EUVIMEDEUVIMED entdecken
Crossref

Taking measurement in every direction: Implicit scene representation for accurately estimating target dimensions under monocular endoscope

Yuchen Zhou, Rui Li, Yu Dai, Gongping Chen, Jianxun Zhang, Liang Cui, Xiaotao Yin

Computer Methods and Programs in Biomedicine · 2024

DOI: 10.1016/j.cmpb.2024.108380 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2024. Verfasst von Yuchen Zhou und 6 weiteren Autor:innen. Beteiligte Einrichtung: The College of Artificial Intelligence, Nankai University, Tianjin 300350, China; The Institute of Robotics and Automatic Information System, Tianjin…. Hauptthemen laut MEDLINE: Endoscopes. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVES: In endoscopy, measurement of target size can assist medical diagnosis. However, limited operating space, low image quality, and irregular target shape pose great challenges to traditional vision-based measurement methods. METHODS: In this paper, we propose a novel approach to measure irregular target size under monocular endoscope using image rendering. Firstly synthesize virtual poses on the same main optical axis as known camera poses, and use implicit neural representation module that considers brightness and target boundaries to render images corresponding to virtual poses. Then, Swin-Unet and rotating calipers are utilized to obtain maximum pixel length of the target in image pairs with the same main optical axis. Finally, the similarity triangle relationship of the endoscopic imaging model is used to measure the size of the target. RESULTS: The evaluation is conducted using renal stone fragments of patients which are placed in the kidney model and the isolated porcine kidney. The mean error of measurement is 0.12 mm. CONCLUSIONS: The approached method can automatically measure object size within narrow body cavities in any visible direction. It improves the effectiveness and accuracy of measurement in limited endoscopic space.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EndoscopesSwineHumansAnimalsAlgorithmsEndoscopyImage Processing, Computer-AssistedKidneyImaging, Three-Dimensional

Stichwörter der Autor:innen

EndoscopyImplicit scene representationTarget dimension measurement

Autor:innen und Institutionen

  • The College of Artificial Intelligence, Nankai University, Tianjin 300350, China; The Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, Tianjin 300350, China.
  • The College of Artificial Intelligence, Nankai University, Tianjin 300350, China; The Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, Tianjin 300350, China. Electr…
  • Department of Urology, Civil Aviation General Hospital, Beijing 100123, China.
  • Department of Urology, Fourth Medical Center of Chinese, PLA General Hospital, Beijing 10048, China.

Zitieren

APA

Zhou, Y., Li, R., Dai, Y., Chen, G., Zhang, J., Cui, L., & Yin, X. (2024). Taking measurement in every direction: Implicit scene representation for accurately estimating target dimensions under monocular endoscope. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2024.108380

Vancouver

Zhou Y, Li R, Dai Y, Chen G, Zhang J, Cui L, et al. Taking measurement in every direction: Implicit scene representation for accurately estimating target dimensions under monocular endoscope. Computer Methods and Programs in Biomedicine. 2024. doi:10.1016/j.cmpb.2024.108380

BibTeX
@article{Zhou2024,
  author = {Zhou, Yuchen and Li, Rui and Dai, Yu and Chen, Gongping and Zhang, Jianxun and Cui, Liang and Yin, Xiaotao},
  title = {Taking measurement in every direction: Implicit scene representation for accurately estimating target dimensions under monocular endoscope},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2024},
  doi = {10.1016/j.cmpb.2024.108380}
}
Kostenlos starten →