相关实验视频

Updated: Jan 12, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

在接受治疗的RR-TB/MDR-TB患者的诊断辅助方法基于CNN-LSTM

Jie Li¹, Wenqing Wu², Zhixiong Fang³

¹Department of Tuberculosis, Jiangxi Chest Hospital, The Third Affiliated Hospital of Nanchang Medical College, Nanchang, 330006, People's Republic of China.

Scientific reports

|October 31, 2025

概括

结合卷积神经网络-长期短期记忆 (CNN-LSTM) 的新型深度学习模型准确地预测了使用胸部CT扫描和免疫指标对抗利法辛耐药结核病/多药耐药结核病 (RR-TB/MDR-TB) 患者的治疗结果.

科学领域:

人工智能在医学中的应用
医学成像分析医学成像分析
结核病研究结核病研究

背景情况:

深度学习模型越来越多地应用于疾病诊断和预后.
胸部计算机断层扫描 (CT) 扫描对于管理抗利芬辛结核病/抗多药结核病 (RR-TB/MDR-TB) 是至关重要的.
预测治疗结果有助于及时对RR-TB/MDR-TB进行治疗调整.

研究的目的:

开发和评估CNN-LSTM模型,用于预测RR-TB/MDR-TB患者的治疗结果.
整合胸部CT图像特征与顺序免疫监测数据进行增强的预测.
为此预测任务比较不同CNN骨干架构的性能.

主要方法:

设计了一个CNN-LSTM模型,集成CNN用于图像特征提取和LSTM用于顺序数据分析.
该模型利用胸部CT图像和免疫指标 (T细胞子集,CD161阳性细胞).
使用重量初始化转移学习和三个骨干架构 (DenseNet201+ABC,ResNet-50+ABC,CheXNet+ABC) 并进行了比较.

主要成果:

用DenseNet201+ABC作为骨干的CNN-LSTM模型证明了治疗指标的最高预测准确性.
该模型有效地整合了成像和免疫学数据,以预测结果.
实验结果证实了该模型在预测后续治疗指标方面的可行性和有效性.

结论:

拟议的CNN-LSTM模型显示了预测RR-TB/MDR-TB患者治疗结果的巨大潜力.
这种方法可以帮助临床医生精确地定制治疗计划,以提高治疗疗效.
这项研究强调了将深度学习与医学成像和临床数据相结合在管理复杂传染病方面的价值.

关键词:

美国有线电视新闻 (CNN-LSTM)计算机辅助诊断计算机辅助诊断深度学习是一种深度学习.在MDR-TB中,使用的是MDR.在RR-TB/MDR-TB中使用RR-TB.

更多相关视频

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Published on: April 25, 2014

Matrix-based DNA Extraction for Targeted Next-Generation Sequencing on Decontaminated Sputum Samples

Matrix-based DNA Extraction for Targeted Next-Generation Sequencing on Decontaminated Sputum Samples

Published on: June 6, 2025

相关概念视频

Pulmonary Tuberculosis IV

Pulmonary Tuberculosis IV

Tuberculosis, more commonly referred to as TB, is an infectious disease stemming from Mycobacterium tuberculosis. While it primarily impacts the lungs, TB can also affect other body areas. Given its severity and global impact, timely and accurate diagnosis is crucial for controlling its spread and improving patient outcomes.
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...

Pulmonary Tuberculosis V

Pulmonary Tuberculosis V

Medical management of tuberculosis (TB) patients involves a comprehensive approach that includes diagnosis, treatment, and monitoring. The specific strategies can vary depending on the type of tuberculosis (latent or active), the patient's overall health status, and other considerations.
Latent tuberculosis infection occurs when TB bacteria are present in a person's body, but are not causing illness or symptoms. It is not contagious, and preventive treatment is crucial to avoid the...