Scholarlink

Objectives <p>Vertebral fractures are severe complications of osteoporosis but are frequently missed on computed tomography (CT). Differentiating true fractures from non-osteoporotic vertebral height loss remains challenging; deep learning (DL) models may improve detection and grading.</p> Materials and methods <p>In this retrospective study, we evaluated eight human raters with different expertise (three students, three residents, and two attendings), four DL models, and one DL-based commercial software using the public Vertebral Segmentation (VerSe) 19 &amp; 20 datasets. Vertebral fractures were graded using the semiquantitative Genant scale (0–3). Diagnostic performance was evaluated using interrater agreement and classification metrics, with significance tested via generalized linear mixed models across patient and vertebral levels for the thoracolumbar spine and its regional subsets. Consensus readings by a senior neuroradiologist and an experienced resident, informed by clinical data, served as the reference standard.</p> Results <p>3548 thoracic and lumbar vertebrae from 331 patients were analyzed. 190 (5.4%) of vertebrae were fractured, and 139 (3.9%) had “clinically most relevant” moderate or severe fractures (Genant 2 or 3). DL models showed comparable accuracy as residents in detecting moderate/severe fractures (0.988 vs. 0.991, <i>p</i> &gt; 0.05)&#xa0;on vetebral level. SpineQ v1.1 consistently showed comparable Area Under the Curve (AUROC) and higher diagnostic accuracy compared to experts in detecting any fracture and moderate/severe fractures across vertebral, regional, and patient-level analyses. Students consistently exhibited the lowest AUROC and diagnostic accuracy across all levels and comparisons.</p> Conclusion <p>When specifically trained to detect a distinct condition like vertebral fractures, advanced algorithms can show comparable performance as experts.</p> Key Points <p><Emphasis Type="BoldItalic">Question</Emphasis> <i>Can dedicated deep learning-based algorithms improve diagnostic performance for accurate detection and grading of osteoporotic vertebral fractures on CT scans?</i></p> <p><Emphasis Type="BoldItalic">Findings</Emphasis> <i>Deep learning models specifically trained for vertebral fracture detection and grading can reach comparable performance as experts for the identification and grading of osteoporotic fractures.</i></p> <p><Emphasis Type="BoldItalic">Clinical relevance</Emphasis> <i>Specifically trained deep learning models represent a valuable advancement for improving the identification and grading of osteoporotic fractures in clinical practice, bringing these tools a significant step closer to routine clinical implementation.</i></p> Graphical Abstract <p></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

Diagnostic accuracy of deep learning vs. human raters for detecting osteoporotic vertebral compression fractures in routine CT scans

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月24日

查看全文
  • Evamaria O. Riedel,
  • David Schinz,
  • Matthias Keicher,
  • Sebastian Rühling,
  • Malek El Husseini,
  • Chantal Pellegrini,
  • Thomas Baum,
  • Michael Dieckmeyer,
  • Luca Malagutti,
  • Isabel Seeger,
  • Anna S. Walburga,
  • Benedikt Wiestler,
  • Nico Sollmann,
  • Maximilian T. Löffler,
  • Arthur Wagner,
  • Jan S. Kirschke

摘要

Objectives

Vertebral fractures are severe complications of osteoporosis but are frequently missed on computed tomography (CT). Differentiating true fractures from non-osteoporotic vertebral height loss remains challenging; deep learning (DL) models may improve detection and grading.

Materials and methods

In this retrospective study, we evaluated eight human raters with different expertise (three students, three residents, and two attendings), four DL models, and one DL-based commercial software using the public Vertebral Segmentation (VerSe) 19 & 20 datasets. Vertebral fractures were graded using the semiquantitative Genant scale (0–3). Diagnostic performance was evaluated using interrater agreement and classification metrics, with significance tested via generalized linear mixed models across patient and vertebral levels for the thoracolumbar spine and its regional subsets. Consensus readings by a senior neuroradiologist and an experienced resident, informed by clinical data, served as the reference standard.

Results

3548 thoracic and lumbar vertebrae from 331 patients were analyzed. 190 (5.4%) of vertebrae were fractured, and 139 (3.9%) had “clinically most relevant” moderate or severe fractures (Genant 2 or 3). DL models showed comparable accuracy as residents in detecting moderate/severe fractures (0.988 vs. 0.991, p > 0.05) on vetebral level. SpineQ v1.1 consistently showed comparable Area Under the Curve (AUROC) and higher diagnostic accuracy compared to experts in detecting any fracture and moderate/severe fractures across vertebral, regional, and patient-level analyses. Students consistently exhibited the lowest AUROC and diagnostic accuracy across all levels and comparisons.

Conclusion

When specifically trained to detect a distinct condition like vertebral fractures, advanced algorithms can show comparable performance as experts.

Key Points

Question Can dedicated deep learning-based algorithms improve diagnostic performance for accurate detection and grading of osteoporotic vertebral fractures on CT scans?

Findings Deep learning models specifically trained for vertebral fracture detection and grading can reach comparable performance as experts for the identification and grading of osteoporotic fractures.

Clinical relevance Specifically trained deep learning models represent a valuable advancement for improving the identification and grading of osteoporotic fractures in clinical practice, bringing these tools a significant step closer to routine clinical implementation.

Graphical Abstract