Predicting Malignant Nodules from Screening CT Scans

Overview

Journal J Thorac Oncol

Publisher Elsevier

Specialties Oncology
Pulmonary Medicine

Date 2016 Jul 17

PMID 27422797

Citations 141

Authors

Samuel Hawkins

Hua Wang

Ying Liu

Alberto Garcia

Olya Stringfield

Henry Krewer

Qian Li

Dmitry Cherezov

Robert A Gatenby

Yoganand Balagurunathan

Dmitry Goldgof

Matthew B Schabath

Lawrence Hall

Robert J Gillies

Affiliations

Soon will be listed here.

Abstract

Objectives: The aim of this study was to determine whether quantitative analyses ("radiomics") of low-dose computed tomography lung cancer screening images at baseline can predict subsequent emergence of cancer.

Methods: Public data from the National Lung Screening Trial (ACRIN 6684) were assembled into two cohorts of 104 and 92 patients with screen-detected lung cancer and then matched with cohorts of 208 and 196 screening subjects with benign pulmonary nodules. Image features were extracted from each nodule and used to predict the subsequent emergence of cancer.

Results: The best models used 23 stable features in a random forests classifier and could predict nodules that would become cancerous 1 and 2 years hence with accuracies of 80% (area under the curve 0.83) and 79% (area under the curve 0.75), respectively. Radiomics outperformed the Lung Imaging Reporting and Data System and volume-only approaches. The performance of the McWilliams risk assessment model was commensurate.

Conclusions: The radiomics of lung cancer screening computed tomography scans at baseline can be used to assess risk for development of cancer.

Citing Articles

Annotated test-retest dataset of lung cancer CT scan images reconstructed at multiple imaging parameters.

Zhao B, Dercle L, Yang H, Riely G, Kris M, Schwartz L Sci Data. 2024; 11(1):1259.

PMID: 39567508 PMC: 11579286. DOI: 10.1038/s41597-024-04085-3.

Enhancing the differential diagnosis of small pulmonary nodules: a comprehensive model integrating plasma methylation, protein biomarkers, and LDCT imaging features.

Yang M, Yu H, Feng H, Duan J, Wang K, Tong B J Transl Med. 2024; 22(1):984.

PMID: 39482707 PMC: 11526513. DOI: 10.1186/s12967-024-05723-5.

Differential Radiomics-Based Signature Predicts Lung Cancer Risk Accounting for Imaging Parameters in NLST Cohort.

Ebrahimpour L, Despres P, Manem V Cancer Med. 2024; 13(20):e70359.

PMID: 39463128 PMC: 11513548. DOI: 10.1002/cam4.70359.

Differential diagnosis of benign and lung adenocarcinoma presenting as larger solid nodules and masses based on multiscale CT radiomics.

Xie J, He Y, Che S, Zhao W, Niu Y, Qin D PLoS One. 2024; 19(10):e0309033.

PMID: 39365772 PMC: 11451992. DOI: 10.1371/journal.pone.0309033.

Artificial Intelligence-What to Expect From Machine Learning and Deep Learning in Hernia Surgery.

Vogel R, Muck B J Abdom Wall Surg. 2024; 3:13059.

PMID: 39310669 PMC: 11412881. DOI: 10.3389/jaws.2024.13059.

References

Gopal M, Abdullah S, Grady J, Goodwin J . Screening for lung cancer with low-dose computed tomography: a systematic review and meta-analysis of the baseline findings of randomized controlled trials. J Thorac Oncol. 2010; 5(8):1233-9. PMC: 4006972. DOI: 10.1097/JTO.0b013e3181e0b977. View

Gillies R, Kinahan P, Hricak H . Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2015; 278(2):563-77. PMC: 4734157. DOI: 10.1148/radiol.2015151169. View

Balagurunathan Y, Gu Y, Wang H, Kumar V, Grove O, Hawkins S . Reproducibility and Prognosis of Quantitative Features Extracted from CT Images. Transl Oncol. 2014; 7(1):72-87. PMC: 3998690. DOI: 10.1593/tlo.13844. View

Sozzi G, Boeri M, Rossi M, Verri C, Suatoni P, Bravi F . Clinical utility of a plasma-based miRNA signature classifier within computed tomography lung cancer screening: a correlative MILD trial study. J Clin Oncol. 2014; 32(8):768-73. PMC: 4876348. DOI: 10.1200/JCO.2013.50.4357. View

Banfield R, Hall L, Bowyer K, Kegelmeyer W . A comparison of decision tree ensemble creation techniques. IEEE Trans Pattern Anal Mach Intell. 2006; 29(1):173-80. DOI: 10.1109/tpami.2007.250609. View

McWilliams A, Tammemagi M, Mayo J, Roberts H, Liu G, Soghrati K . Probability of cancer in pulmonary nodules detected on first screening CT. N Engl J Med. 2013; 369(10):910-9. PMC: 3951177. DOI: 10.1056/NEJMoa1214726. View

Manser R, Lethaby A, Irving L, Stone C, Byrnes G, Abramson M . Screening for lung cancer. Cochrane Database Syst Rev. 2013; (6):CD001991. PMC: 6464996. DOI: 10.1002/14651858.CD001991.pub3. View

Gu Y, Kumar V, Hall L, Goldgof D, Li C, Korn R . Automated Delineation of Lung Tumors from CT Images Using a Single Click Ensemble Segmentation Approach. Pattern Recognit. 2013; 46(3):692-702. PMC: 3580869. DOI: 10.1016/j.patcog.2012.10.005. View

Pinsky P, Gierada D, Black W, Munden R, Nath H, Aberle D . Performance of Lung-RADS in the National Lung Screening Trial: a retrospective assessment. Ann Intern Med. 2015; 162(7):485-91. PMC: 4705835. DOI: 10.7326/M14-2086. View

10.

Patz Jr E, Pinsky P, Gatsonis C, Sicks J, Kramer B, Tammemagi M . Overdiagnosis in low-dose computed tomography screening for lung cancer. JAMA Intern Med. 2013; 174(2):269-74. PMC: 4040004. DOI: 10.1001/jamainternmed.2013.12738. View

11.

Balagurunathan Y, Kumar V, Gu Y, Kim J, Wang H, Liu Y . Test-retest reproducibility analysis of lung CT image features. J Digit Imaging. 2014; 27(6):805-23. PMC: 4391075. DOI: 10.1007/s10278-014-9716-x. View

12.

Aberle D, Adams A, Berg C, Black W, Clapp J, Fagerstrom R . Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med. 2011; 365(5):395-409. PMC: 4356534. DOI: 10.1056/NEJMoa1102873. View

13.

Alpaydin E . Combined 5 x 2 cv F test for comparing supervised classification learning algorithms. Neural Comput. 1999; 11(8):1885-92. DOI: 10.1162/089976699300016007. View

14.

McNEMAR Q . Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika. 2010; 12(2):153-7. DOI: 10.1007/BF02295996. View