Automatic detection of perforators for microsurgical reconstruction

Carlos Mavioso, Ricardo J. Araújo, Hélder P. Oliveira, João C. Anacleto, Maria Antónia Vasconcelos, David Pinto, Pedro F. Gouveia, Celeste Alves, Fátima Cardoso, Jaime S. Cardoso, Maria João Cardoso

Research output: Contribution to journalArticle

Abstract

The deep inferior epigastric perforator (DIEP) is the most commonly used free flap in mastectomy reconstruction. Preoperative imaging techniques are routinely used to detect location, diameter and course of perforators, with direct intervention from the imaging team, who subsequently draw a chart that will help surgeons choosing the best vascular support for the reconstruction. In this work, the feasibility of using a computer software to support the preoperative planning of 40 patients proposed for breast reconstruction with a DIEP flap is evaluated for the first time. Blood vessel centreline extraction and local characterization algorithms are applied to identify perforators and compared with the manual mapping, aiming to reduce the time spent by the imaging team, as well as the inherent subjectivity to the task. Comparing with the measures taken during surgery, the software calibre estimates were worse for vessels smaller than 1.5 mm (P = 6e-4) but better for the remaining ones (P = 2e-3). Regarding vessel location, the vertical component of the software output was significantly different from the manual measure (P = 0.02), nonetheless that was irrelevant during surgery as errors in the order of 2–3 mm do not have impact in the dissection step. Our trials support that a reduction of the time spent is achievable using the automatic tool (about 2 h/case). The introduction of artificial intelligence in clinical practice intends to simplify the work of health professionals and to provide better outcomes to patients. This pilot study paves the way for a success story.

Original languageEnglish
Pages (from-to)19-24
Number of pages6
JournalBreast
Volume50
DOIs
Publication statusPublished - 1 Apr 2020

Fingerprint

Software
Blood Vessels
Perforator Flap
Mammaplasty
Free Tissue Flaps
Artificial Intelligence
Mastectomy
Dissection
Health
Surgeons

Keywords

  • Automatic detection
  • Computer vision
  • DIEP
  • Flap
  • Image analysis
  • Microsurgery
  • Perforators
  • Pre-operative mapping

Cite this

Mavioso, C., Araújo, R. J., Oliveira, H. P., Anacleto, J. C., Vasconcelos, M. A., Pinto, D., ... Cardoso, M. J. (2020). Automatic detection of perforators for microsurgical reconstruction. Breast, 50, 19-24. https://doi.org/10.1016/j.breast.2020.01.001
Mavioso, Carlos ; Araújo, Ricardo J. ; Oliveira, Hélder P. ; Anacleto, João C. ; Vasconcelos, Maria Antónia ; Pinto, David ; Gouveia, Pedro F. ; Alves, Celeste ; Cardoso, Fátima ; Cardoso, Jaime S. ; Cardoso, Maria João. / Automatic detection of perforators for microsurgical reconstruction. In: Breast. 2020 ; Vol. 50. pp. 19-24.
@article{0734fb88fcfe46bdaa83b5631c651892,
title = "Automatic detection of perforators for microsurgical reconstruction",
abstract = "The deep inferior epigastric perforator (DIEP) is the most commonly used free flap in mastectomy reconstruction. Preoperative imaging techniques are routinely used to detect location, diameter and course of perforators, with direct intervention from the imaging team, who subsequently draw a chart that will help surgeons choosing the best vascular support for the reconstruction. In this work, the feasibility of using a computer software to support the preoperative planning of 40 patients proposed for breast reconstruction with a DIEP flap is evaluated for the first time. Blood vessel centreline extraction and local characterization algorithms are applied to identify perforators and compared with the manual mapping, aiming to reduce the time spent by the imaging team, as well as the inherent subjectivity to the task. Comparing with the measures taken during surgery, the software calibre estimates were worse for vessels smaller than 1.5 mm (P = 6e-4) but better for the remaining ones (P = 2e-3). Regarding vessel location, the vertical component of the software output was significantly different from the manual measure (P = 0.02), nonetheless that was irrelevant during surgery as errors in the order of 2–3 mm do not have impact in the dissection step. Our trials support that a reduction of the time spent is achievable using the automatic tool (about 2 h/case). The introduction of artificial intelligence in clinical practice intends to simplify the work of health professionals and to provide better outcomes to patients. This pilot study paves the way for a success story.",
keywords = "Automatic detection, Computer vision, DIEP, Flap, Image analysis, Microsurgery, Perforators, Pre-operative mapping",
author = "Carlos Mavioso and Ara{\'u}jo, {Ricardo J.} and Oliveira, {H{\'e}lder P.} and Anacleto, {Jo{\~a}o C.} and Vasconcelos, {Maria Ant{\'o}nia} and David Pinto and Gouveia, {Pedro F.} and Celeste Alves and F{\'a}tima Cardoso and Cardoso, {Jaime S.} and Cardoso, {Maria Jo{\~a}o}",
year = "2020",
month = "4",
day = "1",
doi = "10.1016/j.breast.2020.01.001",
language = "English",
volume = "50",
pages = "19--24",
journal = "Breast Journal",
issn = "1075-122X",
publisher = "Blackwell Publishing Ltd",

}

Mavioso, C, Araújo, RJ, Oliveira, HP, Anacleto, JC, Vasconcelos, MA, Pinto, D, Gouveia, PF, Alves, C, Cardoso, F, Cardoso, JS & Cardoso, MJ 2020, 'Automatic detection of perforators for microsurgical reconstruction', Breast, vol. 50, pp. 19-24. https://doi.org/10.1016/j.breast.2020.01.001

Automatic detection of perforators for microsurgical reconstruction. / Mavioso, Carlos; Araújo, Ricardo J.; Oliveira, Hélder P.; Anacleto, João C.; Vasconcelos, Maria Antónia; Pinto, David; Gouveia, Pedro F.; Alves, Celeste; Cardoso, Fátima; Cardoso, Jaime S.; Cardoso, Maria João.

In: Breast, Vol. 50, 01.04.2020, p. 19-24.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic detection of perforators for microsurgical reconstruction

AU - Mavioso, Carlos

AU - Araújo, Ricardo J.

AU - Oliveira, Hélder P.

AU - Anacleto, João C.

AU - Vasconcelos, Maria Antónia

AU - Pinto, David

AU - Gouveia, Pedro F.

AU - Alves, Celeste

AU - Cardoso, Fátima

AU - Cardoso, Jaime S.

AU - Cardoso, Maria João

PY - 2020/4/1

Y1 - 2020/4/1

N2 - The deep inferior epigastric perforator (DIEP) is the most commonly used free flap in mastectomy reconstruction. Preoperative imaging techniques are routinely used to detect location, diameter and course of perforators, with direct intervention from the imaging team, who subsequently draw a chart that will help surgeons choosing the best vascular support for the reconstruction. In this work, the feasibility of using a computer software to support the preoperative planning of 40 patients proposed for breast reconstruction with a DIEP flap is evaluated for the first time. Blood vessel centreline extraction and local characterization algorithms are applied to identify perforators and compared with the manual mapping, aiming to reduce the time spent by the imaging team, as well as the inherent subjectivity to the task. Comparing with the measures taken during surgery, the software calibre estimates were worse for vessels smaller than 1.5 mm (P = 6e-4) but better for the remaining ones (P = 2e-3). Regarding vessel location, the vertical component of the software output was significantly different from the manual measure (P = 0.02), nonetheless that was irrelevant during surgery as errors in the order of 2–3 mm do not have impact in the dissection step. Our trials support that a reduction of the time spent is achievable using the automatic tool (about 2 h/case). The introduction of artificial intelligence in clinical practice intends to simplify the work of health professionals and to provide better outcomes to patients. This pilot study paves the way for a success story.

AB - The deep inferior epigastric perforator (DIEP) is the most commonly used free flap in mastectomy reconstruction. Preoperative imaging techniques are routinely used to detect location, diameter and course of perforators, with direct intervention from the imaging team, who subsequently draw a chart that will help surgeons choosing the best vascular support for the reconstruction. In this work, the feasibility of using a computer software to support the preoperative planning of 40 patients proposed for breast reconstruction with a DIEP flap is evaluated for the first time. Blood vessel centreline extraction and local characterization algorithms are applied to identify perforators and compared with the manual mapping, aiming to reduce the time spent by the imaging team, as well as the inherent subjectivity to the task. Comparing with the measures taken during surgery, the software calibre estimates were worse for vessels smaller than 1.5 mm (P = 6e-4) but better for the remaining ones (P = 2e-3). Regarding vessel location, the vertical component of the software output was significantly different from the manual measure (P = 0.02), nonetheless that was irrelevant during surgery as errors in the order of 2–3 mm do not have impact in the dissection step. Our trials support that a reduction of the time spent is achievable using the automatic tool (about 2 h/case). The introduction of artificial intelligence in clinical practice intends to simplify the work of health professionals and to provide better outcomes to patients. This pilot study paves the way for a success story.

KW - Automatic detection

KW - Computer vision

KW - DIEP

KW - Flap

KW - Image analysis

KW - Microsurgery

KW - Perforators

KW - Pre-operative mapping

UR - http://www.scopus.com/inward/record.url?scp=85077971737&partnerID=8YFLogxK

U2 - 10.1016/j.breast.2020.01.001

DO - 10.1016/j.breast.2020.01.001

M3 - Article

VL - 50

SP - 19

EP - 24

JO - Breast Journal

JF - Breast Journal

SN - 1075-122X

ER -

Mavioso C, Araújo RJ, Oliveira HP, Anacleto JC, Vasconcelos MA, Pinto D et al. Automatic detection of perforators for microsurgical reconstruction. Breast. 2020 Apr 1;50:19-24. https://doi.org/10.1016/j.breast.2020.01.001