Solid, part-solid, or non-solid?: classification of pulmonary nodules in low-dose chest computed tomography by a computer-aided diagnosis system
- PMID: 25478740
- DOI: 10.1097/RLI.0000000000000121
Solid, part-solid, or non-solid?: classification of pulmonary nodules in low-dose chest computed tomography by a computer-aided diagnosis system
Abstract
Objectives: The purpose of this study was to develop and validate a computer-aided diagnosis (CAD) tool for automatic classification of pulmonary nodules seen on low-dose computed tomography into solid, part-solid, and non-solid.
Materials and methods: Study lesions were randomly selected from 2 sites participating in the Dutch-Belgian NELSON lung cancer screening trial. On the basis of the annotations made by the screening radiologists, 50 part-solid and 50 non-solid pulmonary nodules with a diameter between 5 and 30 mm were randomly selected from the 2 sites. For each unique nodule, 1 low-dose chest computed tomographic scan was randomly selected, in which the nodule was visible. In addition, 50 solid nodules in the same size range were randomly selected. A completely automatic 3-dimensional segmentation-based classification system was developed, which analyzes the pulmonary nodule, extracting intensity-, texture-, and segmentation-based features to perform a statistical classification. In addition to the nodule classification by the screening radiologists, an independent rating of all nodules by 3 experienced thoracic radiologists was performed. Performance of CAD was evaluated by comparing the agreement between CAD and human experts and among human experts using the Cohen κ statistics.
Results: Pairwise agreement for the differentiation between solid, part-solid, and non-solid nodules between CAD and each of the human experts had a κ range between 0.54 and 0.72. The interobserver agreement among the human experts was in the same range (κ range, 0.56-0.81).
Conclusions: A novel automated classification tool for pulmonary nodules achieved good agreement with the human experts, yielding κ values in the same range as the interobserver agreement. Computer-aided diagnosis may aid radiologists in selecting the appropriate workup for pulmonary nodules.
Similar articles
-
Automatic 3D pulmonary nodule detection in CT images: A survey.Comput Methods Programs Biomed. 2016 Feb;124:91-107. doi: 10.1016/j.cmpb.2015.10.006. Epub 2015 Dec 2. Comput Methods Programs Biomed. 2016. PMID: 26652979 Review.
-
Semi-automatic volumetric measurement of lung cancer using multi-detector CT effects of nodule characteristics.Acad Radiol. 2009 Oct;16(10):1179-86. doi: 10.1016/j.acra.2009.04.007. Epub 2009 Jun 12. Acad Radiol. 2009. PMID: 19524456
-
Noncalcified lung nodules: volumetric assessment with thoracic CT.Radiology. 2009 Apr;251(1):26-37. doi: 10.1148/radiol.2511071897. Radiology. 2009. PMID: 19332844 Free PMC article. Review.
-
Evaluation of computer-aided diagnosis (CAD) software for the detection of lung nodules on multidetector row computed tomography (MDCT): JAFROC study for the improvement in radiologists' diagnostic accuracy.Acad Radiol. 2008 Dec;15(12):1505-12. doi: 10.1016/j.acra.2008.06.009. Acad Radiol. 2008. PMID: 19000867
-
Computer-aided detection of solid lung nodules in lossy compressed multidetector computed tomography chest exams.Acad Radiol. 2006 Oct;13(10):1194-203. doi: 10.1016/j.acra.2006.06.004. Acad Radiol. 2006. PMID: 16979068
Cited by
-
Pulmonary Nodule Detection Based on Multiscale Feature Fusion.Comput Math Methods Med. 2022 Dec 21;2022:8903037. doi: 10.1155/2022/8903037. eCollection 2022. Comput Math Methods Med. 2022. PMID: 36590762 Free PMC article.
-
SC-Dynamic R-CNN: A Self-Calibrated Dynamic R-CNN Model for Lung Cancer Lesion Detection.Comput Math Methods Med. 2022 Mar 28;2022:9452157. doi: 10.1155/2022/9452157. eCollection 2022. Comput Math Methods Med. 2022. PMID: 35387227 Free PMC article.
-
The impact of lung parenchyma attenuation on nodule volumetry in lung cancer screening.Insights Imaging. 2021 Jun 25;12(1):84. doi: 10.1186/s13244-021-01027-0. Insights Imaging. 2021. PMID: 34170410 Free PMC article.
-
A comparison of the fusion model of deep learning neural networks with human observation for lung nodule detection and classification.Br J Radiol. 2021 Jul 1;94(1123):20210222. doi: 10.1259/bjr.20210222. Epub 2021 Jun 11. Br J Radiol. 2021. PMID: 34111976 Free PMC article.
-
Computer-Aided Diagnosis of Pulmonary Fibrosis Using Deep Learning and CT Images.Invest Radiol. 2019 Oct;54(10):627-632. doi: 10.1097/RLI.0000000000000574. Invest Radiol. 2019. PMID: 31483764 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
Miscellaneous