Real-Time Suture Thread Detection with an Image Classifier

Kyotaro Horio; Kanako Harada; Jun Muto; Hirofumi Nakatomi; Nobuhito Saito; Akio Morita; Eiju Watanabe; Mamoru Mitsuishi

doi:10.20965/jrm.2022.p1245

Real-Time Suture Thread Detection with an Image Classifier

Kyotaro Horio
, Kanako Harada
, Jun Muto
, Hirofumi Nakatomi
, Nobuhito Saito
, Akio Morita
, Eiju Watanabe
, Mamoru Mitsuishi

Neurosurgery

Research output: Contribution to journal › Article › peer-review

Abstract

Micro-anastomosis is considered to be a difficult task even for skilled surgeons. Our group has developed a surgical robotic system to assist surgeons. Going further, the detection of surgically relevant objects in the microscopic view is indispensable for the automation or semi-automation of the system. This paper proposes a novel surgical thread detector inspired by an automatic crack detection method. The proposed method achieved a Dice score of 76.30% and an inter-section over union (IOU) of 66.08% at 34.50 fps.

Original language	English
Pages (from-to)	1245-1252
Number of pages	8
Journal	Journal of Robotics and Mechatronics
Volume	34
Issue number	6
DOIs	https://doi.org/10.20965/jrm.2022.p1245
Publication status	Published - 12-2022

All Science Journal Classification (ASJC) codes

General Computer Science
Electrical and Electronic Engineering

Access to Document

10.20965/jrm.2022.p1245

Cite this

@article{7a9d84c0cd044779aa61614747601771,

title = "Real-Time Suture Thread Detection with an Image Classifier",

abstract = "Micro-anastomosis is considered to be a difficult task even for skilled surgeons. Our group has developed a surgical robotic system to assist surgeons. Going further, the detection of surgically relevant objects in the microscopic view is indispensable for the automation or semi-automation of the system. This paper proposes a novel surgical thread detector inspired by an automatic crack detection method. The proposed method achieved a Dice score of 76.30\% and an inter-section over union (IOU) of 66.08\% at 34.50 fps.",

keywords = "deep learning, object detection, surgical robot",

author = "Kyotaro Horio and Kanako Harada and Jun Muto and Hirofumi Nakatomi and Nobuhito Saito and Akio Morita and Eiju Watanabe and Mamoru Mitsuishi",

note = "Publisher Copyright: {\textcopyright} Fuji Technology Press Ltd.",

year = "2022",

month = dec,

doi = "10.20965/jrm.2022.p1245",

language = "English",

volume = "34",

pages = "1245--1252",

journal = "Journal of Robotics and Mechatronics",

issn = "0915-3942",

publisher = "Fuji Technology Press",

number = "6",

}

TY - JOUR

T1 - Real-Time Suture Thread Detection with an Image Classifier

AU - Horio, Kyotaro

AU - Harada, Kanako

AU - Muto, Jun

AU - Nakatomi, Hirofumi

AU - Saito, Nobuhito

AU - Morita, Akio

AU - Watanabe, Eiju

AU - Mitsuishi, Mamoru

N1 - Publisher Copyright: © Fuji Technology Press Ltd.

PY - 2022/12

Y1 - 2022/12

N2 - Micro-anastomosis is considered to be a difficult task even for skilled surgeons. Our group has developed a surgical robotic system to assist surgeons. Going further, the detection of surgically relevant objects in the microscopic view is indispensable for the automation or semi-automation of the system. This paper proposes a novel surgical thread detector inspired by an automatic crack detection method. The proposed method achieved a Dice score of 76.30% and an inter-section over union (IOU) of 66.08% at 34.50 fps.

AB - Micro-anastomosis is considered to be a difficult task even for skilled surgeons. Our group has developed a surgical robotic system to assist surgeons. Going further, the detection of surgically relevant objects in the microscopic view is indispensable for the automation or semi-automation of the system. This paper proposes a novel surgical thread detector inspired by an automatic crack detection method. The proposed method achieved a Dice score of 76.30% and an inter-section over union (IOU) of 66.08% at 34.50 fps.

KW - deep learning

KW - object detection

KW - surgical robot

UR - https://www.scopus.com/pages/publications/85144300409

UR - https://www.scopus.com/pages/publications/85144300409#tab=citedBy

U2 - 10.20965/jrm.2022.p1245

DO - 10.20965/jrm.2022.p1245

M3 - Article

AN - SCOPUS:85144300409

SN - 0915-3942

VL - 34

SP - 1245

EP - 1252

JO - Journal of Robotics and Mechatronics

JF - Journal of Robotics and Mechatronics

IS - 6

ER -

Real-Time Suture Thread Detection with an Image Classifier

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this