RPLS-Net: pulmonary lobe segmentation based on 3D fully convolutional networks and multi-task learning.

Jinxin LiuChengdi WangJixiang GuoJun ShaoXiuyuan XuXiaoxin LiuHongxia LiWeimin LiZhang Yi

Published in: International journal of computer assisted radiology and surgery (2021)

In this paper, a 3D fully convolutional networks framework is proposed to segment pulmonary lobes in chest CT images accurately. Experimental results show the effectiveness of the proposed approach in segmenting the tissues as well as the borders of the lobes.

Keyphrases

pulmonary hypertension
deep learning
convolutional neural network
neural network
randomized controlled trial
computed tomography
gene expression
systematic review
image quality
contrast enhanced
dual energy
machine learning