相关实验视频
Updated: Jan 13, 2026

Experimental Model to Evaluate Resolution of Pneumonia
Published on: February 17, 2023
人工智能模型在胸部计算机断层扫描上区分肺炎病因学方面表现优于经验丰富的临床医生:一项回顾性研究
Wenting Jin1, Ying Shao2, Jue Pan1
1Department of Infectious Diseases, Zhongshan Hospital, Fudan University, Shanghai, China.
深度学习模型使用胸部CT扫描准确地区分了十种肺炎的原因. 大视力模型 (LVM) 优于其他方法,改善了结核病等疾病的诊断.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 肺部病理学 肺部病理学
背景情况:
- 准确的肺炎诊断对于有效的患者管理至关重要.
- 胸部计算机断层扫描 (CT) 扫描对于诊断肺炎至关重要.
- 区分各种肺炎病因仍然是一个临床挑战.
研究的目的:
- 开发和验证深度学习 (DL) 模型,用于分类十种不同的肺炎病因.
- 将DL模型的性能与人类专家 (放射科医生和肺科医生) 的性能进行比较.
主要方法:
- 对1,091名肺炎患者进行了回顾性研究,证实了病因.
- 开发和验证两个DL模型:3D-DenseNet和一个新的大视觉模型 (LVM).
- 对183名非重叠患者进行外部验证;通过AUC和准确度评估性能.
主要成果:
- 与非成像模型 (LVM+) 结合的LVM与DenseNet+ (0.851),放射科医生+ (0.643) 和肺科医生+ (0.644) 相比,显示出更高的预测性能 (Top1 AUC 0.872).
- LVM+实现了更高的Top1,Top2和Top3精度 (分别为0.527,0.701,0.820).
- 这两种DL模型都在识别肺非结核菌 (PNTM),肺结核 (PTB) 和Pneumocystis jirovecii肺炎 (PJP) 中表现出显著的优势.
结论:
- 开发的DL模型为肺炎提供了一个全面的分类方法,与临床实践保持一致.
- 在临床应用方面,LVM显示出有前途,以提高肺炎诊断的准确性.
- 这项研究强调了人工智能在改善肺炎病因诊断方面的潜力.
更多相关视频
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
相关概念视频
Pneumonia III: Complications and Assessment
Pneumonia I: Introduction
Risk Factors
Various factors influence the likelihood of developing pneumonia. Age plays a crucial role, with infants, children under two, and individuals over 65 at increased risk due to their...
Pneumonia IV: Management
Bacterial Pneumonia Treatment
For bacterial pneumonia, antibiotics serve as the cornerstone of therapy. Initial treatment often begins with empirical antibiotics, tailored to the anticipated causative organism and adjusted based on culture results. Key antibiotic choices include:
Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History