使用深度学习对上呼吸道进行细分 - nnUNet
Silvia Gianoni-Capenakas1, Alejandro Matos2, Gauthier Dot3
1Registered Orthodontist. Clinical Assistant Professor, Mike Petric School of Dentistry, University of Alberta. Kaye Edmonton Clinic. 11400 University Ave, 8th floor. Edmonton, AB, Canada. T6G 1Z1.
Journal of dentistry
|January 16, 2026
概括
深度学习模型自动化了CBCT和CT扫描的上呼吸道细分,实现了高精度和减少分析时间. 这种高效的工具有助于跨不同患者群体的临床决策和研究.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 放射学 放射学是一门学科.
背景情况:
- 上呼吸道的手动细分是耗时的,容易引起观察者之间的变化.
- 对上呼吸道进行准确的3D分析对于诊断和治疗计划至关重要.
研究的目的:
- 开发和评估用于自动化3D上呼吸道细分的深度学习框架.
- 评估模型在多源CBCT和CT数据集上的性能.
主要方法:
- 使用了来自不同人群的220个多源3D图像 (CBCT,CT) 的数据集.
- 使用nnUNet采用多源培训方法.
- 在CBCT扫描上进行了一个中心外验证.
主要成果:
- 多源深度学习模型实现了0.962.9的高平均子得分.
- 与手动细分相比,nnUNet-155模型显示了3.31%的绝对体积差异.
- 预测时间减少到每卷5分钟.
结论:
- 开发的深度学习模型为自动上呼吸道细分提供了强大,高效和可通用的解决方案.
- 该工具提供精确,一致和节省时间的3D分析,支持临床决策和研究.
- 该模型克服了手动细分的局限性,提高了跨不同患者人口统计和成像模式的可靠性.
相关概念视频
Anatomy of Respiratory System I: Upper Respiratory Tract
4.8K
The upper respiratory tract plays a vital role in the respiratory system, comprising several structures that facilitate air intake and prepare air for the lungs. It also serves as the first line of defense against pathogens and particles. This tract includes the nose and nasal cavity, the oral cavity, the paranasal sinuses, and the pharynx, each with specific functions and features.
Nose and nasal cavity
The nose and nasal cavity represent the main external openings of the respiratory tract....
Nose and nasal cavity
The nose and nasal cavity represent the main external openings of the respiratory tract....
4.8K
Suctioning the Nasopharyngeal Airway
3.0K
Nasopharyngeal suctioning is a procedure to remove secretions from the upper part of the respiratory tract that the patient cannot clear independently. It helps maintain airway patency and prevents complications such as aspiration pneumonia.
Equipment Required
Equipment Required
3.0K


