Segmentation of lung tissue in computed tomography (CT) images is a precursor to most pulmonary image analysis applications. Semantic segmentation methods using deep learning have exhibited top-tier performance in recent years, however designing accurate and robust segmentation models for lung tissue is challenging due to the variations in shape, size, and orientation. Additionally, medical image artifacts and noise can affect lung tissue segmentation and degrade the accuracy of downstream analysis. The practicality of current deep learning methods for lung tissue segmentation is limited as they require significant computational resources and may not be easily deployable in clinical settings. This paper presents a fully automatic method that identifies the lungs in three-dimensional (3D) pulmonary CT images using deep networks and transfer learning. We introduce (1) a novel 2.5-dimensional image representation from consecutive CT slices that succinctly represents volumetric information and (2) a U-Net architecture equipped with pre-trained InceptionV3 blocks to segment 3D CT scans while maintaining the number of learnable parameters as low as possible. Our method was quantitatively assessed using one public dataset, LUNA16, for training and testing and two public datasets, namely, VESSEL12 and CRPF, only for testing. Due to the low number of learnable parameters, our method achieved high generalizability to the unseen VESSEL12 and CRPF datasets while obtaining superior performance over Luna16 compared to existing methods (Dice coefficients of 99.7, 99.1, and 98.8 over LUNA16, VESSEL12, and CRPF datasets, respectively). We made our method publicly accessible via a graphical user interface at medvispy.ee.kntu.ac.ir.
翻译:在计算机断层成像(CT)图像中对肺组织进行分割是大多数肺部图像分析应用程序的先决条件。近年来,使用深度学习的语义分割方法表现出一流的性能,然而为肺组织设计准确和强健的分割模型是具有挑战性的,因为形状,大小和方向变化很大。此外,医学图像中的伪影和噪声可能影响肺组织分割,并降低下游分析的准确性。目前用于肺组织分割的深度学习方法的实用性受到限制,因为它们需要大量的计算资源,并且在临床环境中可能不容易部署。本文提出了一种完全自动化的方法,使用深度网络和迁移学习在三维肺部 CT 图像中识别肺部。我们引入了一种新颖的 2.5D 图像表示方法,该方法从连续 CT 切片中简明地表示容积信息,并且使用具有预先训练的 InceptionV3 块的 U-Net 架构来在维持尽可能少的可学习参数的同时分割 3D CT 扫描。我们使用一个公共数据集 LUNA16 进行量化评估的方法用于训练和测试,而使用两个公共数据集 VESSEL12 和 CRPF 仅用于测试。由于可学习参数的数量很少,我们的方法在未见过的 VESSEL12 和 CRPF 数据集上达到了高通用性,而相对于现有方法(Dice 系数在 LUNA16,VESSEL12 和 CRPF 数据集上分别为 99.7、99.1 和 98.8),在 Luna16 上取得了卓越的性能。我们通过 medvispy.ee.kntu.ac.ir 提供了一个可公开访问的图形用户界面来使用我们的方法。