TY - JOUR
T1 - CT Lung Nodule Segmentation
T2 - A Comparative Study of Data Preprocessing and Deep Learning Models
AU - Chen, Weihao
AU - Wang, Yu
AU - Tian, Dingcheng
AU - Yao, Yudong
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2023
Y1 - 2023
N2 - The number of deaths from lung cancer reached 1.8 million in 2020, ranking first among all cancers. Early diagnosis has been found to improve the survival rate of lung cancer patients after treatment in clinical care. Computed tomography (CT) is a technique commonly used in the early detection of lung cancer to determine the benignity or malignancy of lung nodules. Manual analysis of CT results is less efficient and its accuracy is affected by physicians' experience levels. Segmenting lung nodules in a computer-aided diagnosis (CAD) system can effectively improve the efficiency and accuracy of the diagnosis. In this paper, we evaluate several deep learning segmentation models (including UNet, SegNet, GCN, FCN, DeepLabV3+, PspNet TransUNet, SwinUNet) and examine the effects of different preprocessing methods on the models to explore the best preprocessing and training strategies for lung nodule segmentation. Specifically, we investigate the effects of two different data preprocessing methods (adding a lung mask and croping the region of interest) on the segmentation results, where better segmentation results are achieved by including the nodal data of the region of interest without the lung mask. Through a comprehensive comparison, TransUNet achieves the best segmentation accuracy, with DICE indices of 0.887, 0.871, 0.75, and 0.744 tested on four datasets, respectively.
AB - The number of deaths from lung cancer reached 1.8 million in 2020, ranking first among all cancers. Early diagnosis has been found to improve the survival rate of lung cancer patients after treatment in clinical care. Computed tomography (CT) is a technique commonly used in the early detection of lung cancer to determine the benignity or malignancy of lung nodules. Manual analysis of CT results is less efficient and its accuracy is affected by physicians' experience levels. Segmenting lung nodules in a computer-aided diagnosis (CAD) system can effectively improve the efficiency and accuracy of the diagnosis. In this paper, we evaluate several deep learning segmentation models (including UNet, SegNet, GCN, FCN, DeepLabV3+, PspNet TransUNet, SwinUNet) and examine the effects of different preprocessing methods on the models to explore the best preprocessing and training strategies for lung nodule segmentation. Specifically, we investigate the effects of two different data preprocessing methods (adding a lung mask and croping the region of interest) on the segmentation results, where better segmentation results are achieved by including the nodal data of the region of interest without the lung mask. Through a comprehensive comparison, TransUNet achieves the best segmentation accuracy, with DICE indices of 0.887, 0.871, 0.75, and 0.744 tested on four datasets, respectively.
KW - Deep learning
KW - data preprocessing
KW - image segmentation
KW - lung cancer
UR - http://www.scopus.com/inward/record.url?scp=85153384014&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153384014&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2023.3265170
DO - 10.1109/ACCESS.2023.3265170
M3 - Article
AN - SCOPUS:85153384014
VL - 11
SP - 34925
EP - 34931
JO - IEEE Access
JF - IEEE Access
ER -