Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer Journal Article
| Authors: | Choi, W.; Oh, J. H.; Riyahi, S.; Liu, C. J.; Jiang, F.; Chen, W.; White, C.; Rimner, A.; Mechalakos, J. G.; Deasy, J. O.; Lu, W. |
| Article Title: | Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer |
| 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 PNs (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 CVs. 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). PNs 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 CVs (accuracy 84.1% and 81.6%, respectively). Conclusion: We developed an SVM-LASSO model to predict malignancy of PNs with two CT radiomic features. We demonstrated that the model achieved an accuracy of 84.6%, which was 12.4% higher than Lung-RADS. © 2018 American Association of Physicists in Medicine |
| Keywords: | lung cancer; ct; pulmonary nodule; radiomics; svm |
| Journal Title: | Medical Physics |
| Volume: | 45 |
| Issue: | 4 |
| ISSN: | 0094-2405 |
| Publisher: | American Association of Physicists in Medicine |
| Date Published: | 2018-04-01 |
| Start Page: | 1537 |
| End Page: | 1549 |
| Language: | English |
| DOI: | 10.1002/mp.12820 |
| PROVIDER: | scopus |
| PMCID: | PMC5903960 |
| PUBMED: | 29457229 |
| DOI/URL: | |
| Notes: | Article -- Export Date: 1 May 2018 -- Source: Scopus |
Altmetric
Citation Impact
MSK Authors
-
467Rimner -
156Mechalakos -
170Oh -
471Deasy -
59Lu -
18Choi -
46
Riyahi Alam -
8
Liu
Related MSK Work