EUVIMEDEUVIMED entdecken
Crossref

Deep-Learning Segmentation of Urinary Stones in Noncontrast Computed Tomography

Young In Kim, Sang Hoon Song iD, Juhyun Park, Hye Jung Youn, Jihoon Kweon, Hyung Keun Park

Journal of Endourology · 2023-05 · 37 (5) · 595-606

DOI: 10.1089/end.2022.0722 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Endourology, online erschienen am 01.05.2023. Verfasst von Young In Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Science, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medi…. Hauptthemen laut MEDLINE: Deep Learning, Urolithiasis, Urinary Calculi. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 33 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Noncontrast CT (NCCT) relies on labor-intensive examinations of CT slices to identify urolithiasis in the urinary tract, and, despite the use of deep-learning algorithms, false positives remain. Materials and Methods: A total of 410 NCCT axial scans from patients undergoing surgical treatment for urolithiasis were used for model development. The deep learning model was customized to combine a urolithiasis segmentation with per-slice classification for screening. Prediction models of the axial, coronal, and sagittal views were trained, and an additive model with an intersection of the coronal and sagittal predictions added to the axial outcome was introduced. Automated quantification of clinical metrics was evaluated in three-dimensional models of urinary stones.

Results

The axial model detected 88.92% of urinary stones and produced a dice similarity coefficient of 87.56% in the urolithiasis segmentation. For urolithiasis (>5 mm), the sensitivity of the axial model reached 95.10%. False positives were reduced to 0.34 per patient using an ensemble of individual models. The additive model improved the sensitivity to 90.97% by detecting more small urolithiasis ( 0.964.

Conclusions

The proposed system could reduce the burden on the physician for imaging diagnosis and help determine treatment strategies for urinary stones through automated quantification of clinical metrics with high accuracy and reproducibility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningUrolithiasisUrinary CalculiHumansReproducibility of ResultsTomography, X-Ray Computed

Stichwörter der Autor:innen

deep learningmultiview ensemblesegmentationurinary stone

Autor:innen und Institutionen

  • Department of Medical Science, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.
  • Department of Urology, and Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.
  • Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.

ORCID-Profile: Sang Hoon Song

Zitieren

APA

Kim, Y. I., Song, S. H., Park, J., Youn, H. J., Kweon, J., & Park, H. K. (2023). Deep-Learning Segmentation of Urinary Stones in Noncontrast Computed Tomography. Journal of Endourology, 37(5), 595-606. https://doi.org/10.1089/end.2022.0722

Vancouver

Kim YI, Song SH, Park J, Youn HJ, Kweon J, Park HK. Deep-Learning Segmentation of Urinary Stones in Noncontrast Computed Tomography. Journal of Endourology. 2023;37(5):595-606. doi:10.1089/end.2022.0722

BibTeX
@article{Kim2023,
  author = {Kim, Young In and Song, Sang Hoon and Park, Juhyun and Youn, Hye Jung and Kweon, Jihoon and Park, Hyung Keun},
  title = {Deep-Learning Segmentation of Urinary Stones in Noncontrast Computed Tomography},
  journal = {Journal of Endourology},
  year = {2023},
  volume = {37},
  number = {5},
  pages = {595--606},
  doi = {10.1089/end.2022.0722}
}
Kostenlos starten →