Multi-class artefact detection in video endoscopy via convolution neural networks

Mohammad Azam Khan, Jaegul Choo

Research output: Contribution to journalConference article

Abstract

This paper describes our approach for EAD2019: Multi-class artefact detection in video endoscopy. We optimized focal loss for dense object detection based RetinaNet network pretrained with the ImageNet dataset and applied several data augmentation and hyperparmeter tuning strategies, obtaining a weighted final score of 0.2880 for multi-class artefact detection task and mean average precision (mAP) score of 0.2187 with deviation 0.0770 for multi-class artefact generalisation task. In addition, we developed a U-Net based convolutional neural networks (CNNs) for multi-class artefact region segmentation task and achieved a final score of 0.4320 for the online test set in the competition.

Original languageEnglish
JournalCEUR Workshop Proceedings
Volume2366
Publication statusPublished - 2019 Jan 1
Event2019 Challenge on Endoscopy Artefacts Detection: Multi-Class Artefact Detection in Video Endoscopy, EAD 2019 - Venice, Italy
Duration: 2019 Apr 8 → …

Fingerprint

Endoscopy
Convolution
Tuning
Neural networks
Object detection

Keywords

  • Artefact generalization
  • Convolutional neural networks
  • Terms— endoscopic artefact
  • Video endoscopy

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Multi-class artefact detection in video endoscopy via convolution neural networks. / Khan, Mohammad Azam; Choo, Jaegul.

In: CEUR Workshop Proceedings, Vol. 2366, 01.01.2019.

Research output: Contribution to journalConference article

@article{d21136bf06284dc9b3dfa044c5c4f203,
title = "Multi-class artefact detection in video endoscopy via convolution neural networks",
abstract = "This paper describes our approach for EAD2019: Multi-class artefact detection in video endoscopy. We optimized focal loss for dense object detection based RetinaNet network pretrained with the ImageNet dataset and applied several data augmentation and hyperparmeter tuning strategies, obtaining a weighted final score of 0.2880 for multi-class artefact detection task and mean average precision (mAP) score of 0.2187 with deviation 0.0770 for multi-class artefact generalisation task. In addition, we developed a U-Net based convolutional neural networks (CNNs) for multi-class artefact region segmentation task and achieved a final score of 0.4320 for the online test set in the competition.",
keywords = "Artefact generalization, Convolutional neural networks, Terms— endoscopic artefact, Video endoscopy",
author = "Khan, {Mohammad Azam} and Jaegul Choo",
year = "2019",
month = "1",
day = "1",
language = "English",
volume = "2366",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - Multi-class artefact detection in video endoscopy via convolution neural networks

AU - Khan, Mohammad Azam

AU - Choo, Jaegul

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper describes our approach for EAD2019: Multi-class artefact detection in video endoscopy. We optimized focal loss for dense object detection based RetinaNet network pretrained with the ImageNet dataset and applied several data augmentation and hyperparmeter tuning strategies, obtaining a weighted final score of 0.2880 for multi-class artefact detection task and mean average precision (mAP) score of 0.2187 with deviation 0.0770 for multi-class artefact generalisation task. In addition, we developed a U-Net based convolutional neural networks (CNNs) for multi-class artefact region segmentation task and achieved a final score of 0.4320 for the online test set in the competition.

AB - This paper describes our approach for EAD2019: Multi-class artefact detection in video endoscopy. We optimized focal loss for dense object detection based RetinaNet network pretrained with the ImageNet dataset and applied several data augmentation and hyperparmeter tuning strategies, obtaining a weighted final score of 0.2880 for multi-class artefact detection task and mean average precision (mAP) score of 0.2187 with deviation 0.0770 for multi-class artefact generalisation task. In addition, we developed a U-Net based convolutional neural networks (CNNs) for multi-class artefact region segmentation task and achieved a final score of 0.4320 for the online test set in the competition.

KW - Artefact generalization

KW - Convolutional neural networks

KW - Terms— endoscopic artefact

KW - Video endoscopy

UR - http://www.scopus.com/inward/record.url?scp=85066508317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066508317&partnerID=8YFLogxK

M3 - Conference article

VL - 2366

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -