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

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 dataset, authored by Yichen Zhao and last updated in April 2026, aggregates findings from studies identified up to November 2024.

Use Cases

• Benchmarking segmentation model performance based on reported Dice coefficients for false lumen, true lumen, and entire aorta.
• Comparing diagnostic accuracy of deep learning models versus clinicians based on pooled sensitivity and specificity metrics.
• Evaluating the performance of different imaging modalities (CT, CTA, ECG) for aortic dissection diagnosis using the reported pooled metrics.
• Informing the development of clinical assistive tools by analyzing the evidence base for model accuracy.

Strengths

• Aggregates results from 48 studies, providing a consolidated evidence base.
• Reports specific performance metrics, including Dice coefficients and confidence intervals for sensitivity/specificity.
• Includes a comparison of model performance against clinicians.
• Follows a systematic review methodology with a registered protocol (CRD42024619403).

Limitations

• The underlying data is a 22.3 KB DOCX file summarizing results; the raw study data is not included.
• Column-level documentation for the summary table is absent; field semantics must be inferred from the description.
• The dataset's scope is limited to the aggregated statistical results of the meta-analysis.

Provenance

Source

Systematic review and meta-analysis conducted by author Yichen Zhao, published on figshare.

Collection Method

Comprehensive search across Cochrane Library, PubMed, Embase, and Web of Science; studies assessed with QUADAS-2.

Time Range

Studies included up to November 3, 2024.

Freshness

Last updated 2026-04-14 04:21:48; includes studies up to November 2024.