EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

UMInSe: An Unsupervised Method for Segmentation and Detection of Surgical Instruments based on K-means

Rodrigo Eduardo Arevalo-Ancona, Daniel Haro-Mendoza, Manuel Cedillo-Hernandez, Victor J. Gonzalez-Villela

Revista Mexicana de Ingeniería Biomédica · 14.09.2024 · 45 (3) · 20-50

DOI: 10.17488/rmib.45.3.2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Revista Mexicana de Ingeniería Biomédica, online erschienen am 14.09.2024. Verfasst von Rodrigo Eduardo Arevalo-Ancona und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Surgical instrument segmentation in images is crucial for improving precision and efficiency in surgery, but it currently relies on costly and labor-intensive manual annotations. An unsupervised approach is a promising solution to this challenge. This paper introduces a surgical instrument segmentation method using unsupervised machine learning, based on the K-means algorithm, to identify Regions of Interest (ROI) in images and create the image ground truth for neural network training. The Gamma correction adjusts image brightness and enhances the identification of areas containing surgical instruments. The K-means algorithm clusters similar pixels and detects ROIs despite changes in illumination, yielding an efficient segmentation despite variations in image illumination and obstructing objects. As a result, the neural network learns image features that generalize to instrument segmentation in different tasks. Experimental results using the JIGSAWS and EndoVis databases demonstrate the method's effectiveness and robustness, with a minimal error (0.0297) and high accuracy (0.9602). These results underscore the precision of surgical instrument detection and segmentation, which is crucial for automating instrument detection in surgical procedures without pre-labeled datasets. Furthermore, this technique could be applied in surgical applications such as surgeon skills assessment and robot motion planning, where precise instrument detection is indispensable.

Zitieren

APA

Arevalo-Ancona, R. E., Haro-Mendoza, D., Cedillo-Hernandez, M., & Gonzalez-Villela, V. J. (2024). UMInSe: An Unsupervised Method for Segmentation and Detection of Surgical Instruments based on K-means. Revista Mexicana de Ingeniería Biomédica, 45(3), 20-50. https://doi.org/10.17488/rmib.45.3.2

Vancouver

Arevalo-Ancona RE, Haro-Mendoza D, Cedillo-Hernandez M, Gonzalez-Villela VJ. UMInSe: An Unsupervised Method for Segmentation and Detection of Surgical Instruments based on K-means. Revista Mexicana de Ingeniería Biomédica. 2024;45(3):20-50. doi:10.17488/rmib.45.3.2

BibTeX
@article{ArevaloAncona2024,
  author = {Arevalo-Ancona, Rodrigo Eduardo and Haro-Mendoza, Daniel and Cedillo-Hernandez, Manuel and Gonzalez-Villela, Victor J.},
  title = {UMInSe: An Unsupervised Method for Segmentation and Detection of Surgical Instruments based on K-means},
  journal = {Revista Mexicana de Ingeniería Biomédica},
  year = {2024},
  volume = {45},
  number = {3},
  pages = {20--50},
  doi = {10.17488/rmib.45.3.2}
}
Kostenlos starten →