在使用数据驱动计算框架的腹部计算机断层扫描上检测和描述下静脉膜过器.
Sema Candemir1,2, Robert Moranville3, Kelvin A Wong3,4
1Department of Radiology, The Ohio State University Wexner Medical Center, Columbus, OH, 43210, USA. candemirsema@gmail.com.
本研究介绍了两种AI算法,用于在CT扫描中检测和分类下静脉卡瓦 (IVC) 过器. 这些工具旨在改善患者管理,并减少与IVC过器相关的并发症.
科学领域:
- 放射学和医学成像学 医学成像学
- 医疗保健中的人工智能
- 计算病理学计算病理学
背景情况:
- 下静脉 (IVC) 过器对于预防肺栓塞至关重要,但如果不适当管理,可能导致并发症.
- 在腹部计算机断层扫描 (CT) 上精确检测和描述IVC过器对于临床决策至关重要.
- 现有的IVC过器评估方法可能耗时且容易出现人为错误.
研究的目的:
- 开发和评估数据驱动的算法,用于在腹部CT扫描上自动检测和表征IVC过器.
- 帮助医疗保健提供者管理IVC过器的放置和移除,从而减少相关的并发症.
- 建立一个计算框架,用于识别保留IVC过器的患者,以进行个性化治疗决策.
主要方法:
- 开发了两个算法:2D + 转移学习 (2D + TL) 模型和3D + 循环卷积神经网络 (3D + RCNN) 模型.
- 使用Tensorflow Keras API在439名患者的2048个腹部CT研究数据集上训练计算模型.
- 使用微调监督培训策略,对过器位置和类型进行参考注释.
主要成果:
- 与2D + TL模型相比,3D + RCNN模型在波器检测方面获得了更高的灵敏度 (0.923) 和精度 (0.853),而2D + TL模型则获得了更高的灵敏度 (0.911灵敏度,0.804精度).
- 这两种模型都在预测IVC过器位置方面表现出很高的信心 (2D + TL的0.993,3D + RCNN的0.996).
- 过器类型预测组件实现了高性能,3D + RCNN模型显示0.940灵敏度,0.927特异性和0.975AUC.
结论:
- 开发的AI框架显示出在从腹部CT扫描中准确检测和描述IVC过器方面显著的前景.
- 这些算法可以作为医疗保健提供者的宝贵工具,帮助及时和适当地管理IVC过器.
- 这项研究代表了自动化IVC过器分析的新贡献,为改善患者治疗结果和减少医疗并发症铺平了道路.
更多相关视频
06:50Troubleshooting FoCUS Image Acquisition: Patient Positioning, Transducer Manipulation, and Image Optimization
Published on: March 3, 2023
06:02Anatomical Reconstructions of the Human Cardiac Venous System using Contrast-computed Tomography of Perfusion-fixed Specimens
Published on: April 18, 2013
相关概念视频
Computed Tomography
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
Venous Thrombosis II: Clinical Manifestations and Diagnostic Studies
Imaging Studies for Cardiovascular System V: CT
Imaging Studies III: Computed Tomography
Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
