand Diagnostic Laboratory, 54, Bowring Tower, Bowring Hospital Road, Shivajinagar, 560001, Bengaluru, Karnataka, India
    159 rdf:type schema:Organization
     




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


    ...