Meta-Analysis of Deep Learning Models for Aortic Dissection Segmentation and Diagnosis

48 studies on deep learning models for aortic dissection segmentation or diagnostic tasks were included in this systematic review. The supplementary file, authored by Yichen Zhao and last updated in April 2026, contains the meta-analysis results. It reports performance metrics like a mean Dice coefficient of 89.2% for false lumen segmentation and pooled sensitivity of 0.94 for CT-based diagnosis.

Use Cases

• Benchmarking new segmentation models against reported performance metrics like the Dice coefficient for false lumen segmentation.
• Evaluating the diagnostic accuracy of AI models for aortic detection based on reported pooled sensitivity and specificity values.
• Informing the design of clinical validation studies by referencing the comparison data between deep learning models and clinician performance.

Strengths

• Includes results from 48 studies, providing a broad evidence base.
• Reports specific, quantitative performance metrics like Dice coefficients and confidence intervals for sensitivity/specificity.
• Compares model performance against clinicians, offering a clinical benchmark.

Limitations

• The 2.9 MB file is a DOCX document; the underlying raw data or model code is not directly accessible.
• Row count and column-level documentation for any potential tabular data within the file are unknown.
• Description metadata is limited; actual data quality and structure require manual inspection after download.

Provenance

Source

Systematic review and meta-analysis conducted by author Yichen Zhao, sourced from figshare.

Collection Method

Comprehensive search across Cochrane Library, PubMed, Embase, and Web of Science up to November 3, 2024.

Time Range

Studies included up to November 3, 2024.

Freshness

Last updated 2026-04-14 04:21:47; freshness should be verified.