Shanghai Jiao Tong University, Shanghai, China; Shanghai United Imaging Intelligence Co. Ltd, Shanghai, China.
Hunan University, Changsha, Hunan, China; Shanghai United Imaging Intelligence Co. Ltd, Shanghai, China.
Comput Med Imaging Graph. 2021 Apr;89:101899. doi: 10.1016/j.compmedimag.2021.101899. Epub 2021 Mar 11.
Computed tomography (CT) screening is essential for early lung cancer detection. With the development of artificial intelligence techniques, it is particularly desirable to explore the ability of current state-of-the-art methods and to analyze nodule features in terms of a large population. In this paper, we present an artificial-intelligence lung image analysis system (ALIAS) for nodule detection and segmentation. And after segmenting the nodules, the locations, sizes, as well as imaging features are computed at the population level for studying the differences between benign and malignant nodules. The results provide better understanding of the underlying imaging features and their ability for early lung cancer diagnosis.
计算机断层扫描（CT）筛查对于早期肺癌的检测至关重要。随着人工智能技术的发展，探索当前最先进方法的能力，并根据大量人群分析结节特征，是非常令人期望的。在本文中，我们提出了一个用于结节检测和分割的人工智能肺部图像分析系统（ALIAS）。结节分割后，在人群水平上计算结节的位置、大小以及影像学特征，以研究良恶性结节之间的差异。研究结果提供了对潜在影像学特征及其早期肺癌诊断能力的更好理解。
