基于人工智能的肺栓塞检测:一个虚假阳性减少模块的附加值在一个区域的建议网络上
Jeong Sub Lee1, Euijin Hwang2, Changgyun Jin3
1College of Medicine, Seoul National University, Seoul 03080, Republic of Korea.
Diagnostics (Basel, Switzerland)
|February 27, 2026
概括
一个新的修改面具R-CNN模型显著减少了使用CTPA扫描检测肺栓塞的错误阳性. 这种人工智能的进步提高了特异性和积极的预测价值,有助于准确的诊断.
科学领域:
- 医疗成像医学成像
- 放射学中的人工智能
- 肺栓塞检测检测 肺栓塞检测
背景情况:
- 高错误阳性率挑战通过CTPA自动肺栓塞 (PE) 检测.
- 评估一个被整合到区域提案网络 (RPN) 中的虚假阳性减少 (FPR) 模块.
研究的目的:
- 评估PFR模块在PE检测中的附加值.
- 将仅RPN的诊断性能与仅RPN的诊断性能进行比较. 修改过的面具R-CNN与FPR.
主要方法:
- 对303个CTPA扫描 (163个PE阳性,140个PE阴性) 的回顾性分析.
- 从RSNA PE挑战数据集中对100个CTPA扫描进行外部验证.
- 单阶段的RPN-only模型与两个阶段的修改面具R-CNN与FPR相比.
主要成果:
- 修改过的R-CNN口罩显著提高了特异性,将假阳性率降低了31%.
- 阳性预测值增加了10.5%,敏感度略有降低.
- 改善了临床显著栓塞 (≥1000 mm3) 的患者水平特异性.
结论:
- 修改过的面具R-CNN有效地减少了基于CTPA的PE检测中的假阳性.
- 该模型保持高灵敏度,同时提高诊断准确度.
- 这种方法比标准RPN模型提供了有价值的改进.
相关概念视频
01:29Pulmonary Embolism I: Introduction
1.0K
Pulmonary embolism (PE) occurs when a thrombus, fat or air embolus, amniotic fluid, or tumor tissue blocks one or more pulmonary arteries. These blockages originate in the venous system or the right side of the heart.EtiologyPE primarily arises from deep vein thrombosis (DVT) and other hypercoagulable states, such as inherited thrombophilias. Additional etiological factors include venous stasis, commonly seen in obesity, and endothelial injury from surgery and trauma. Less common causes include...
1.0K
01:29Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
553
Diagnosing Pulmonary EmbolismDiagnosing pulmonary embolism (PE) involves clinical assessment and advanced imaging tests. The preferred diagnostic tool is the spiral (helical) CT scan or CT angiography (CTA), which uses intravenous contrast media to visualize the pulmonary vasculature and identify emboli.A ventilation-perfusion (V/Q) scan is an alternative for patients unable to receive contrast media. This scan includes both perfusion and ventilation scanning. Perfusion scanning involves...
553