Abstract
In computer-aided diagnosis systems for lung cancer, segmentation of lung nodules is important for analyzing image features of lung nodules on computed tomography (CT) images and distinguishing malignant nodules from benign ones. However, it is difficult to accurately and robustly segment lung nodules attached to the chest wall or with ground-glass opacities using conventional image processing methods. Therefore, this study aimed to develop a method for robust and accurate three-dimensional (3D) segmentation of lung nodule regions using deep learning. In this study, a nested 3D fully connected convolutional network with residual unit structures was proposed, and designed a new loss function. Compared with annotated images obtained under the guidance of a radiologist, the Dice similarity coefficient (DS) and intersection over union (IoU) were 0.845 ± 0.008 and 0.738 ± 0.011, respectively, for 332 lung nodules (lung adenocarcinoma) obtained from 332 patients. On the other hand, for 3D U-Net and 3D SegNet, the DS was 0.822 ± 0.009 and 0.786 ± 0.011, respectively, and the IoU was 0.711 ± 0.011 and 0.660 ± 0.012, respectively. These results indicate that the proposed method is significantly superior to well-known deep learning models. Moreover, we compared the results obtained from the proposed method with those obtained from conventional image processing methods, watersheds, and graph cuts. The DS and IoU results for the watershed method were 0.628 ± 0.027 and 0.494 ± 0.025, respectively, and those for the graph cut method were 0.566 ± 0.025 and 0.414 ± 0.021, respectively. These results indicate that the proposed method is significantly superior to conventional image processing methods. The proposed method may be useful for accurate and robust segmentation of lung nodules to assist radiologists in the diagnosis of lung nodules such as lung adenocarcinoma on CT images.
Highlights
Lung cancer is considered one of the most serious and morbid cancers as it is the leading cause of cancer-related deaths and the most commonly detected cancer in men (Sung et al, 2021)
According to the National Lung Screening Trial, the mortality rate owing to lung cancer among participants between the ages of 55 and 74 years with a minimum of 30 pack-years of smoking and no more than 15 years since quitting, was reduced by 20% when using computed tomography (CT) compared with the rate when using non-CT methods (The National Lung Screening Trial Research Team, 2011)
The proposed method was significantly better than 3D U-Net and 3D SegNet
Summary
Lung cancer is considered one of the most serious and morbid cancers as it is the leading cause of cancer-related deaths and the most commonly detected cancer in men (Sung et al, 2021). According to the American Cancer Society, the 5-year survival rate for patients with lung cancer is 19% (Siegel et al, 2019). If lung cancer is detected in early-stage lung nodules, the survival rate improves from 10–15% to 60–80% (Diederich et al, 2002). Detection of lung nodules is of high importance for reducing mortality rates of patients with lung cancer, because the cure rate is very low once clinical symptoms of lung cancer appear (Wu et al, 2020). According to the National Lung Screening Trial, the mortality rate owing to lung cancer among participants between the ages of 55 and 74 years with a minimum of 30 pack-years of smoking and no more than 15 years since quitting, was reduced by 20% when using CT compared with the rate when using non-CT methods (The National Lung Screening Trial Research Team, 2011). A radiologist’s diagnosis still relies on experience and subjective evaluation
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
