What question did this study set out to answer?

The study aims to evaluate whether deep learning algorithms can improve the diagnostic accuracy for detecting osteoporotic vertebral fractures compared to human raters.

February 26, 2026Open Access

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

Puntos clave

The study aims to evaluate whether deep learning algorithms can improve the diagnostic accuracy for detecting osteoporotic vertebral fractures compared to human raters.
Retrospective analysis of thoracic and lumbar vertebrae from patients using CT scans.
Evaluation of eight human raters with varying expertise alongside four deep learning models.
Grading of vertebral fractures using the semiquantitative Genant scale.
Assessment of diagnostic performance through interrater agreement and classification metrics.
Among 3548 analyzed vertebrae, 190 (5.4%) were fractured, with 139 (3.9%) exhibiting clinically significant fractures.
Deep learning models demonstrated comparable accuracy to residents for detecting moderate/severe fractures.
Specific deep learning software outperformed experts in overall diagnostic accuracy.
Students showed the lowest accuracy across all assessments.

Resumen

Abstract 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

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo