Deep Learning Method for Precise Landmark Identification and Structural Assessment of Whole-Spine Radiographs

Sung Hyun Noh, Gaeun Lee, Hyun Jin Bae, Ju Yeon Han, Su Jeong Son, Deok Kim, Jeong Yeon Park, Seung Kyeong Choi, Pyung Goo Cho, Sang Hyun Kim, Woon Tak Yuh, Su Hun Lee, Bumsoo Park, Kwang Ryeol Kim, Kyoung Tae Kim, Yoon Ha

Research output: Contribution to journalArticlepeer-review

Abstract

This study measured parameters automatically by marking the point for measuring each parameter on whole-spine radiographs. Between January 2020 and December 2021, 1017 sequential lateral whole-spine radiographs were retrospectively obtained. Of these, 819 and 198 were used for training and testing the performance of the landmark detection model, respectively. To objectively evaluate the program’s performance, 690 whole-spine radiographs from four other institutions were used for external validation. The combined dataset comprised radiographs from 857 female and 850 male patients (average age 42.2 ± 27.3 years; range 20–85 years). The landmark localizer showed the highest accuracy in identifying cervical landmarks (median error 1.5–2.4 mm), followed by lumbosacral landmarks (median error 2.1–3.0 mm). However, thoracic landmarks displayed larger localization errors (median 2.4–4.3 mm), indicating slightly reduced precision compared with the cervical and lumbosacral regions. The agreement between the deep learning model and two experts was good to excellent, with intraclass correlation coefficient values >0.88. The deep learning model also performed well on the external validation set. There were no statistical differences between datasets in all parameters, suggesting that the performance of the artificial intelligence model created was excellent. The proposed automatic alignment analysis system identified anatomical landmarks and positions of the spine with high precision and generated various radiograph imaging parameters that had a good correlation with manual measurements.

Original languageEnglish
Article number481
JournalBioengineering
Volume11
Issue number5
DOIs
Publication statusPublished - 2024 May

Bibliographical note

Publisher Copyright:
© 2024 by the authors.

All Science Journal Classification (ASJC) codes

  • Bioengineering

Fingerprint

Dive into the research topics of 'Deep Learning Method for Precise Landmark Identification and Structural Assessment of Whole-Spine Radiographs'. Together they form a unique fingerprint.

Cite this