medical imaging physics
基于人工智能的影像学检测胆囊癌
Artificial intelligence for imaging-based detection of gallbladder cancerA systematic review and diagnostic test accuracy meta-analysis evaluating the performance of AI-assisted imaging models in detecting gallbladder cancer (GBC) using ultrasound, computed tomography, and radiomics. / 一项系统综述和诊断试验准确性荟萃分析，评估了人工智能辅助影像模型在利用超声、计算机断层扫描和放射组学检测胆囊癌（GBC）方面的性能。
- Knowledge type
- 实际应用
- First proposed or discovered
- Proposer
- Turkey Farm member
- Creator
- 农场主
- Last updated
- 2026-11-10 20:05:48
Sub-knowledge points
AI-assisted imaging showed promising sensitivity and moderate-to-high specificityEvidence is most consistent with AI as a triage or second-reader adjunctNot yet suitable as a stand-alone diagnostic replacement
Higher-order knowledge points
Diagnostic test accuracy (DTA)Meta-analysisReitsma bivariate random-effects modelQuality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2)Receiver operating characteristic (ROC) curve
Main parameters and performance indicators
Pooled sensitivity: 0.888 (95% CI: 0.834-0.927)Pooled specificity: 0.838 (95% CI: 0.717-0.914)Summary ROC AUC: 0.921Validation datasets: 5 (comprising 615 patients/cases)
Open problems
Greater uncertainty for specificity than sensitivityPrediction intervals for specificity were wider than sensitivityNeed for further external and prospective validationHeterogeneity in modalities, target contrasts, models, thresholds, and validation designs
Related literature
ranked by community starsArtificial intelligence for imaging-based detection of gallbladder cancer: A systematic review and diagnostic test accuracy meta-analysisOpen source
Related products and links
AI-assisted imaging modelsUltrasound-based diagnosis modelsComputed tomography-based diagnosis modelsRadiomics-based diagnosis models
Creation and modification trail
1 recordsRecord title: Artificial intelligence for imaging-based detection of gallbladder cancer.
Node update feedback
review required