Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer - PubMed (original) (raw)
Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer
Chintan Parmar et al. Sci Rep. 2015.
Abstract
Radiomics provides a comprehensive quantification of tumor phenotypes by extracting and mining large number of quantitative image features. To reduce the redundancy and compare the prognostic characteristics of radiomic features across cancer types, we investigated cancer-specific radiomic feature clusters in four independent Lung and Head &Neck (H) cancer cohorts (in total 878 patients). Radiomic features were extracted from the pre-treatment computed tomography (CT) images. Consensus clustering resulted in eleven and thirteen stable radiomic feature clusters for Lung and H cancer, respectively. These clusters were validated in independent external validation cohorts using rand statistic (Lung RS = 0.92, p < 0.001, H RS = 0.92, p < 0.001). Our analysis indicated both common as well as cancer-specific clustering and clinical associations of radiomic features. Strongest associations with clinical parameters: Prognosis Lung CI = 0.60 ± 0.01, Prognosis H CI = 0.68 ± 0.01; Lung histology AUC = 0.56 ± 0.03, Lung stage AUC = 0.61 ± 0.01, H HPV AUC = 0.58 ± 0.03, H stage AUC = 0.77 ± 0.02. Full utilization of these cancer-specific characteristics of image features may further improve radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor phenotypic characteristics in clinical practice.
Figures
Figure 1
(a) Radiomic analysis overview: For both Lung and H & N cancer datasets, we extracted radiomic features from pre-treatment CT images. Cluster analysis was performed on the feature data. (b) Datasets overview: Four independent radiomic cohorts of Lung and Head & Neck cancer were included in the analysis. Lung1 and HN1 were used for training; Lung2 and HN2 were used for validation.
Figure 2. Heatmap showing the prognostic performance of radiomic features in Lung2 and HN2 cohorts.
Prognostic performance was evaluated using the concordance index (CI). Note that a large number of features are prognostic in both cancer types. However, also a large number of features are cancer-type specific, e.g. prognostic only in Lung or only in H & N cancer.
Figure 3. Heatmaps for radiomic features of Lung and H & N training cohorts ordered with respect to the obtained Lung and H & N clusters.
(a–b) Cluster consensus maps of Lung cancer (11 clusters) and H & N cancer (13 clusters) cohorts. (c–d) Radiomic feature expressions of Lung and H & N radiomic clusters. (e–f) Clinical relevance (CI & AUC) of radiomic clusters of Lung and H & N cancer.
Figure 4. Heatmap depicting cluster overlap and clinical relevance (CI & AUC).
Center matrix in green & white color represents the overlap (Jaccard index) between the clusters of Lung (rows) and H & N (columns) radiomic cohorts. Top and left side panels in blue & white color depicts the average CI & AUC of the corresponding Lung and H & N radiomic clusters.
Similar articles
- CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer.
Huynh E, Coroller TP, Narayan V, Agrawal V, Hou Y, Romano J, Franco I, Mak RH, Aerts HJ. Huynh E, et al. Radiother Oncol. 2016 Aug;120(2):258-66. doi: 10.1016/j.radonc.2016.05.024. Epub 2016 Jun 10. Radiother Oncol. 2016. PMID: 27296412 - Integrative nomogram of CT imaging, clinical, and hematological features for survival prediction of patients with locally advanced non-small cell lung cancer.
Wang L, Dong T, Xin B, Xu C, Guo M, Zhang H, Feng D, Wang X, Yu J. Wang L, et al. Eur Radiol. 2019 Jun;29(6):2958-2967. doi: 10.1007/s00330-018-5949-2. Epub 2019 Jan 14. Eur Radiol. 2019. PMID: 30643940 - Machine Learning methods for Quantitative Radiomic Biomarkers.
Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJWL. Parmar C, et al. Sci Rep. 2015 Aug 17;5:13087. doi: 10.1038/srep13087. Sci Rep. 2015. PMID: 26278466 Free PMC article. - Radiomics in Head and Neck Cancer: Extracting Valuable Information from Data beyond Recognition.
Scheckenbach K, Colter L, Wagenmann M. Scheckenbach K, et al. ORL J Otorhinolaryngol Relat Spec. 2017;79(1-2):65-71. doi: 10.1159/000455704. Epub 2017 Feb 24. ORL J Otorhinolaryngol Relat Spec. 2017. PMID: 28231582 Review. - Radiomics and its emerging role in lung cancer research, imaging biomarkers and clinical management: State of the art.
Lee G, Lee HY, Park H, Schiebler ML, van Beek EJR, Ohno Y, Seo JB, Leung A. Lee G, et al. Eur J Radiol. 2017 Jan;86:297-307. doi: 10.1016/j.ejrad.2016.09.005. Epub 2016 Sep 10. Eur J Radiol. 2017. PMID: 27638103 Review.
Cited by
- Disparities in the diagnostic efficacy of radiomics models in predicting various degrees of cognitive impairment in patients with cerebral small vessel disease.
Huang B, Zheng W, Mu R, Yang P, Li X, Liu F, Qin X, Zhu X. Huang B, et al. BMC Med Imaging. 2024 Sep 27;24(1):257. doi: 10.1186/s12880-024-01431-0. BMC Med Imaging. 2024. PMID: 39333913 Free PMC article. - Pretreatment Spatially Aware Magnetic Resonance Imaging Radiomics Can Predict Distant Brain Metastases (DBMs) After Stereotactic Radiosurgery/Radiation Therapy (SRS/SRT).
Bae J, Mani K, Zabrocka E, Cattell R, O'Grady B, Payne D, Roberson J, Ryu S, Prasanna P. Bae J, et al. Adv Radiat Oncol. 2024 Feb 6;9(5):101457. doi: 10.1016/j.adro.2024.101457. eCollection 2024 May. Adv Radiat Oncol. 2024. PMID: 38550363 Free PMC article. - Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging.
Mahajan A, Kania V, Agarwal U, Ashtekar R, Shukla S, Patil VM, Noronha V, Joshi A, Menon N, Kaushal RK, Rane S, Chougule A, Vaidya S, Kaluva K, Prabhash K. Mahajan A, et al. Cancers (Basel). 2024 Mar 12;16(6):1130. doi: 10.3390/cancers16061130. Cancers (Basel). 2024. PMID: 38539465 Free PMC article. - Segmentation of Variants of Nuclei on Whole Slide Images by Using Radiomic Features.
Sheikh TS, Cho M. Sheikh TS, et al. Bioengineering (Basel). 2024 Mar 4;11(3):252. doi: 10.3390/bioengineering11030252. Bioengineering (Basel). 2024. PMID: 38534526 Free PMC article. - Research on multi-model imaging machine learning for distinguishing early hepatocellular carcinoma.
Ma Y, Gong Y, Qiu Q, Ma C, Yu S. Ma Y, et al. BMC Cancer. 2024 Mar 21;24(1):363. doi: 10.1186/s12885-024-12109-9. BMC Cancer. 2024. PMID: 38515051 Free PMC article.
References
- Chung C. H., Levy S., Chaurand P. & Carbone D. P. Genomics and proteomics: emerging technologies in clinical cancer research. Crit. Rev. Oncol. Hemat. 61, 1–25 (2007). - PubMed
- Buckler A. J., Bresolin L., Dunnick N. R. & Sullivan D. C. A collaborative enterprise for multi-stakeholder participation in the advancement of quantitative imaging. Radiology 258, 906–914 (2011). - PubMed
Publication types
MeSH terms
Substances
Grants and funding
- U01 CA143062/CA/NCI NIH HHS/United States
- U01 CA190234/CA/NCI NIH HHS/United States
- U01 CA 143062-01/CA/NCI NIH HHS/United States
- U01 CA 190234-01/CA/NCI NIH HHS/United States
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical