A Low-Dose CT-Based Radiomic Model to Improve Characterization and Screening Recall Intervals of Indeterminate Prevalent Pulmonary Nodules

Leonardo Rundo, Roberta Eufrasia Ledda, Christian di Noia, Evis Sala, Giancarlo Mauri, Gianluca Milanese, Nicola Sverzellati, Giovanni Apolone, Maria Carla Gilardi, Maria Cristina Messa, Isabella Castiglioni, Ugo Pastorino, Leonardo Rundo, Roberta Eufrasia Ledda, Christian di Noia, Evis Sala, Giancarlo Mauri, Gianluca Milanese, Nicola Sverzellati, Giovanni Apolone, Maria Carla Gilardi, Maria Cristina Messa, Isabella Castiglioni, Ugo Pastorino

Abstract

Lung cancer (LC) is currently one of the main causes of cancer-related deaths worldwide. Low-dose computed tomography (LDCT) of the chest has been proven effective in secondary prevention (i.e., early detection) of LC by several trials. In this work, we investigated the potential impact of radiomics on indeterminate prevalent pulmonary nodule (PN) characterization and risk stratification in subjects undergoing LDCT-based LC screening. As a proof-of-concept for radiomic analyses, the first aim of our study was to assess whether indeterminate PNs could be automatically classified by an LDCT radiomic classifier as solid or sub-solid (first-level classification), and in particular for sub-solid lesions, as non-solid versus part-solid (second-level classification). The second aim of the study was to assess whether an LCDT radiomic classifier could automatically predict PN risk of malignancy, and thus optimize LDCT recall timing in screening programs. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, positive predictive value, negative predictive value, sensitivity, and specificity. The experimental results showed that an LDCT radiomic machine learning classifier can achieve excellent performance for characterization of screen-detected PNs (mean AUC of 0.89 ± 0.02 and 0.80 ± 0.18 on the blinded test dataset for the first-level and second-level classifiers, respectively), providing quantitative information to support clinical management. Our study showed that a radiomic classifier could be used to optimize LDCT recall for indeterminate PNs. According to the performance of such a classifier on the blinded test dataset, within the first 6 months, 46% of the malignant PNs and 38% of the benign ones were identified, improving early detection of LC by doubling the current detection rate of malignant nodules from 23% to 46% at a low cost of false positives. In conclusion, we showed the high potential of LDCT-based radiomics for improving the characterization and optimizing screening recall intervals of indeterminate PNs.

Keywords: low-dose computed tomography; lung cancer risk stratification; lung cancer screening; machine learning; pulmonary nodules; radiomics.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Overall workflow for the development of LDCT radiomic automatic classifiers for PNs.
Figure 2
Figure 2
Classification results achieved by the radiomic classifiers for Aim 1 (PN characterization) and Aim 2 (PN risk) based on the Elastic Net on the discovery dataset by using (a) informative, non-redundant radiomic features, and (b) only the most frequently selected radiomic features. The bar graph and error bars denote the average value and the variability across 50 repetitions, respectively.
Figure 3
Figure 3
Percentage of LDCT second scan recalls for subjects with malignant and benign PN on the (a) discovery and (b) blinded test datasets, according to the reference standard (biopsy). Time interval for the second LDCT examination after LDCT baseline: (i) 0–6 months, (ii) 12–24 months, (iii) 24–36 months.
Figure 4
Figure 4
Percentage of LDCT second scan recalls for subjects with malignant and benign PN on the (a) discovery and (b) blinded test datasets, according to the radiomics-based classifier. Time interval for the second LDCT examination after LDCT baseline: (i) 0–6 months, (ii) 12–24 months, (iii) 24–36 months.

References

    1. De Koning H.J., van der Aalst C.M., de Jong P.A., Scholten E.T., Nackaerts K., Heuvelmans M.A., Lammers J.-W.J., Weenink C., Yousaf-Khan U., Horeweg N., et al. Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial. N. Engl. J. Med. 2020;382:503–513. doi: 10.1056/NEJMoa1911793.
    1. National Lung Screening Trial Research Team. Aberle D.R., Berg C.D., Black W.C., Church T.R., Fagerstrom R.M., Galen B., Gareen I.F., Gatsonis C., Goldin J., et al. The National Lung Screening Trial: Overview and Study Design. Radiology. 2011;258:243–253.
    1. Goldstraw P., Chansky K., Crowley J., Rami-Porta R., Asamura H., Eberhardt W.E.E., Nicholson A.G., Groome P., Mitchell A., Bolejack V., et al. The IASLC Lung Cancer Staging Project: Proposals for Revision of the TNM Stage Groupings in the Forthcoming (Eighth) Edition of the TNM Classification for Lung Cancer. J. Thorac. Oncol. 2016;11:39–51. doi: 10.1016/j.jtho.2015.09.009.
    1. Saul E.E., Guerra R.B., Saul M.E., da Silva L.L., Aleixo G.F.P., Matuda R.M.K., Lopes G. The Challenges of Implementing Low-Dose Computed Tomography for Lung Cancer Screening in Low- and Middle-Income Countries. Nat. Cancer. 2020;1:1140–1152. doi: 10.1038/s43018-020-00142-z.
    1. National Lung Screening Trial Research Team. Aberle D.R., Adams A.M., Berg C.D., Black W.C., Clapp J.D., Fagerstrom R.M., Gareen I.F., Gatsonis C., Marcus P.M., et al. Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening. N. Engl. J. Med. 2011;365:395–409.
    1. Pastorino U., Silva M., Sestini S., Sabia F., Boeri M., Cantarutti A., Sverzellati N., Sozzi G., Corrao G., Marchianò A. Prolonged Lung Cancer Screening Reduced 10-Year Mortality in the MILD Trial: New Confirmation of Lung Cancer Screening Efficacy. Ann. Oncol. 2019;30:1162–1169. doi: 10.1093/annonc/mdz117.
    1. Hunger T., Wanka-Pail E., Brix G., Griebel J. Lung Cancer Screening with Low-Dose CT in Smokers: A Systematic Review and Meta-Analysis. Diagnostics. 2021;11:1040. doi: 10.3390/diagnostics11061040.
    1. Tammemagi M.C., Schmidt H., Martel S., McWilliams A., Goffin J.R., Johnston M.R., Nicholas G., Tremblay A., Bhatia R., Liu G., et al. Participant Selection for Lung Cancer Screening by Risk Modelling (the Pan-Canadian Early Detection of Lung Cancer [PanCan] Study): A Single-Arm, Prospective Study. Lancet Oncol. 2017;18:1523–1531. doi: 10.1016/S1470-2045(17)30597-1.
    1. Swensen S.J., Jett J.R., Sloan J.A., Midthun D.E., Hartman T.E., Sykes A.-M., Aughenbaugh G.L., Zink F.E., Hillman S.L., Noetzel G.R., et al. Screening for Lung Cancer with Low-Dose Spiral Computed Tomography. Am. J. Respir. Crit. Care Med. 2002;165:508–513. doi: 10.1164/ajrccm.165.4.2107006.
    1. Lung–RADS® Version 1.1, Assessment Categories (Release date: 2019) [(accessed on 16 August 2021)]. Available online: .
    1. Gierada D.S., Rydzak C.E., Zei M., Rhea L. Improved Interobserver Agreement on Lung-RADS Classification of Solid Nodules Using Semiautomated CT Volumetry. Radiology. 2020;297:675–684. doi: 10.1148/radiol.2020200302.
    1. De Margerie-Mellon C., Gill R.R., Monteiro Filho A.C., Heidinger B.H., Onken A., VanderLaan P.A., Bankier A.A. Growth Assessment of Pulmonary Adenocarcinomas Manifesting as Subsolid Nodules on CT: Comparison of Diameter-Based and Volume Measurements. Acad. Radiol. 2020;27:1385–1393. doi: 10.1016/j.acra.2019.09.028.
    1. Borghesi A., Michelini S., Scrimieri A., Golemi S., Maroldi R. Solid indeterminate pulmonary nodules of less than 300 mm3: Application of different volume doubling time cut-offs in clinical practice. Diagnostics. 2019;9:62. doi: 10.3390/diagnostics9020062.
    1. Godoy M.C.B., Naidich D.P. Subsolid Pulmonary Nodules and the Spectrum of Peripheral Adenocarcinomas of the Lung: Recommended Interim Guidelines for Assessment and Management. Radiology. 2009;253:606–622. doi: 10.1148/radiol.2533090179.
    1. Borghesi A., Farina D., Michelini S., Ferrari M., Benetti D., Fisogni S., Tironi A., Maroldi R. Pulmonary adenocarcinomas presenting as ground-glass opacities on multidetector CT: Three-dimensional computer-assisted analysis of growth pattern and doubling time. Diagn. Interv. Radiol. 2016;22:525–533. doi: 10.5152/dir.2016.16110.
    1. Esserman L.J., Thompson I.M., Jr., Reid B. Overdiagnosis and Overtreatment in Cancer: An Opportunity for Improvement. JAMA. 2013;310:797–798. doi: 10.1001/jama.2013.108415.
    1. Carter J.L., Coletti R.J., Harris R.P. Quantifying and Monitoring Overdiagnosis in Cancer Screening: A Systematic Review of Methods. BMJ. 2015;350:g7773. doi: 10.1136/bmj.g7773.
    1. Bach P.B. Overdiagnosis in Lung Cancer: Different Perspectives, Definitions, Implications. Thorax. 2008;63:298–300. doi: 10.1136/thx.2007.082990.
    1. Wu G.X., Raz D.J., Brown L., Sun V. Psychological Burden Associated With Lung Cancer Screening: A Systematic Review. Clin. Lung Cancer. 2016;17:315–324. doi: 10.1016/j.cllc.2016.03.007.
    1. Gillies R.J., Kinahan P.E., Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2016;278:563–577. doi: 10.1148/radiol.2015151169.
    1. Castiglioni I., Rundo L., Codari M., Di Leo G., Salvatore C., Interlenghi M., Gallivanone F., Cozzi A., D’Amico N.C., Sardanelli F. AI Applications to Medical Images: From Machine Learning to Deep Learning. Phys. Med. 2021;83:9–24. doi: 10.1016/j.ejmp.2021.02.006.
    1. Ninatti G., Kirienko M., Neri E., Sollini M., Chiti A. Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review. Diagnostics. 2020;10:359. doi: 10.3390/diagnostics10060359.
    1. Mazzaschi G., Milanese G., Pagano P., Madeddu D., Gnetti L., Trentini F., Falco A., Frati C., Lorusso B., Lagrasta C., et al. Integrated CT Imaging and Tissue Immune Features Disclose a Radio-Immune Signature with High Prognostic Impact on Surgically Resected NSCLC. Lung Cancer. 2020;144:30–39. doi: 10.1016/j.lungcan.2020.04.006.
    1. Antunovic L., Gallivanone F., Sollini M., Sagoma A., Invento A., Manfrinato G., Kirienko M., Tinterri C., Chiti A. [18F]FDG PET/CT features for the molecular characterization of primary breast tumors. Eur. J. Nucl. Med. Mol. Imaging. 2017;44:1945–1954. doi: 10.1007/s00259-017-3770-9.
    1. Huang P., Park S., Yan R., Lee J., Chu L.C., Lin C.T., Hussien A., Rathmell J., Thomas B., Chen C., et al. Added Value of Computer-Aided CT Image Features for Early Lung Cancer Diagnosis with Small Pulmonary Nodules: A Matched Case-Control Study. Radiology. 2018;286:286–295. doi: 10.1148/radiol.2017162725.
    1. Fedorov A., Beichel R., Kalpathy-Cramer J., Finet J., Fillion-Robin J.-C., Pujol S., Bauer C., Jennings D., Fennessy F., Sonka M., et al. 3D Slicer as an Image Computing Platform for the Quantitative Imaging Network. Magn. Reson. Imaging. 2012;30:1323–1341. doi: 10.1016/j.mri.2012.05.001.
    1. Zwanenburg A., Vallières M., Abdalah M.A., Aerts H.J.W.L., Andrearczyk V., Apte A., Ashrafinia S., Bakas S., Beukinga R.J., Boellaard R., et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-Based Phenotyping. Radiology. 2020;295:328–338. doi: 10.1148/radiol.2020191145.
    1. Zwanenburg A., Leger S., Vallières M., Löck S. Image biomarker standardisation initiative. arXiv. 20161612.07003
    1. Haralick R.M., Shanmugam K., Dinstein I. Textural Features for Image Classification. IEEE Trans. Syst. Man Cybern. 1973;6:610–621. doi: 10.1109/TSMC.1973.4309314.
    1. Haralick R.M. Statistical and Structural Approaches to Texture. Proc. IEEE. 1979;67:786–804. doi: 10.1109/PROC.1979.11328.
    1. Rundo L., Tangherloni A., Galimberti S., Cazzaniga P., Woitek R., Sala E. HaraliCU: GPU-powered Haralick feature extraction on medical images exploiting the full dynamics of gray-scale levels; Proceedings of the International Conference on Parallel Computing Technologies (PaCT) 2019; Almaty, Kazakhstan. 19–23 August 2019; Cham, Switzerland: Springer; 2019. pp. 304–318. LNCS.
    1. Galloway M.M. Texture Analysis Using Gray Level Run Lengths. Comput. Graph. Image Process. 1975;4:172–179. doi: 10.1016/S0146-664X(75)80008-6.
    1. Thibault G., Angulo J., Meyer F. Advanced Statistical Matrices for Texture Characterization: Application to Cell Classification. IEEE Trans. Biomed. Eng. 2014;61:630–637. doi: 10.1109/TBME.2013.2284600.
    1. Sun C., Wee W.G. Neighboring Gray Level Dependence Matrix for Texture Classification. Comput. Graph. Image Process. 1982;20:297. doi: 10.1016/0146-664X(82)90093-4.
    1. Amadasun M., King R. Textural Features Corresponding to Textural Properties. IEEE Trans. Syst. Man Cybern. 1989;19:1264–1274. doi: 10.1109/21.44046.
    1. Revel M.-P., Mannes I., Benzakoun J., Guinet C., Léger T., Grenier P., Lupo A., Fournel L., Chassagnon G., Bommart S. Subsolid Lung Nodule Classification: A CT Criterion for Improving Interobserver Agreement. Radiology. 2018;286:316–325. doi: 10.1148/radiol.2017170044.
    1. Papanikolaou N., Matos C., Koh D.M. How to Develop a Meaningful Radiomic Signature for Clinical Use in Oncologic Patients. Cancer Imaging. 2020;20:33. doi: 10.1186/s40644-020-00311-4.
    1. Zou H., Hastie T. Regularization and Variable Selection via the Elastic Net. J. R. Stat. Soc. B. 2005;67:301–320. doi: 10.1111/j.1467-9868.2005.00503.x.
    1. Tibshirani R. Regression Shrinkage and Selection via the Lasso: A Retrospective. R. Stat. Soc. B. 2011;73:273–282. doi: 10.1111/j.1467-9868.2011.00771.x.
    1. Gill A.B., Rundo L., Wan J.C.M., Lau D., Zawaideh J.P., Woitek R., Zaccagna F., Beer L., Gale D., Sala E., et al. Correlating Radiomic Features of Heterogeneity on CT with Circulating Tumor DNA in Metastatic Melanoma. Cancers. 2020;12:3493. doi: 10.3390/cancers12123493.
    1. Hoerl A.E., Kennard R.W. Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics. 2000;42:80–86. doi: 10.1080/00401706.2000.10485983.
    1. Parvandeh S., Yeh H.-W., Paulus M.P., McKinney B.A. Consensus Features Nested Cross-Validation. Bioinformatics. 2020;36:3093–3098. doi: 10.1093/bioinformatics/btaa046.
    1. Cawley G.C. Advances in Intelligent Data Analysis XI (IDA 2012) Volume 7619. Springer; Berlin/Heidelberg, Germany: 2012. Over-Fitting in Model Selection and Its Avoidance; p. 1. LNCS.
    1. Briggs W.M., Zaretzki R. The Skill Plot: A Graphical Technique for Evaluating Continuous Diagnostic Tests. Biometrics. 2008;64:250–266. doi: 10.1111/j.1541-0420.2007.00781_1.x.
    1. Chawla N.V., Bowyer K.W., Hall L.O., Kegelmeyer W.P. SMOTE: Synthetic Minority Over-Sampling Technique. J. Artif. Intell. Res. 2002;16:321–357. doi: 10.1613/jair.953.
    1. Han H., Wang W.-Y., Mao B.-H. Advances in Intelligent Computing (ICIC 2005) Volume 3644. Springer; Berlin/Heidelberg, Germany: 2005. Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning; pp. 878–887. LNCS.
    1. Bunkhumpornpat C., Sinapiromsaran K., Lursinsap C. Advances in Knowledge Discovery and Data Mining. Volume 5476. Springer; Berlin/Heidelberg, Germany: 2009. Safe-Level-SMOTE: Safe-Level-Synthetic Minority Over-Sampling TEchnique for Handling the Class Imbalanced Problem; pp. 475–482. LNCS.
    1. He H., Bai Y., Garcia E.A., Li S. ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning; Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) 2008; Hong Kong, China. 1–6 June 2008; pp. 1322–1328.
    1. Hotelling H. Analysis of a Complex of Statistical Variables into Principal Components. J. Educ. Psychol. 1933;24:417–441. doi: 10.1037/h0071325.
    1. Van der Maaten L., Hinton G. Visualizing Data Using t-SNE. J. Mach. Learn. Res. 2008;9:2579–2605.
    1. Ramentol E., Vluymans S., Verbiest N., Caballero Y., Bello R., Cornelis C., Herrera F. IFROWANN: Imbalanced Fuzzy-Rough Ordered Weighted Average Nearest Neighbor Classification. IEEE Trans. Fuzzy Syst. 2015;23:1622–1637. doi: 10.1109/TFUZZ.2014.2371472.
    1. Lokhandwala T., Bittoni M.A., Dann R.A., D’Souza A.O., Johnson M., Nagy R.J., Lanman R.B., Merritt R.E., Carbone D.P. Costs of Diagnostic Assessment for Lung Cancer: A Medicare Claims Analysis. Clin. Lung Cancer. 2017;18:e27–e34. doi: 10.1016/j.cllc.2016.07.006.
    1. Freiman M.R., Clark J.A., Slatore C.G., Gould M.K., Woloshin S., Schwartz L.M., Wiener R.S. Patients’ Knowledge, Beliefs, and Distress Associated with Detection and Evaluation of Incidental Pulmonary Nodules for Cancer: Results from a Multicenter Survey. J. Thorac. Oncol. 2016;11:700–708. doi: 10.1016/j.jtho.2016.01.018.
    1. Huang Y., Liu Z., He L., Chen X., Pan D., Ma Z., Liang C., Tian J., Liang C. Radiomics Signature: A Potential Biomarker for the Prediction of Disease-Free Survival in Early-Stage (I or II) Non-Small Cell Lung Cancer. Radiology. 2016;281:947–957. doi: 10.1148/radiol.2016152234.
    1. Choi W., Oh J.H., Riyahi S., Liu C.-J., Jiang F., Chen W., White C., Rimner A., Mechalakos J.G., Deasy J.O., et al. Radiomics Analysis of Pulmonary Nodules in Low-Dose CT for Early Detection of Lung Cancer. Med. Phys. 2018;45:1537–1549. doi: 10.1002/mp.12820.
    1. Pérez-Morales J., Tunali I., Stringfield O., Eschrich S.A., Balagurunathan Y., Gillies R.J., Schabath M.B. Peritumoral and Intratumoral Radiomic Features Predict Survival Outcomes among Patients Diagnosed in Lung Cancer Screening. Sci. Rep. 2020;10:10528. doi: 10.1038/s41598-020-67378-8.
    1. Garau N., Paganelli C., Summers P., Choi W., Alam S., Lu W., Fanciullo C., Bellomi M., Baroni G., Rampinelli C. External Validation of Radiomics-Based Predictive Models in Low-Dose CT Screening for Early Lung Cancer Diagnosis. Med. Phys. 2020;47:4125–4136. doi: 10.1002/mp.14308.
    1. Silva M., Milanese G., Sestini S., Sabia F., Jacobs C., van Ginneken B., Prokop M., Schaefer-Prokop C.M., Marchianò A., Sverzellati N., et al. Lung Cancer Screening by Nodule Volume in Lung-RADS v1.1: Negative Baseline CT Yields Potential for Increased Screening Interval. Eur. Radiol. 2021;31:1956–1968. doi: 10.1007/s00330-020-07275-w.
    1. Doran S.J., Kumar S., Orton M., d’Arcy J., Kwaks F., O’Flynn E., Ahmed Z., Downey K., Dowsett M., Turner N., et al. “Real-world” radiomics from multi-vendor MRI: An original retrospective study on the prediction of nodal status and disease survival in breast cancer, as an exemplar to promote discussion of the wider issues. Cancer Imaging. 2021;21:37. doi: 10.1186/s40644-021-00406-6.
    1. Boeri M., Verri C., Conte D., Roz L., Modena P., Facchinetti F., Calabrò E., Croce C.M., Pastorino U., Sozzi G. MicroRNA Signatures in Tissues and Plasma Predict Development and Prognosis of Computed Tomography Detected Lung Cancer. Proc. Natl. Acad. Sci. USA. 2011;108:3713–3718. doi: 10.1073/pnas.1100048108.
    1. Bianconi F., Palumbo I., Spanu A., Nuvoli S., Fravolini M.L., Palumbo B. PET/CT Radiomics in Lung Cancer: An Overview. Appl. Sci. 2020;10:1718. doi: 10.3390/app10051718.
    1. Fraioli F., Lyasheva M., Porter J.C., Bomanji J., Shortman R.I., Endozo R., Wan S., Bertoletti L., Machado M., Ganeshan B., et al. Synergistic Application of Pulmonary F-FDG PET/HRCT and Computer-Based CT Analysis with Conventional Severity Measures to Refine Current Risk Stratification in Idiopathic Pulmonary Fibrosis (IPF) Eur. J. Nucl. Med. Mol. Imaging. 2019;46:2023–2031. doi: 10.1007/s00259-019-04386-5.

Source: PubMed

Sponsors et collaborateurs

Les conditions médicales

Interventions en matière de drogue

3
S'abonner