A Pulmonary Vascular Extraction Algorithm from Chest CT/CTA Images

Segmentation of pulmonary vessels in CT/CTA images can help physicians better determine the patient’s condition and treatment. However, due to the complexity of CT images, existing methods have limitations in the segmentation of pulmonary vessels. In this paper, a method based on the separation of p...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Shihui Xu, Ziming Zhang, Qinghua Zhou, Wei Shao, Wenjun Tan
Formato: article
Lenguaje:EN
Publicado: Hindawi Limited 2021
Materias:
Acceso en línea:https://doaj.org/article/2a634cb7e21146949bdc926e324c6ad0
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:Segmentation of pulmonary vessels in CT/CTA images can help physicians better determine the patient’s condition and treatment. However, due to the complexity of CT images, existing methods have limitations in the segmentation of pulmonary vessels. In this paper, a method based on the separation of pulmonary vessels in CT/CTA images is investigated. The method is divided into two steps: in the first step, the lung parenchyma is extracted using the Unet++ algorithm, which can effectively reduce the oversegmentation rate; in the second step, the pulmonary vessels in the lung parenchyma are extracted using nnUnet. According to the obtained lung parenchyma segmentation results, the “AND” operation is performed on the original image and the lung parenchyma segmentation results, and only the blood vessels within the lung parenchyma are segmented, which reduces the interference of external tissues and improves the segmentation accuracy. The experimental data source used CT/CTA images acquired from the partner hospital. After the experiments were performed on a total of 67 sets of images, the accuracy of CT and CTA images reached 85.1% and 87.7%, respectively. The comparison of whether to segment the lung parenchyma and with other conventional methods was also performed, and the experimental results showed that the algorithm in this paper has high accuracy.