Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autorschaft

  • Jorge Adrián Badilla Solórzano
  • Nils Claudius Gellrich
  • Thomas Seel
  • Sontje Ihler

Organisationseinheiten

Externe Organisationen

  • Medizinische Hochschule Hannover (MHH)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksData Augmentation, Labelling, and Imperfections
UntertitelThird MICCAI Workshop, DALI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 12, 2023, Proceedings
Herausgeber/-innenYuan Xue, Chen Chen, Chao Chen, Lianrui Zuo, Yihao Liu
Seiten95-105
Seitenumfang11
ISBN (elektronisch)978-3-031-58171-7
PublikationsstatusVeröffentlicht - 27 Apr. 2024

Publikationsreihe

Name Lecture Notes in Computer Science
Band14379
ISSN (Print)0302-9743
ISSN (elektronisch)1611-3349

Abstract

Surgical instrument detection is a fundamental task of a
robotic scrub nurse. For this, image-based deep learning techniques are
effective but usually demand large amounts of annotated data, whose creation
is expensive and time-consuming. In this work, we propose a strategy
based on the copy-paste technique for the generation of reliable synthetic
image training data with a minimal amount of annotation effort.
Our approach enables the efficient in situ creation of datasets for specific
surgeries and contexts. We study the amount of employed manually annotated
data and training set sizes on our model’s performance, as well
as different blending techniques for improved training data. We achieve
91.9 box mAP and 91.6 mask mAP, training solely on synthetic data, in a
real-world scenario. Our evaluation relies on an annotated image dataset
of the wisdom teeth extraction surgery set, created in an actual operating
room. This dataset, the corresponding code, and further data are made
publicly available (https://github.com/Jorebs/Modular-Label-Efficient-
Dataset-Generation-for-Instrument-Detection-for-Robotic-Scrub-Nurses).

ASJC Scopus Sachgebiete

Zitieren

Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses. / Badilla Solórzano, Jorge Adrián; Gellrich, Nils Claudius; Seel, Thomas et al.
Data Augmentation, Labelling, and Imperfections : Third MICCAI Workshop, DALI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 12, 2023, Proceedings. Hrsg. / Yuan Xue; Chen Chen; Chao Chen; Lianrui Zuo; Yihao Liu. 2024. S. 95-105 ( Lecture Notes in Computer Science ; Band 14379).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Badilla Solórzano, JA, Gellrich, NC, Seel, T & Ihler, S 2024, Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses. in Y Xue, C Chen, C Chen, L Zuo & Y Liu (Hrsg.), Data Augmentation, Labelling, and Imperfections : Third MICCAI Workshop, DALI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 12, 2023, Proceedings. Lecture Notes in Computer Science , Bd. 14379, S. 95-105. https://doi.org/10.1007/978-3-031-58171-7_10
Badilla Solórzano, J. A., Gellrich, N. C., Seel, T., & Ihler, S. (2024). Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses. In Y. Xue, C. Chen, C. Chen, L. Zuo, & Y. Liu (Hrsg.), Data Augmentation, Labelling, and Imperfections : Third MICCAI Workshop, DALI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 12, 2023, Proceedings (S. 95-105). ( Lecture Notes in Computer Science ; Band 14379). https://doi.org/10.1007/978-3-031-58171-7_10
Badilla Solórzano JA, Gellrich NC, Seel T, Ihler S. Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses. in Xue Y, Chen C, Chen C, Zuo L, Liu Y, Hrsg., Data Augmentation, Labelling, and Imperfections : Third MICCAI Workshop, DALI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 12, 2023, Proceedings. 2024. S. 95-105. ( Lecture Notes in Computer Science ). doi: 10.1007/978-3-031-58171-7_10
Badilla Solórzano, Jorge Adrián ; Gellrich, Nils Claudius ; Seel, Thomas et al. / Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses. Data Augmentation, Labelling, and Imperfections : Third MICCAI Workshop, DALI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 12, 2023, Proceedings. Hrsg. / Yuan Xue ; Chen Chen ; Chao Chen ; Lianrui Zuo ; Yihao Liu. 2024. S. 95-105 ( Lecture Notes in Computer Science ).
Download
@inproceedings{ebc3274951d24c98a161cd5156acde5b,
title = "Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses",
abstract = "Surgical instrument detection is a fundamental task of arobotic scrub nurse. For this, image-based deep learning techniques areeffective but usually demand large amounts of annotated data, whose creationis expensive and time-consuming. In this work, we propose a strategybased on the copy-paste technique for the generation of reliable syntheticimage training data with a minimal amount of annotation effort.Our approach enables the efficient in situ creation of datasets for specificsurgeries and contexts. We study the amount of employed manually annotateddata and training set sizes on our model{\textquoteright}s performance, as wellas different blending techniques for improved training data. We achieve91.9 box mAP and 91.6 mask mAP, training solely on synthetic data, in areal-world scenario. Our evaluation relies on an annotated image datasetof the wisdom teeth extraction surgery set, created in an actual operatingroom. This dataset, the corresponding code, and further data are madepublicly available (https://github.com/Jorebs/Modular-Label-Efficient-Dataset-Generation-for-Instrument-Detection-for-Robotic-Scrub-Nurses).",
keywords = "Synthetic data, Efficient annotation, Robotic scrub nurse, MBOI, Copy-paste, Deep learning, Robotic Scrub Nurse",
author = "{Badilla Sol{\'o}rzano}, {Jorge Adri{\'a}n} and Gellrich, {Nils Claudius} and Thomas Seel and Sontje Ihler",
year = "2024",
month = apr,
day = "27",
doi = "10.1007/978-3-031-58171-7_10",
language = "English",
isbn = "978-3-031-58170-0",
series = " Lecture Notes in Computer Science ",
pages = "95--105",
editor = "Yuan Xue and Chen Chen and Chao Chen and Lianrui Zuo and Yihao Liu",
booktitle = "Data Augmentation, Labelling, and Imperfections",

}

Download

TY - GEN

T1 - Modular, Label-Efficient Dataset Generation for Instrument Detection for Robotic Scrub Nurses

AU - Badilla Solórzano, Jorge Adrián

AU - Gellrich, Nils Claudius

AU - Seel, Thomas

AU - Ihler, Sontje

PY - 2024/4/27

Y1 - 2024/4/27

N2 - Surgical instrument detection is a fundamental task of arobotic scrub nurse. For this, image-based deep learning techniques areeffective but usually demand large amounts of annotated data, whose creationis expensive and time-consuming. In this work, we propose a strategybased on the copy-paste technique for the generation of reliable syntheticimage training data with a minimal amount of annotation effort.Our approach enables the efficient in situ creation of datasets for specificsurgeries and contexts. We study the amount of employed manually annotateddata and training set sizes on our model’s performance, as wellas different blending techniques for improved training data. We achieve91.9 box mAP and 91.6 mask mAP, training solely on synthetic data, in areal-world scenario. Our evaluation relies on an annotated image datasetof the wisdom teeth extraction surgery set, created in an actual operatingroom. This dataset, the corresponding code, and further data are madepublicly available (https://github.com/Jorebs/Modular-Label-Efficient-Dataset-Generation-for-Instrument-Detection-for-Robotic-Scrub-Nurses).

AB - Surgical instrument detection is a fundamental task of arobotic scrub nurse. For this, image-based deep learning techniques areeffective but usually demand large amounts of annotated data, whose creationis expensive and time-consuming. In this work, we propose a strategybased on the copy-paste technique for the generation of reliable syntheticimage training data with a minimal amount of annotation effort.Our approach enables the efficient in situ creation of datasets for specificsurgeries and contexts. We study the amount of employed manually annotateddata and training set sizes on our model’s performance, as wellas different blending techniques for improved training data. We achieve91.9 box mAP and 91.6 mask mAP, training solely on synthetic data, in areal-world scenario. Our evaluation relies on an annotated image datasetof the wisdom teeth extraction surgery set, created in an actual operatingroom. This dataset, the corresponding code, and further data are madepublicly available (https://github.com/Jorebs/Modular-Label-Efficient-Dataset-Generation-for-Instrument-Detection-for-Robotic-Scrub-Nurses).

KW - Synthetic data

KW - Efficient annotation

KW - Robotic scrub nurse

KW - MBOI

KW - Copy-paste

KW - Deep learning

KW - Robotic Scrub Nurse

UR - http://www.scopus.com/inward/record.url?scp=85192879852&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-58171-7_10

DO - 10.1007/978-3-031-58171-7_10

M3 - Conference contribution

SN - 978-3-031-58170-0

T3 - Lecture Notes in Computer Science

SP - 95

EP - 105

BT - Data Augmentation, Labelling, and Imperfections

A2 - Xue, Yuan

A2 - Chen, Chen

A2 - Chen, Chao

A2 - Zuo, Lianrui

A2 - Liu, Yihao

ER -

Von denselben Autoren