EUVIMEDEUVIMED entdecken
Crossref

THA-Net: A Deep Learning Solution for Next-Generation Templating and Patient-specific Surgical Execution

Pouria Rouzrokh, Bardia Khosravi, John P Mickley, Bradley J Erickson, Michael J Taunton, Cody C Wyles

The Journal of Arthroplasty · 2024

DOI: 10.1016/j.arth.2023.08.063 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Arthroplasty, 2024. Verfasst von Pouria Rouzrokh und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Mayo Clinic, Minnesota. Hauptthemen laut MEDLINE: Arthroplasty, Replacement, Hip, Hip Prosthesis, Deep Learning. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 35 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: This study introduces THA-Net, a deep learning inpainting algorithm for simulating postoperative total hip arthroplasty (THA) radiographs from a single preoperative pelvis radiograph input, while being able to generate predictions either unconditionally (algorithm chooses implants) or conditionally (surgeon chooses implants). METHODS: The THA-Net is a deep learning algorithm which receives an input preoperative radiograph and subsequently replaces the target hip joint with THA implants to generate a synthetic yet realistic postoperative radiograph. We trained THA-Net on 356,305 pairs of radiographs from 14,357 patients from a single institution's total joint registry and evaluated the validity (quality of surgical execution) and realism (ability to differentiate real and synthetic radiographs) of its outputs against both human-based and software-based criteria. RESULTS: The surgical validity of synthetic postoperative radiographs was significantly higher than their real counterparts (mean difference: 0.8 to 1.1 points on 10-point Likert scale, P < .001), but they were not able to be differentiated in terms of realism in blinded expert review. Synthetic images showed excellent validity and realism when analyzed with already validated deep learning models. CONCLUSION: We developed a THA next-generation templating tool that can generate synthetic radiographs graded higher on ultimate surgical execution than real radiographs from training data. Further refinement of this tool may potentiate patient-specific surgical planning and enable technologies such as robotics, navigation, and augmented reality (an online demo of THA-Net is available at: https://demo.osail.ai/tha_net).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Arthroplasty, Replacement, HipHip ProsthesisDeep LearningHumansHip JointRadiographyRetrospective Studies

Stichwörter der Autor:innen

artificial intelligencedeep learningdenoising diffusion probabilistic modelsmachine learningtemplatingtotal hip arthroplasty

Autor:innen und Institutionen

  • Department of Radiology, Mayo Clinic, Minnesota.
  • Department of Orthopedic Surgery, Mayo Clinic, Minnesota.

Zitieren

APA

Rouzrokh, P., Khosravi, B., Mickley, J. P., Erickson, B. J., Taunton, M. J., & Wyles, C. C. (2024). THA-Net: A Deep Learning Solution for Next-Generation Templating and Patient-specific Surgical Execution. The Journal of Arthroplasty. https://doi.org/10.1016/j.arth.2023.08.063

Vancouver

Rouzrokh P, Khosravi B, Mickley JP, Erickson BJ, Taunton MJ, Wyles CC. THA-Net: A Deep Learning Solution for Next-Generation Templating and Patient-specific Surgical Execution. The Journal of Arthroplasty. 2024. doi:10.1016/j.arth.2023.08.063

BibTeX
@article{Rouzrokh2024,
  author = {Rouzrokh, Pouria and Khosravi, Bardia and Mickley, John P and Erickson, Bradley J and Taunton, Michael J and Wyles, Cody C},
  title = {THA-Net: A Deep Learning Solution for Next-Generation Templating and Patient-specific Surgical Execution},
  journal = {The Journal of Arthroplasty},
  year = {2024},
  doi = {10.1016/j.arth.2023.08.063}
}
Kostenlos starten →