Radiomics analysis of pulmonary nodules in low‐dose CT for early detection of lung cancer
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Purpose: To develop a radiomics prediction model to improve pulmonary nodule (PN) classification in low‐dose CT. To compare the model with the American College of Radiology (ACR) Lung CT Screening Reporting and Data System (Lung‐RADS) for early detection of lung cancer. Methods: We examined a set of 72 PN s (31 benign and 41 malignant) from the Lung Image Database Consortium image collection (LIDC‐IDRI). One hundred three CT radiomic features were extracted from each PN. Before the model building process, distinctive features were identified using a hierarchical clustering method. We then constructed a prediction model by using a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). A tenfold cross‐validation (CV) was repeated ten times (10 × 10‐fold CV) to evaluate the accuracy of the SVM‐LASSO model. Finally, the best model from the 10 × 10‐fold CV was further evaluated using 20 × 5‐ and 50 × 2‐fold CV s. Results: The best SVM‐LASSO model consisted of only two features: the bounding box anterior–posterior dimension (BB _ AP) and the standard deviation of inverse difference moment (SD _ IDM). The BB _ AP measured the extension of a PN in the anterior–posterior direction and was highly correlated (r = 0.94) with the PN size. The SD _ IDM was a texture feature that measured the directional variation of the local homogeneity feature IDM. Univariate analysis showed that both features were statistically significant and discriminative (P = 0.00013 and 0.000038, respectively). PN s with larger BB _ AP or smaller SD _ IDM were more likely malignant. The 10 × 10‐fold CV of the best SVM model using the two features achieved an accuracy of 84.6% and 0.89 AUC. By comparison, Lung‐RADS achieved an accuracy of 72.2% and 0.77 AUC using four features (size, type, calcification, and spiculation). The prediction improvement of SVM‐LASSO comparing to Lung‐RADS was statistically significant (McNemar's test P = 0.026). Lung‐RADS misclassified 19 cases because it was mainly based on PN size, whereas the SVM‐LASSO model correctly classified 10 of these cases by combining a size (BB _ AP) feature and a texture (SD _ IDM) feature. The performance of the SVM‐LASSO model was stable when leaving more patients out with five‐ and twofold CV s (accuracy 84.1% and 81.6%, respectively). Conclusion: We developed an SVM‐LASSO model to predict malignancy of PN s with two CT radiomic features. We demonstrated that the model achieved an accuracy of 84.6%, which was 12.4% higher than Lung‐RADS.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Textural Features for Image Classification
Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1973.4309314 · Cited by 22,886
Radiomics: Images Are More than Pictures, They Are Data
Gillies, R. J., Kinahan, P. E., & Hricak, H. (2016) · Radiology · doi:10.1148/radiol.2015151169 · Cited by 8,421
Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
Aerts, H. J. W. L., Velazquez, E. R., Leijenaar, R. T. H., Parmar, C., Grossmann, P., Carvalho, S., Bussink, J., Monshouwer, R., Haibe-Kains, B., Rietveld, D., et al. (2014) · Nature Communications · doi:10.1038/ncomms5006 · Cited by 5,132 · cited 1×
“Third, we extracted 103 radiomic features from each PN to quantify its intensity, shape, and texture (spatial variations).(23,27,41) Finally, we performed a univariate analysis using Wilcoxon rank-sum test and the area under the receiver operating characteristic curve (AUC) to evaluate the significance of each feature.”
MethodArmato, S. G., McLennan, G., Bidaut, L., McNitt‐Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., et al. (2011) · Medical Physics · doi:10.1118/1.3528204 · Cited by 2,887 · cited 1×
“The Lung Image Database Consortium image collection (LIDC-IDRI) in The Cancer Imaging Archive (TCIA) contains 1018 cases with low-dose screening thoracic CT scans and marked-up annotated lesions.(37) Four experienced thoracic radiologists performed contouring and image annotation.”
MethodWarfield, S. K., Zou, K. H., & Wells, W. M. (2004) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2004.828354 · Cited by 2,072
Agreement Between Methods of Measurement with Multiple Observations Per Individual
Bland, J. M., & Altman, D. G. (2007) · Journal of Biopharmaceutical Statistics · doi:10.1080/10543400701329422 · Cited by 2,065
Overdiagnosis in Low-Dose Computed Tomography Screening for Lung Cancer
Patz, E. F., Pinsky, P., Gatsonis, C., Sicks, J. D., Kramer, B. S., Tammemägi, M. C., Chiles, C., Black, W. C., & Aberle, D. R. (2014) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2013.12738 · Cited by 776
Cited by
Non‐small cell lung cancer in China
Chen, P., Liu, Y., Wen, Y., & Zhou, C. (2022) · Cancer Communications · doi:10.1002/cac2.12359 · Cited by 656
Apostolopoulos, I. D., Aznaouridis, S. I., & Tzani, M. A. (2020) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-020-00529-4 · Cited by 335
Huang, S., Yang, J., Shen, N., Xu, Q., & Zhao, Q. (2023) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2023.01.006 · Cited by 317
Radiomics and deep learning in lung cancer
Avanzo, M., Stancanello, J., Pirrone, G., & Sartor, G. (2020) · Strahlentherapie und Onkologie · doi:10.1007/s00066-020-01625-9 · Cited by 263
Artificial Intelligence and its future potential in lung cancer screening
Joy Mathew, C., David, A. M., & Joy Mathew, C. M. (2020) · IfADo - Leibniz Research Centre for Working Environment and Human Factors, Dortmund · doi:10.17179/excli2020-3095 · Cited by 59
Metadata
- Authors
- Choi, W., Oh, J. H., Riyahi, S., Liu, C., Jiang, F., Chen, W., White, C., Rimner, A., Mechalakos, J. G., Deasy, J. O., & Lu, W.
- Venue
- Medical Physics
- Publisher
- Wiley
- Published
- 2018-03-12
- Volume
- 45
- Issue
- 4
- Pages
- 1537-1549
- ISSN
- 0094-2405 (ISSN-L)
- 2473-4209
- OpenAlex
- W2791069488
- Cited by
- 152
- References
- 8
- FWCI
- 10.55
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.