Performance Metrics for Deep Learning Models in Aortic Dissection Analysis

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

Use Cases

• Benchmarking segmentation model performance based on reported Dice coefficients for false lumen, true lumen, and entire aorta
• Evaluating diagnostic model accuracy based on pooled sensitivity and specificity metrics for CT, ECG, and CTA modalities
• Comparing AI diagnostic performance to clinicians using the reported pooled sensitivity and specificity figures

Strengths

• Includes results from 48 studies, providing a broad evidence base
• Reports specific quantitative metrics like Dice coefficients (e.g., 90.8% ± 3.4% for true lumen) and confidence intervals for sensitivity/specificity
• Follows a systematic review methodology with a registered protocol (CRD42024619403)

Limitations

• The dataset is a 16.6 KB DOCX file containing summary tables, not the raw underlying data
• Column-level documentation for the performance metrics table is absent; field semantics must be inferred from the text
• Row count for the underlying data is unknown, which may limit suitability assessment

Provenance

Source

figshare

Collection Method

Systematic review and meta-analysis of studies from 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 04:21:49