Automatic Lung Nodule Segmentation and Intra-Nodular Heterogeneity Image Generation
Authors:
- Jiangdian SongJSJiangdian Song
- Shih-Cheng HuangSHShih-Cheng Huang
- Brendan KellyBKBrendan Kelly
- Guanqun LiaoGLGuanqun Liao
- Jing-Yun ShiJSJing-Yun Shi
- Ning WuNWNing Wu
- Weimin LiWLWeimin Li
- Zaiyi LiuZLZaiyi Liu
- Lei CuiLCLei Cui
- Matthew P. LungrenMLMatthew P. Lungren
- Michael E. MoseleyMMMichael E. Moseley
- Peng GaoPGPeng Gao
Open Access
- 15 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (6) , 2570-2581
Abstract
Automatic segmentation of lung nodules on computed tomography (CT) images is challenging owing to the variability of morphology, location, and intensity. In addition, few segmentation methods can capture intra-nodular heterogeneity to assist lung nodule diagnosis. In this study, we propose an end-to-end architecture to perform fully automated segmentation of multiple types of lung nodules and generate intra-nodular heterogeneity images for clinical use. To this end, a hybrid loss is considered by introducing a Faster R-CNN model based on generalized intersection over union loss in generative adversarial network. The Lung Image Database Consortium image collection dataset, comprising 2,635 lung nodules, was combined with 3,200 lung nodules from five hospitals for this study. Compared with manual segmentation by radiologists, the proposed model obtained an average dice coefficient (DC) of 82.05% on the test dataset. Compared with U-net , NoduleNet , nnU-net , and other three models, the proposed method achieved comparable performance on lung nodule segmentation and generated more vivid and valid intra-nodular heterogeneity images, which are beneficial in radiological diagnosis. In an external test of 91 patients from another hospital, the proposed model achieved an average DC of 81.61%. The proposed method effectively addresses the challenges of inevitable human interaction and additional pre-processing procedures in the existing solutions for lung nodule segmentation. In addition, the results show that the intra-nodular heterogeneity images generated by the proposed model are suitable to facilitate lung nodule diagnosis in radiology.Keywords
Funding Information
- China Scholarship Council
- National Natural Science Foundation of China (82001904)
This publication has 37 references indexed in Scilit:
- 3-D Active Contour Segmentation Based on Sparse Linear Combination of Training Shapes (SCoTS)IEEE Transactions on Medical Imaging, 2017
- Lung nodule detection in CT using 3D convolutional neural networks2017
- Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imagingClinical Radiology, 2017
- Reliability of PET/CT Shape and Heterogeneity Features in Functional and Morphologic Components of Non–Small Cell Lung Cancer Tumors: A Repeatability Analysis in a Prospective Multicenter CohortJournal of Nuclear Medicine, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance imagesProceedings of the National Academy of Sciences, 2015
- Lung Lesion Extraction Using a Toboggan Based Growing Automatic Segmentation ApproachIEEE Transactions on Medical Imaging, 2015
- A Segmentation Framework of Pulmonary Nodules in Lung CT ImagesJournal of Digital Imaging, 2015
- Segmentation of pulmonary nodules in computed tomography using a regression neural network approach and its application to the Lung Image Database Consortium and Image Database Resource Initiative datasetMedical Image Analysis, 2015
- The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT ScansMedical Physics, 2011