Biomedical concept detection in medical images: MQ-CSIRO at 2019 ImageCLEFmed caption task

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

We describe our concept detection system submitted for the ImageCLEFmed Caption task, part of the ImageCLEF 2019 challenge. The advancements in imaging technologies has improved the ability of clinicians to detect, diagnose, and treat diseases. Radiologists routinely interpret medical images and summarise their findings in the form of radiology reports. The mapping of visual information present in medical images to the condensed textual description is a tedious, time-consuming, expensive, and error-prone task. The development of methods that can automatically detect the presence and location of medical concepts in medical images can improve the efficiency of radiologists, reduce the burden of manual interpretation, and also help in reducing diagnostic errors. We propose a Convolutional Neural Network based multi-label image classifier to predict relevant concepts present in medical images. The proposed method achieved an F1-score of 0.1435 on the held-out test set of the 2019 ImageCLEFmed Caption Task. We present our proposed system with data analysis, experimental results, comparison, and discussion.

LanguageEnglish
Title of host publicationCLEF 2019 Working Notes
Subtitle of host publicationWorking Notes of CLEF 2019 - Conferenceand Labs of the Evaluation Forum
EditorsLinda Cappellato, Nicola Ferro, David E. Losada, Henning Müller
Pages1-15
Number of pages15
Publication statusPublished - 9 Sep 2019
Event20th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2019 - Lugano, Switzerland
Duration: 9 Sep 201912 Sep 2019

Publication series

NameCEUR Workshop Proceedings
Volume2380
ISSN (Electronic)1613-0073

Conference

Conference20th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2019
CountrySwitzerland
CityLugano
Period9/09/1912/09/19

Fingerprint

Radiology
Labels
Classifiers
Neural networks
Imaging techniques

Bibliographical note

Copyright the Author(s) 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

  • Caption Prediction
  • Computer Vision
  • Concept Detection
  • Convolutional Neural Network
  • Medical Imaging
  • Multi-label classification

Cite this

Singh, S., Karimi, S., Ho-Shon, K., & Hamey, L. (2019). Biomedical concept detection in medical images: MQ-CSIRO at 2019 ImageCLEFmed caption task. In L. Cappellato, N. Ferro, D. E. Losada, & H. Müller (Eds.), CLEF 2019 Working Notes: Working Notes of CLEF 2019 - Conferenceand Labs of the Evaluation Forum (pp. 1-15). [131] (CEUR Workshop Proceedings; Vol. 2380).
Singh, Sonit ; Karimi, Sarvnaz ; Ho-Shon, Kevin ; Hamey, Len. / Biomedical concept detection in medical images : MQ-CSIRO at 2019 ImageCLEFmed caption task. CLEF 2019 Working Notes: Working Notes of CLEF 2019 - Conferenceand Labs of the Evaluation Forum. editor / Linda Cappellato ; Nicola Ferro ; David E. Losada ; Henning Müller. 2019. pp. 1-15 (CEUR Workshop Proceedings).
@inproceedings{0199c7da3edf4e48acce2e2123688321,
title = "Biomedical concept detection in medical images: MQ-CSIRO at 2019 ImageCLEFmed caption task",
abstract = "We describe our concept detection system submitted for the ImageCLEFmed Caption task, part of the ImageCLEF 2019 challenge. The advancements in imaging technologies has improved the ability of clinicians to detect, diagnose, and treat diseases. Radiologists routinely interpret medical images and summarise their findings in the form of radiology reports. The mapping of visual information present in medical images to the condensed textual description is a tedious, time-consuming, expensive, and error-prone task. The development of methods that can automatically detect the presence and location of medical concepts in medical images can improve the efficiency of radiologists, reduce the burden of manual interpretation, and also help in reducing diagnostic errors. We propose a Convolutional Neural Network based multi-label image classifier to predict relevant concepts present in medical images. The proposed method achieved an F1-score of 0.1435 on the held-out test set of the 2019 ImageCLEFmed Caption Task. We present our proposed system with data analysis, experimental results, comparison, and discussion.",
keywords = "Caption Prediction, Computer Vision, Concept Detection, Convolutional Neural Network, Medical Imaging, Multi-label classification",
author = "Sonit Singh and Sarvnaz Karimi and Kevin Ho-Shon and Len Hamey",
note = "Copyright the Author(s) 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",
year = "2019",
month = "9",
day = "9",
language = "English",
series = "CEUR Workshop Proceedings",
pages = "1--15",
editor = "Linda Cappellato and Nicola Ferro and Losada, {David E.} and Henning M{\"u}ller",
booktitle = "CLEF 2019 Working Notes",

}

Singh, S, Karimi, S, Ho-Shon, K & Hamey, L 2019, Biomedical concept detection in medical images: MQ-CSIRO at 2019 ImageCLEFmed caption task. in L Cappellato, N Ferro, DE Losada & H Müller (eds), CLEF 2019 Working Notes: Working Notes of CLEF 2019 - Conferenceand Labs of the Evaluation Forum., 131, CEUR Workshop Proceedings, vol. 2380, pp. 1-15, 20th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2019, Lugano, Switzerland, 9/09/19.

Biomedical concept detection in medical images : MQ-CSIRO at 2019 ImageCLEFmed caption task. / Singh, Sonit; Karimi, Sarvnaz; Ho-Shon, Kevin; Hamey, Len.

CLEF 2019 Working Notes: Working Notes of CLEF 2019 - Conferenceand Labs of the Evaluation Forum. ed. / Linda Cappellato; Nicola Ferro; David E. Losada; Henning Müller. 2019. p. 1-15 131 (CEUR Workshop Proceedings; Vol. 2380).

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Biomedical concept detection in medical images

T2 - MQ-CSIRO at 2019 ImageCLEFmed caption task

AU - Singh, Sonit

AU - Karimi, Sarvnaz

AU - Ho-Shon, Kevin

AU - Hamey, Len

N1 - Copyright the Author(s) 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2019/9/9

Y1 - 2019/9/9

N2 - We describe our concept detection system submitted for the ImageCLEFmed Caption task, part of the ImageCLEF 2019 challenge. The advancements in imaging technologies has improved the ability of clinicians to detect, diagnose, and treat diseases. Radiologists routinely interpret medical images and summarise their findings in the form of radiology reports. The mapping of visual information present in medical images to the condensed textual description is a tedious, time-consuming, expensive, and error-prone task. The development of methods that can automatically detect the presence and location of medical concepts in medical images can improve the efficiency of radiologists, reduce the burden of manual interpretation, and also help in reducing diagnostic errors. We propose a Convolutional Neural Network based multi-label image classifier to predict relevant concepts present in medical images. The proposed method achieved an F1-score of 0.1435 on the held-out test set of the 2019 ImageCLEFmed Caption Task. We present our proposed system with data analysis, experimental results, comparison, and discussion.

AB - We describe our concept detection system submitted for the ImageCLEFmed Caption task, part of the ImageCLEF 2019 challenge. The advancements in imaging technologies has improved the ability of clinicians to detect, diagnose, and treat diseases. Radiologists routinely interpret medical images and summarise their findings in the form of radiology reports. The mapping of visual information present in medical images to the condensed textual description is a tedious, time-consuming, expensive, and error-prone task. The development of methods that can automatically detect the presence and location of medical concepts in medical images can improve the efficiency of radiologists, reduce the burden of manual interpretation, and also help in reducing diagnostic errors. We propose a Convolutional Neural Network based multi-label image classifier to predict relevant concepts present in medical images. The proposed method achieved an F1-score of 0.1435 on the held-out test set of the 2019 ImageCLEFmed Caption Task. We present our proposed system with data analysis, experimental results, comparison, and discussion.

KW - Caption Prediction

KW - Computer Vision

KW - Concept Detection

KW - Convolutional Neural Network

KW - Medical Imaging

KW - Multi-label classification

UR - http://www.scopus.com/inward/record.url?scp=85070523349&partnerID=8YFLogxK

UR - http://ceur-ws.org/Vol-2380/

M3 - Conference proceeding contribution

T3 - CEUR Workshop Proceedings

SP - 1

EP - 15

BT - CLEF 2019 Working Notes

A2 - Cappellato, Linda

A2 - Ferro, Nicola

A2 - Losada, David E.

A2 - Müller, Henning

ER -

Singh S, Karimi S, Ho-Shon K, Hamey L. Biomedical concept detection in medical images: MQ-CSIRO at 2019 ImageCLEFmed caption task. In Cappellato L, Ferro N, Losada DE, Müller H, editors, CLEF 2019 Working Notes: Working Notes of CLEF 2019 - Conferenceand Labs of the Evaluation Forum. 2019. p. 1-15. 131. (CEUR Workshop Proceedings).