View in EDS

CATARACTS: Challenge on automatic tool annotation for cataRACT surgery.

Saved in:
Bibliographic Details
Title: CATARACTS: Challenge on automatic tool annotation for cataRACT surgery.
Authors: Al Hajj, Hassan1, Lamard, Mathieu1,2, Conze, Pierre-Henri1,3, Roychowdhury, Soumali4, Hu, Xiaowei5, Maršalkaitė, Gabija6, Zisimopoulos, Odysseas7, Dedmari, Muneer Ahmad8, Zhao, Fenqiang9, Prellberg, Jonas10, Sahu, Manish11, Galdran, Adrian12, Araújo, Teresa12,13, Vo, Duc My14, Panda, Chandan15, Dahiya, Navdeep16, Kondo, Satoshi17, Bian, Zhengbing4, Vahdat, Arash4, Bialopetravičius, Jonas6
Source: Medical Image Analysis. Feb2019, Vol. 52, p24-41. 18p.
Subjects: Cataract surgery, Laparoscopic surgery, Surgical instruments, Deep learning, Surgeons
Abstract: Highlights • The challenge on automatic tool annotation for cataract surgery is presented. • Tool usage was manually annotated for 21 tools in 50 cataract surgery videos. • Various deep learning solutions were proposed by 14 teams. • Lessons learnt from the differential analysis of these solutions are presented. • Automatic annotations are almost as accurate as manual annotations. Graphical abstract Abstract Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparoscopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected, the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future. [ABSTRACT FROM AUTHOR]
Copyright of Medical Image Analysis is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 134151882
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: CATARACTS: Challenge on automatic tool annotation for cataRACT surgery.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Al+Hajj%2C+Hassan%22">Al Hajj, Hassan</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Lamard%2C+Mathieu%22">Lamard, Mathieu</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Conze%2C+Pierre-Henri%22">Conze, Pierre-Henri</searchLink><relatesTo>1,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Roychowdhury%2C+Soumali%22">Roychowdhury, Soumali</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Hu%2C+Xiaowei%22">Hu, Xiaowei</searchLink><relatesTo>5</relatesTo><br /><searchLink fieldCode="AR" term="%22Maršalkaitė%2C+Gabija%22">Maršalkaitė, Gabija</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22Zisimopoulos%2C+Odysseas%22">Zisimopoulos, Odysseas</searchLink><relatesTo>7</relatesTo><br /><searchLink fieldCode="AR" term="%22Dedmari%2C+Muneer+Ahmad%22">Dedmari, Muneer Ahmad</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Zhao%2C+Fenqiang%22">Zhao, Fenqiang</searchLink><relatesTo>9</relatesTo><br /><searchLink fieldCode="AR" term="%22Prellberg%2C+Jonas%22">Prellberg, Jonas</searchLink><relatesTo>10</relatesTo><br /><searchLink fieldCode="AR" term="%22Sahu%2C+Manish%22">Sahu, Manish</searchLink><relatesTo>11</relatesTo><br /><searchLink fieldCode="AR" term="%22Galdran%2C+Adrian%22">Galdran, Adrian</searchLink><relatesTo>12</relatesTo><br /><searchLink fieldCode="AR" term="%22Araújo%2C+Teresa%22">Araújo, Teresa</searchLink><relatesTo>12,13</relatesTo><br /><searchLink fieldCode="AR" term="%22Vo%2C+Duc+My%22">Vo, Duc My</searchLink><relatesTo>14</relatesTo><br /><searchLink fieldCode="AR" term="%22Panda%2C+Chandan%22">Panda, Chandan</searchLink><relatesTo>15</relatesTo><br /><searchLink fieldCode="AR" term="%22Dahiya%2C+Navdeep%22">Dahiya, Navdeep</searchLink><relatesTo>16</relatesTo><br /><searchLink fieldCode="AR" term="%22Kondo%2C+Satoshi%22">Kondo, Satoshi</searchLink><relatesTo>17</relatesTo><br /><searchLink fieldCode="AR" term="%22Bian%2C+Zhengbing%22">Bian, Zhengbing</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Vahdat%2C+Arash%22">Vahdat, Arash</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Bialopetravičius%2C+Jonas%22">Bialopetravičius, Jonas</searchLink><relatesTo>6</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Medical+Image+Analysis%22">Medical Image Analysis</searchLink>. Feb2019, Vol. 52, p24-41. 18p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Cataract+surgery%22">Cataract surgery</searchLink><br /><searchLink fieldCode="DE" term="%22Laparoscopic+surgery%22">Laparoscopic surgery</searchLink><br /><searchLink fieldCode="DE" term="%22Surgical+instruments%22">Surgical instruments</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Surgeons%22">Surgeons</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Highlights • The challenge on automatic tool annotation for cataract surgery is presented. • Tool usage was manually annotated for 21 tools in 50 cataract surgery videos. • Various deep learning solutions were proposed by 14 teams. • Lessons learnt from the differential analysis of these solutions are presented. • Automatic annotations are almost as accurate as manual annotations. Graphical abstract Abstract Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparoscopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected, the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Medical Image Analysis is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=134151882
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.media.2018.11.008
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 18
        StartPage: 24
    Subjects:
      – SubjectFull: Cataract surgery
        Type: general
      – SubjectFull: Laparoscopic surgery
        Type: general
      – SubjectFull: Surgical instruments
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Surgeons
        Type: general
    Titles:
      – TitleFull: CATARACTS: Challenge on automatic tool annotation for cataRACT surgery.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Al Hajj, Hassan
      – PersonEntity:
          Name:
            NameFull: Lamard, Mathieu
      – PersonEntity:
          Name:
            NameFull: Conze, Pierre-Henri
      – PersonEntity:
          Name:
            NameFull: Roychowdhury, Soumali
      – PersonEntity:
          Name:
            NameFull: Hu, Xiaowei
      – PersonEntity:
          Name:
            NameFull: Maršalkaitė, Gabija
      – PersonEntity:
          Name:
            NameFull: Zisimopoulos, Odysseas
      – PersonEntity:
          Name:
            NameFull: Dedmari, Muneer Ahmad
      – PersonEntity:
          Name:
            NameFull: Zhao, Fenqiang
      – PersonEntity:
          Name:
            NameFull: Prellberg, Jonas
      – PersonEntity:
          Name:
            NameFull: Sahu, Manish
      – PersonEntity:
          Name:
            NameFull: Galdran, Adrian
      – PersonEntity:
          Name:
            NameFull: Araújo, Teresa
      – PersonEntity:
          Name:
            NameFull: Vo, Duc My
      – PersonEntity:
          Name:
            NameFull: Panda, Chandan
      – PersonEntity:
          Name:
            NameFull: Dahiya, Navdeep
      – PersonEntity:
          Name:
            NameFull: Kondo, Satoshi
      – PersonEntity:
          Name:
            NameFull: Bian, Zhengbing
      – PersonEntity:
          Name:
            NameFull: Vahdat, Arash
      – PersonEntity:
          Name:
            NameFull: Bialopetravičius, Jonas
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2019
              Type: published
              Y: 2019
          Identifiers:
            – Type: issn-print
              Value: 13618415
          Numbering:
            – Type: volume
              Value: 52
          Titles:
            – TitleFull: Medical Image Analysis
              Type: main
ResultId 1