Machine Learning Classifier Results for Maxillary Sinus Analysis on 127 Instances

127 instances of maxillary sinus volumetric data were used to evaluate machine learning classifiers. The results, provided by Çağatay Bölgen, include performance metrics with 95% confidence intervals derived from five-fold stratified cross-validation. The dataset was last updated on March 18, 2026.

Use Cases

• Compare classifier performance based on metrics with confidence intervals.
• Benchmark feature selection methods for small-sample medical imaging datasets.
• Analyze the relationship between maxillary sinus volume and temporomandibular disorders.
• Validate volumetric assessment techniques using 3D Slicer software outputs.

Strengths

• Results are based on 127 specific instances.
• Performance metrics include lower bound, mean, and upper bound values at a 95% confidence level.
• Evaluation methodology uses five-fold stratified cross-validation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

Çağatay Bölgen via figshare

Collection Method

Results obtained from classifiers with feature selection, likely from analysis of facial CBCT images.

Freshness

Last updated 2026-03-18 17:32:26; freshness should be verified.