Scoping Review of AI-Based Anatomical Landmark Identification in 3D CT/CBCT

A scoping review of 37 studies published until January 2026, analyzing automatic landmark identification techniques in three-dimensional computed tomography and cone-beam computed tomography. The review was authored by You Wu and focuses on the accuracy, efficiency, and clinical applicability of AI-based methods. It is a 47.0 KB document available under a CC-BY-4.0 license.

Use Cases

• Benchmarking AI model performance for landmark detection based on reported accuracy metrics like mean radial error.
• Identifying research gaps in automatic landmarking for soft-tissue versus hard-tissue based on the review's findings.
• Designing clinical validation studies based on the reported sample size and population limitations described in the review.
• Informing the standardization of evaluation metrics for 3D landmarking systems based on the review's conclusions.

Strengths

• Provides a structured analysis of 37 specific studies, offering a consolidated view of the field.
• Explicitly reports key statistics, such as 75.7% of included studies having fewer than 200 cases and 56.8% meeting a clinical correctness standard.
• Clearly defines its scope and methodology as a scoping review focused on AI-based methods.

Limitations

• The dataset is a 47.0 KB review document, not a primary data collection, limiting direct analysis.
• Row count and column-level documentation for any underlying data are absent.
• The review notes limited sample sizes and types in the included studies, and a lack of standardized evaluation metrics.

Provenance

Source

figshare, authored by You Wu.

Collection Method

Scoping review of studies from PubMed, Web of Science, and the Cochrane Library.

Time Range

Studies published until January 2026.

Freshness

Last updated 2026-05-29 06:07:39.