Highlights
- •Introducing a physiologically meaningful pattern to capture intra tumor heterogeneity.
- •Proposed features are highly robust against differences in patients’ variable.
- •Survival prediction power is 0.90 (AUC) without feature selection.
- •Combined with radiomics, prediction power increased up to 0.95 (AUC).
Abstract
Purpose
To explore prognostic and predictive values of a novel quantitative feature set describing
intra-tumor heterogeneity in patients with lung cancer treated with concurrent and
sequential chemoradiotherapy.
Methods
Longitudinal PET-CT images of 30 patients with non-small cell lung cancer were analysed.
To describe tumor cell heterogeneity, the tumors were partitioned into one to ten
concentric regions depending on their sizes, and, for each region, the change in average
intensity between the two scans was calculated for PET and CT images separately to
form the proposed feature set. To validate the prognostic value of the proposed method,
radiomics analysis was performed and a combination of the proposed novel feature set
and the classic radiomic features was evaluated. A feature selection algorithm was
utilized to identify the optimal features, and a linear support vector machine was
trained for the task of overall survival prediction in terms of area under the receiver
operating characteristic curve (AUROC).
Results
The proposed novel feature set was found to be prognostic and even outperformed the
radiomics approach with a significant difference (AUROCSALoP = 0.90 vs. AUROCradiomic = 0.71) when feature selection was not employed, whereas with feature selection,
a combination of the novel feature set and radiomics led to the highest prognostic
values.
Conclusion
A novel feature set designed for capturing intra-tumor heterogeneity was introduced.
Judging by their prognostic power, the proposed features have a promising potential
for early survival prediction.
Graphical abstract
Graphical Abstract
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Physica Medica: European Journal of Medical PhysicsAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Global Cancer Statistics, 2012.CA Cancer J Clin. 2015; 65: 87-108https://doi.org/10.3322/caac.21262
Cancer Fact Sheet. World Heal Organ. http://www.who.int/mediacentre/factsheets/fs297/en/.
- CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma.Radiother Oncol. 2015; 114: 345-350https://doi.org/10.1016/j.radonc.2015.02.015
- Prognostic value and reproducibility of pretreatment ct texture features in stage III non-small cell lung cancer.Int J Radiat Oncol Biol Phys. 2014; 90: 834-842https://doi.org/10.1016/j.ijrobp.2014.07.020
- Test-retest reproducibility analysis of lung CT image features.J Digit Imaging. 2014; 27: 805-823https://doi.org/10.1007/s10278-014-9716-x
- Positron emission tomography/computerized tomography for tumor response assessment—a review of clinical practices and radiomics studies.Transl Cancer Res. 2016; 5: 364-370https://doi.org/10.21037/tcr.2016.07.12
- From RECIST to PERCIST: evolving considerations for PET response criteria in solid tumors.J Nucl Med. 2009; 50: 122S-150Shttps://doi.org/10.2967/jnumed.108.057307
- Radiomics and its emerging role in lung cancer research, imaging biomarkers and clinical management: state of the art.Eur J Radiol. 2017; 86: 297-307https://doi.org/10.1016/j.ejrad.2016.09.005
- PET to assess early metabolic response and to guide treatment of adenocarcinoma of the oesophagogastric junction: the MUNICON phase II trial.Lancet Oncol. 2007; 8: 797-805https://doi.org/10.1016/S1470-2045(07)70244-9
- Positron emission tomography-computed tomography standardized uptake values in clinical practice and assessing response to therapy.Semin Ultrasound, CT MRI. 2010; 31: 496-505https://doi.org/10.1053/j.sult.2010.10.001
- Reproducibility of radiomics for deciphering tumor phenotype with imaging.Sci Rep. 2016; 6: 1-7https://doi.org/10.1038/srep23428
- Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma.Cancer Lett. 2017; 403: 21-27https://doi.org/10.1016/j.canlet.2017.06.004
- Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomics and fuzzy classification.Artif Intell Med. 2017; 81: 41-53https://doi.org/10.1016/j.artmed.2017.03.004
- Radiomics-based assessment of radiation-induced lung injury after stereotactic body radiotherapy.Clin Lung Cancer. 2017; 18: e425-e431https://doi.org/10.1016/j.cllc.2017.05.014
- Predictive and prognostic value of CT based radiomics signature in locally advanced head and neck cancers patients treated with concurrent chemoradiotherapy or bioradiotherapy and its added value to Human Papillomavirus status.Oral Oncol. 2017; 71: 150-155https://doi.org/10.1016/j.oraloncology.2017.06.015
- Radiomics: images are more than pictures, they are data.Radiology. 2016; 278: 563-577https://doi.org/10.1148/radiol.2015151169
- Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.Nat Commun. 2014; 5https://doi.org/10.1038/ncomms5006
- Radiomics: extracting more information from medical images using advanced feature analysis.Eur J Cancer. 2012; 48: 441-446https://doi.org/10.1016/j.ejca.2011.11.036
- 4DCT imaging to assess radiomics feature stability: an investigation for thoracic cancers.Radiother Oncol. 2017; 125: 147-153https://doi.org/10.1016/j.radonc.2017.07.023
- Radiomics: the bridge between medical imaging and personalized medicine.Nat Rev Clin Oncol. 2017; 14: 749-762https://doi.org/10.1038/nrclinonc.2017.141
- CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer.Radiother Oncol. 2016; 120: 258-266https://doi.org/10.1016/j.radonc.2016.05.024
- Survival prediction of non-small cell lung cancer patients using radiomics analyses of cone-beam CT images.Radiother Oncol. 2017; 123: 363-369https://doi.org/10.1016/j.radonc.2017.04.016
- Radiomic phenotype features predict pathological response in non-small cell lung cancer.Radiother Oncol. 2016; 119: 480-486https://doi.org/10.1016/j.radonc.2016.04.004
- Fusion of quantitative image and genomic biomarkers to improve prognosis assessment of early stage lung cancer patients.IEEE Trans Biomed Eng. 2016; 63: 1034-1043https://doi.org/10.1109/TBME.2015.2477688
- Stability of FDG-PET radiomics features: an integrated analysis of test-retest and inter-observer variability.Acta Oncol (Madr). 2013; 52: 1391-1397https://doi.org/10.3109/0284186X.2013.812798
- Heterogeneity of metabolic response to systemic therapy in metastatic breast cancer patients.Clin Oncol. 2010; 22: 818-827https://doi.org/10.1016/j.clon.2010.05.021
- Imaging intratumor heterogeneity: Role in therapy response, resistance, and clinical outcome.Clin Cancer Res. 2015; 21: 249-257https://doi.org/10.1158/1078-0432.CCR-14-0990
- Robust intratumor partitioning to identify high-risk subregions in lung cancer: a pilot study.Int J Radiat Oncol Biol Phys. 2016; 95: 1504-1512https://doi.org/10.1016/j.ijrobp.2016.03.018
- Early tumor response prediction for lung cancer patients using novel longitudinal pattern features from sequential PET/CT image scans.Phys Medica. 2018; 54: 21-29https://doi.org/10.1016/j.ejmp.2018.09.003
International Commission on Radiation Units: Prescribing, Recording, and Reporting Photon Beam Therapy. Washington, DC, 1993. doi: 10.2307/3578862.
- Routine individualised patient dosimetry using electronic portal imaging devices.Radiother Oncol. 2007; 83: 65-75https://doi.org/10.1016/j.radonc.2007.03.003
- Response assessment using 18F-FDG PET early in the course of radiotherapy correlates with survival in advanced-stage non-small cell lung cancer.J Nucl Med. 2012; 53: 1514-1520https://doi.org/10.2967/jnumed.111.102566
- Beyond imaging: the promise of radiomics.Phys Medica. 2017; 38: 122-139https://doi.org/10.1016/j.ejmp.2017.05.071
- Fast level-set based image segmentation using coherent propagation.Med Phys. 2014; 41073501https://doi.org/10.1118/1.4881315
Wang C. Mia Lite Solution. http://www.mia-solution.com/products.html.
Medical Image Processing and Visualization. https://www.mevislab.de/.
Insight Segmentation and Registration Toolkit (ITK). https://itk.org/.
- The cancer imaging archive (TCIA): maintaining and operating a public information repository.J Digit Imaging. 2013; 26: 1045-1057https://doi.org/10.1007/s10278-013-9622-7
- Evaluating variability in tumor measurements from same-day repeat CT scans of patients with non-small cell lung cancer.Radiology. 2009; 252: 263-272https://doi.org/10.1148/radiol.2522081593
Zhao B, James LP, Moskowitz CS, Guo P, Ginsberg MS. Data From RIDER_Lung CT. Cancer Imaging Arch.https://wiki.cancerimagingarchive.net/display/Public/RIDER+Lung+CT#b2e97b8e89914ca5acf418cd47bb7386.
Zwanenburg A, Leger S, Vallières M, Löck S, Initiative for the IBS. Image biomarker standardisation initiative 2016. arXiv: 1612.07003.
- A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities.Phys Med Biol. 2015; 60: 5471-5496https://doi.org/10.1088/0031-9155/60/14/5471
- Evaluating tumor response of non-small cell lung cancer patients with 18F-fludeoxyglucose positron emission tomography: potential for treatment individualization.Int J Radiat Oncol. 2015; 91: 376-384https://doi.org/10.1016/j.ijrobp.2014.10.012
Lin LI. A Concordance Correlation Coefficient to Evaluate Reproducibility Published by : International Biometric Society Stable URL : http://www.jstor.org/stable/2532051. 1989;45:255–68.
- Floating search methods in feature selection.Pattern Recognit Lett. 1994; 15: 1119-1125https://doi.org/10.1016/0167-8655(94)90127-9
- Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction.Med Image Anal. 2016; 32: 257-268https://doi.org/10.1016/j.media.2016.05.007
- Robust feature selection to predict tumor treatment outcome.Artif Intell Med. 2015; 64: 195-204https://doi.org/10.1016/j.artmed.2015.07.002
- Radiomic-based pathological response prediction from primary tumors and lymph nodes in NSCLC.J Thorac Oncol. 2017; 12: 467-476https://doi.org/10.1016/j.jtho.2016.11.2226
- Estimating the confidence interval for prediction errors of support vector machine classifiers.J Mach Learn Res. 2008; 9: 521-540
Vallières M. MATLAB programming tools for radiomics analysis. https://github.com/mvallieres/radiomics.
- Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach.Biometrics. 1988; 44: 837https://doi.org/10.2307/2531595
- Early variation of FDG-PET radiomics features in NSCLC is related to overall survival – the “delta radiomics” concept.Radiother Oncol. 2016; 118: S20-S21https://doi.org/10.1016/S0167-8140(16)30042-1
- 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; 281https://doi.org/10.1148/radiol.2016152234
- Applicability of a prognostic CT-based radiomic signature model trained on stage I-III non-small cell lung cancer in stage IV non-small cell lung cancer.Lung Cancer. 2018; 124: 6-11https://doi.org/10.1016/j.lungcan.2018.07.023
- Prediction of disease-free survival by the PET/CT radiomic signature in non-small cell lung cancer patients undergoing surgery.Eur J Nucl Med Mol Imaging. 2018; 45: 207-217https://doi.org/10.1007/s00259-017-3837-7
- 18F-fluorodeoxyglucose positron-emission tomography (FDG-PET)-Radiomics of metastatic lymph nodes and primary tumor in non-small cell lung cancer (NSCLC) – a prospective externally validated study.PLoS ONE. 2018; 13e0192859https://doi.org/10.1371/journal.pone.0192859
- Prognostic value of combining a quantitative image feature from positron emission tomography with clinical factors in oligometastatic non-small cell lung cancer.Radiother Oncol. 2018; 126: 362-367https://doi.org/10.1016/j.radonc.2017.11.006
- Prognostic value and reproducibility of pretreatment CT texture features in stage III non-small cell lung cancer.Int J Radiat Oncol Biol Physicsy Biol Phys. 2014; 9: 834-842https://doi.org/10.1016/j.ijrobp.2014.07.020
- Early change in metabolic tumor heterogeneity during chemoradiotherapy and its prognostic value for patients with locally advanced non-small cell lung cancer.PLoS ONE. 2016; 11https://doi.org/10.1371/journal.pone.0157836
- Non-small cell lung cancer treated with erlotinib: heterogeneity of 18F-FDG uptake at PET—association with treatment response and prognosis.Radiology. 2015; 276: 883-893https://doi.org/10.1148/radiol.2015141309
- Characterization of PET/CT images using texture analysis: the past, the present… any future?.Eur J Nucl Med Mol Imaging. 2017; 44: 151-165https://doi.org/10.1007/s00259-016-3427-0
- Tumour heterogeneity in non-small cell lung carcinoma assessed by CT texture analysis: a potential marker of survival.Eur Radiol. 2012; 22: 796-802https://doi.org/10.1007/s00330-011-2319-8
Article info
Publication history
Published online: March 27, 2019
Accepted:
March 21,
2019
Received in revised form:
February 12,
2019
Received:
October 27,
2018
Identification
Copyright
© 2019 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.
