Abstract:

Bronchiectasis is a common chronic respiratory disease, which seriously affects the quality of life of patients and brings heavy social and economic burden. Moreover, that diagnosis of bronchiectasis requires a certain degree of experience and professionalism on the part of the doctor in order to effectively obtain the correct result. With the development of artificial intelligence, target detection technology in the field of computer vision can be used to assist in the diagnosis of such diseases. This paper reports the research status of artificial intelligence diagnosis system for bronchiectasis, introduces the clinical diagnosis methods of bronchiectasis, and puts forward the technical route of computer aided diagnosis of this kind of disease based on it, summarizes the traditional and deep learning methods of CT image noise suppression, lung parenchyma extraction and lung lobe segmentation, aiming at the problem of lack of gold standard data set for bronchiectasis, it summarizes the problems and challenges of target detection applied to computer aided diagnosis from two aspects, and compares the characteristics and application scenarios of different algorithms in detail. Finally, the possible development trend in the future is discussed.

Key words: bronchiectasis, lung parenchyma segmentation, pulmonary lobectomy, object detection

摘要：

支气管扩张症是一种常见的慢性呼吸道疾病，严重影响患者的生活质量，带来了沉重的社会经济负担。随着人工智能的发展，可利用计算机视觉领域的目标检测技术辅助诊断这类疾病。报告了支气管扩张症人工智能诊断系统的研究现状，介绍了支气管扩张症的临床诊断方式，并基于此提出了计算机辅助诊断该类疾病的诊断技术路线，总结了CT影像噪声抑制、肺实质提取、肺叶分割的传统和深度学习方法，针对支气管扩张金标准数据集匮乏的问题，从两个方面综述了目标检测应用于计算机辅助诊断的问题及挑战，详细比较了不同算法的特点和适用场景。最后讨论了未来可能的发展趋势。

关键词: 支气管扩张, 肺实质提取, 肺叶分割, 目标检测