Purpose: Pulmonary nodules are a potential manifestation of lung cancer. In computer-aided diagnosis (CAD) of lung cancer, it is of great significance to extract the complete boundary of the pulmonary nodules in the computed tomography (CT) scans accurately. It can provide doctors with important information such as tumor size and density, which assist doctors in subsequent diagnosis and treatment. In addition to this, in the molecular subtype and radiomics of lung cancer, segmentation of lung nodules also plays a pivotal role. Existing methods are difficult to use only one model to simultaneously treat the boundaries of multiple types of lung nodules in CT images. Method: In order to solve the problem, this paper proposed a three-dimensional (3D)-UNET network model optimized by a 3D conditional random field (3D-CRF) to segment pulmonary nodules. On the basis of 3D-UNET, the 3D-CRF is used to optimize the sample output of the training set, so as to update the network weights in training process, reduce the model training time, and reduce the loss rate of the model. We selected 936 sets of pulmonary nodule data for the lung image database consortium and image database resource initiative (LIDC-IDRI) 1 database to train and test the model. What's more, we used clinical data from partner hospitals for additional validation. Results and conclusions: The results show that our method is accurate and effective. Particularly, it shows more significance for the optimization of the segmentation of adhesive pulmonary nodules (the juxta-pleural and juxta-vascular nodules) and ground glass pulmonary nodules (GGNs).
To help the radiologists better differentiate the benign from malignant pulmonary nodules on CT images, a novel classification scheme was proposed to improve the performance of benign and malignant classifier of pulmonary nodules. First, the pulmonary nodules were segmented with the references to the results from four radiologists. Then, some basic features of the segmented nodules such as the shape, gray and texture are given by calculation. Finally, malignant-benign classification of pulmonary nodules is performed by using random forest (RF) with the aid of clustering analysis. The data with a set of 952 nodules have been collected from lung image database consortium (LIDC). The effect of proposed classification scheme was verified by three experiments, in which the variant composite rank of malignancy were got from four radiologists (experiment 1: rank of malignancy ‘1’, ‘2’ as benign and ‘4’, ‘5’ as malignant; experiment 2: rank of malignancy ‘1’, ‘2’, ‘3’ as benign and ‘4’, ‘5’ as malignant; experiment 3: rank of malignancy ‘1’, ‘2’ as benign and ‘3’, ‘4’, ‘5’ as malignant) and the corresponding () (area under the receiver operating characteristic curve) are 0.9702, 0.9190 and 0.8662, respectively. It can be drawn that the method in this work can greatly improve the accuracy of the classification of benign and malignant pulmonary nodules based on CT images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.