Stability of radiomic features in CT perfusion maps

被引:53
作者
Bogowicz, M. [1 ]
Riesterer, O. [1 ]
Bundschuh, R. A. [4 ]
Veit-Haibach, P. [2 ,3 ]
Huellner, M. [2 ]
Studer, G. [1 ]
Stieb, S. [1 ]
Glatz, S. [1 ]
Pruschy, M. [1 ]
Guckenberger, M. [1 ]
Tanadini-Lang, S. [1 ]
机构
[1] Univ Zurich, Univ Zurich Hosp, Dept Radiat Oncol, Ramistr 100, CH-8091 Zurich, Switzerland
[2] Univ Zurich, Univ Zurich Hosp, Dept Nucl Med, Ramistr 100, CH-8091 Zurich, Switzerland
[3] Univ Zurich, Univ Zurich Hosp, Dept Diagnost & Intervent Radiol, Ramistr 100, CH-8091 Zurich, Switzerland
[4] Univ Hosp Bonn, Dept Nucl Med, Sigmund Freud Str 25, D-53127 Bonn, Germany
关键词
radiomics; CT perfusion; radiomic features stability; FDG-PET RADIOMICS; CELL LUNG-CANCER; TEXTURAL FEATURES; MICROVESSEL DENSITY; TUMOR PHENOTYPE; HETEROGENEITY; PARAMETERS; IMPACT; HEAD; RECONSTRUCTION;
D O I
10.1088/1361-6560/61/24/8736
中图分类号
R318 [生物医学工程];
学科分类号
100103 [病原生物学];
摘要
This study aimed to identify a set of stable radiomic parameters in CT perfusion (CTP) maps with respect to CTP calculation factors and image discretization, as an input for future prognostic models for local tumor response to chemo-radiotherapy. Pre-treatment CTP images of eleven patients with oropharyngeal carcinoma and eleven patients with non-small cell lung cancer (NSCLC) were analyzed. 315 radiomic parameters were studied per perfusion map (blood volume, blood flow and mean transit time). Radiomics robustness was investigated regarding the potentially standardizable (image discretization method, Hounsfield unit (HU) threshold, voxel size and temporal resolution) and non-standardizable (artery contouring and noise threshold) perfusion calculation factors using the intraclass correlation (ICC). To gain added value for our model radiomic parameters correlated with tumor volume, a well-known predictive factor for local tumor response to chemo-radiotherapy, were excluded from the analysis. The remaining stable radiomic parameters were grouped according to inter-parameter Spearman correlations and for each group the parameter with the highest ICC was included in the final set. The acceptance level was 0.9 and 0.7 for the ICC and correlation, respectively. The image discretization method using fixed number of bins or fixed intervals gave a similar number of stable radiomic parameters (around 40%). The potentially standardizable factors introduced more variability into radiomic parameters than the non-standardizable ones with 56-98% and 43-58% instability rates, respectively. The highest variability was observed for voxel size (instability rate >97% for both patient cohorts). Without standardization of CTP calculation factors none of the studied radiomic parameters were stable. After standardization with respect to non-standardizable factors ten radiomic parameters were stable for both patient cohorts after correction for inter-parameter correlations. Voxel size, image discretization, HU threshold and temporal resolution have to be standardized to build a reliable predictive model based on CTP radiomics analysis.
引用
收藏
页码:8736 / 8749
页数:14
相关论文
共 51 条
[1]
Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J].
Aerts, Hugo J. W. L. ;
Velazquez, Emmanuel Rios ;
Leijenaar, Ralph T. H. ;
Parmar, Chintan ;
Grossmann, Patrick ;
Cavalho, Sara ;
Bussink, Johan ;
Monshouwer, Rene ;
Haibe-Kains, Benjamin ;
Rietveld, Derek ;
Hoebers, Frank ;
Rietbergen, Michelle M. ;
Leemans, C. Rene ;
Dekker, Andre ;
Quackenbush, John ;
Gillies, Robert J. ;
Lambin, Philippe .
NATURE COMMUNICATIONS, 2014, 5
[2]
TEXTURAL FEATURES CORRESPONDING TO TEXTURAL PROPERTIES [J].
AMADASUN, M ;
KING, R .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1989, 19 (05) :1264-1274
[3]
[Anonymous], 2011, INT J COMPUT TECHNOL
[4]
The Effect of Small Tumor Volumes on Studies of Intratumoral Heterogeneity of Tracer Uptake [J].
Brooks, Frank J. ;
Grigsby, Perry W. .
JOURNAL OF NUCLEAR MEDICINE, 2014, 55 (01) :37-42
[5]
Lung texture in serial thoracic CT scans: Assessment of change introduced by image registration [J].
Cunliffe, Alexandra R. ;
Al-Hallaq, Hania A. ;
Labby, Zacariah E. ;
Pelizzari, Charles A. ;
Straus, Christopher ;
Sensakovic, William F. ;
Ludwig, Michelle ;
Armato, Samuel G., III .
MEDICAL PHYSICS, 2012, 39 (08) :4679-4690
[6]
Duda D, 2013, LECT NOTES COMPUT SC, V8104, P96, DOI 10.1007/978-3-642-40925-7_10
[7]
Deconvolution-Based CT and MR Brain Perfusion Measurement: Theoretical Model Revisited and Practical Implementation Details [J].
Fieselmann, Andreas ;
Kowarschik, Markus ;
Ganguly, Arundhuti ;
Hornegger, Joachim ;
Fahrig, Rebecca .
INTERNATIONAL JOURNAL OF BIOMEDICAL IMAGING, 2011, 2011
[8]
Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters [J].
Galavis, Paulina E. ;
Hollensen, Christian ;
Jallow, Ngoneh ;
Paliwal, Bhudatt ;
Jeraj, Robert .
ACTA ONCOLOGICA, 2010, 49 (07) :1012-1016
[9]
Colorectal Tumor Vascularity: Quantitative Assessment with Multidetector CT-Do Tumor Perfusion Measurements Reflect Angiogenesis? [J].
Goh, Vicky ;
Halligan, Steve ;
Daley, Frances ;
Wellsted, David M. ;
Guenther, Thomas ;
Bartram, Clive I. .
RADIOLOGY, 2008, 249 (02) :510-517
[10]
TEXTURAL FEATURES FOR IMAGE CLASSIFICATION [J].
HARALICK, RM ;
SHANMUGAM, K ;
DINSTEIN, I .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1973, SMC3 (06) :610-621