Scholarlink

<p>We developed and externally validated a hierarchical deep learning pipeline that automates cervical sagittal measurements, explicitly addressing C7 obscuration on lateral radiographs. The model combines a global keypoint detector with C2/C7 specialists localized via a multilayer perceptron to refine landmarks on high‑resolution patches. Trained on 5604 images and tested internally and on a challenging external cohort enriched for C7 obscuration (82%), it achieved excellent agreement with ground truth. Externally, intraclass correlation coefficients (ICCs) were 0.97 for lordosis (mean absolute error [MAE] 2.6°), &gt;0.99 for C2 slope (MAE 0.8°), and 0.93 for C7 slope (MAE 2.3°), with minimal bias and narrower limits of agreement than a single‑stage baseline. The model showed near-perfect repeatability (ICC &gt; 0.99) and higher artificial intelligence-expert agreement (ICC 0.81–0.84) for C7 slope than inter-expert reliability (ICC 0.67). In failure cases, the pipeline corrected large global model errors (e.g., 10.22°– 0.22°). This robust, coarse‑to‑fine approach advances reliable, generalizable cervical alignment assessment in real‑world conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hierarchical deep learning pipeline for robust cervical parameter measurement in radiographs with C7 obscuration

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月19日

查看全文
  • Dong-Ho Kang,
  • Se-Jun Park,
  • Jin-Sung Park,
  • Hyeonsu Park,
  • Chong-Suh Lee

摘要

We developed and externally validated a hierarchical deep learning pipeline that automates cervical sagittal measurements, explicitly addressing C7 obscuration on lateral radiographs. The model combines a global keypoint detector with C2/C7 specialists localized via a multilayer perceptron to refine landmarks on high‑resolution patches. Trained on 5604 images and tested internally and on a challenging external cohort enriched for C7 obscuration (82%), it achieved excellent agreement with ground truth. Externally, intraclass correlation coefficients (ICCs) were 0.97 for lordosis (mean absolute error [MAE] 2.6°), >0.99 for C2 slope (MAE 0.8°), and 0.93 for C7 slope (MAE 2.3°), with minimal bias and narrower limits of agreement than a single‑stage baseline. The model showed near-perfect repeatability (ICC > 0.99) and higher artificial intelligence-expert agreement (ICC 0.81–0.84) for C7 slope than inter-expert reliability (ICC 0.67). In failure cases, the pipeline corrected large global model errors (e.g., 10.22°– 0.22°). This robust, coarse‑to‑fine approach advances reliable, generalizable cervical alignment assessment in real‑world conditions.