Feature Robustness and Diagnostic Capabilities of Convolutional Neural Networks Against Radiomics Features in Computed Tomography Imaging.
Journal
Investigative radiology
ISSN: 1536-0210
Titre abrégé: Invest Radiol
Pays: United States
ID NLM: 0045377
Informations de publication
Date de publication:
01 03 2022
01 03 2022
Historique:
pubmed:
16
9
2021
medline:
15
4
2022
entrez:
15
9
2021
Statut:
ppublish
Résumé
Imaging phantoms were scanned twice on 3 computed tomography scanners from 2 different manufactures with varying tube voltages and currents. Phantoms were segmented, and features were extracted using PyRadiomics and a pretrained CNN. After standardization the concordance correlation coefficient (CCC), mean feature variance, feature range, and the coefficient of variant were calculated to assess feature robustness. In addition, the cosine similarity was calculated for the vectorized activation maps for an exemplary phantom. For the in vivo comparison, the radiomics and CNN features of 30 patients with hepatocellular carcinoma (HCC) and 30 patients with hepatic colon carcinoma metastasis were compared. In total, 851 radiomics features and 256 CNN features were extracted for each phantom. For all phantoms, the global CCC of the CNN features was above 98%, whereas the highest CCC for the radiomics features was 36%. The mean feature variance and feature range was significantly lower for the CNN features. Using a coefficient of variant ≤0.2 as a threshold to define robust features and averaging across all phantoms 346 of 851 (41%) radiomics features and 196 of 256 (77%) CNN features were found to be robust. The cosine similarity was greater than 0.98 for all scanner and parameter variations. In the retrospective analysis, 122 of the 256 CNN (49%) features showed significant differences between HCC and hepatic colon metastasis. Convolutional neural network features were more stable compared with radiomics features against technical variations. Moreover, the possibility of tumor entity differentiation based on CNN features was shown. Combined with visualization methods, CNN features are expected to increase reproducibility of quantitative image representations. Further studies are warranted to investigate the impact of feature stability on radiological image-based prediction of clinical outcomes.
Identifiants
pubmed: 34524173
doi: 10.1097/RLI.0000000000000827
pii: 00004424-202203000-00005
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
171-177Informations de copyright
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: none declared.
Références
Morin O, Vallières M, Jochems A, et al. A deep look into the future of quantitative imaging in oncology: a statement of working principles and proposal for change. Int J Radiat Oncol Biol Phys . 2018;102:1074–1082.
Zhang H, Mao Y, Chen X, et al. Magnetic resonance imaging radiomics in categorizing ovarian masses and predicting clinical outcome: a preliminary study. Eur Radiol . 2019;29:3358–3371.
Ji G-W, Zhu F-P, Zhang Y-D, et al. A radiomics approach to predict lymph node metastasis and clinical outcome of intrahepatic cholangiocarcinoma. Eur Radiol . 2019;29:3725–3735.
Mayerhoefer ME, Materka A, Langs G, et al. Introduction to radiomics. J Nucl Med . 2020;61:488–495.
Wang W, Cao K, Jin S, et al. Differentiation of renal cell carcinoma subtypes through MRI-based radiomics analysis. Eur Radiol . 2020;30:5738–5747.
Chu LC, Park S, Kawamoto S, et al. Utility of CT radiomics features in differentiation of pancreatic ductal adenocarcinoma from normal pancreatic tissue. Am J Roentgenol . 2019;213:349–357.
Aerts HJ, Grossmann P, Tan Y, et al. Defining a radiomic response phenotype: a pilot study using targeted therapy in NSCLC. Sci Rep . 2016;6:33860.
Kim H, Park CM, Lee M, et al. Impact of reconstruction algorithms on CT radiomic features of pulmonary tumors: analysis of intra- and inter-reader variability and inter-reconstruction algorithm variability. PLoS One . 2016;11:e0164924.
Berenguer R, Pastor-Juan MDR, Canales-Vázquez J, et al. Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology . 2018;288:407–415.
Lu L, Ehmke RC, Schwartz LH, et al. Assessing agreement between radiomic features computed for multiple CT imaging settings. PLoS One . 2016;11:e0166550.
Shafiq-ul-Hassan M, Zhang GG, Latifi K, et al. Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels. Med Phys . 2017;44:1050–1062.
Jimenez-Del-Toro O, Aberle C, Bach M, et al. The discriminative power and stability of radiomics features with computed tomography variations: task-based analysis in an anthropomorphic 3D-printed CT phantom. Investig Radiol . 2021.
Shukla-Dave A, Obuchowski NA, Chenevert TL, et al. Quantitative imaging biomarkers alliance (QIBA) recommendations for improved precision of DWI and DCE-MRI derived biomarkers in multicenter oncology trials. J Magn Reson Imaging . 2019;49:e101–e121.
Zwanenburg A, Abdalah M, Ashrafinia S, et al. Results from the image biomarker standardisation initiative. Radiother Oncol . 2018.
Sun Q, Lin X, Zhao Y, et al. Deep learning vs. radiomics for predicting axillary lymph node metastasis of breast cancer using ultrasound images: don't forget the peritumoral region. Front Oncol . 2020;10:53.
Truhn D, Schrading S, Haarburger C, et al. Radiomic versus convolutional neural networks analysis for classification of contrast-enhancing lesions at multiparametric breast MRI. Radiology . 2019;290:290–297.
Paul R, Shafiq-Ul Hassan M, Moros EG, et al. Deep feature stability analysis using CT images of a physical phantom across scanner manufacturers, cartridges, pixel sizes, and slice thickness. Tomography . 2020;6:250–260.
Baeßler B, Weiss K, Pinto Dos Santos D. Robustness and reproducibility of radiomics in magnetic resonance imaging: a phantom study. Investig Radiol . 2019;54:221–228.
Pieper S, Halle M, Kikinis R. 3D Slicer. 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821), 2004 . 2004;632–635.
Van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res . 2017;77:e104–e107.
Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge. Int J Comput Vis . 2015;115:211–252.
R Core Team. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. 2013.
Feng D. agRee: Various methods for measuring agreement. R Package Version 0.5-2. 2018.
Da-Ano R, Masson I, Lucia F, et al. Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies. Sci Rep . 2020;10:10248.
Hagiwara A, Fujita S, Ohno Y, et al. Variability and standardization of quantitative imaging: monoparametric to multiparametric quantification, radiomics, and artificial intelligence. Investig Radiol . 2020;55:601–616.
Ger RB, Zhou S, Chi PM, et al. Comprehensive investigation on controlling for CT imaging variabilities in radiomics studies. Sci Rep . 2018;8:13047.
Zwanenburg A, Vallières M, Abdalah MA, et al. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology . 2020;295:328–338.
Karmazyn B, Liang Y, Klahr P, et al. Effect of tube voltage on CT noise levels in different phantom sizes. Am J Roentgenol . 2013;200:1001–1005.
Achenbach S, Boehmer K, Pflederer T, et al. Influence of slice thickness and reconstruction kernel on the computed tomographic attenuation of coronary atherosclerotic plaque. J Cardiovasc Comput Tomogr . 2010;4:110–115.
Andrearczyk V, Depeursinge A, Müller H. Learning cross-protocol radiomics and deep feature standardization from CT images of texture phantoms. Proceedings Volume 10954, Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications . 2019.
Buckner C. Empiricism without magic: transformational abstraction in deep convolutional neural networks. Synthese . 2018;195:5339–5372.
O'Shea K, Nash R. An introduction to convolutional neural networks arXiv preprint arXiv:1511.08458. 2015.
Lee G, Lee HY, Park H, et al. Radiomics and its emerging role in lung cancer research, imaging biomarkers and clinical management: state of the art. Eur J Radiol . 2017;86:297–307.
Alhindi TJ, Kalra S, Ng KH, et al. Comparing LBP, HOG and deep features for classification of histopathology images. 2018 International Joint Conference on Neural Networks (IJCNN). IEEE . 2018;1–7.
Mason BR, Chatterjee D, Menias CO, et al. Encyclopedia of endometriosis: a pictorial rad-path review. Abdom Radiol (NY) . 2020;45:1587–1607.
Kuo MD, Yamamoto S. Next generation radiologic-pathologic correlation in oncology: Rad-Path 2.0. Am J Roentgenol . 2011;197:990–997.
He L, Huang Y, Ma Z, et al. Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule. Sci Rep . 2016;6:34921.
Liu R, Elhalawani H, Radwan Mohamed AS, et al. Stability analysis of CT radiomic features with respect to segmentation variation in oropharyngeal cancer. Clin Transl Radiat Oncol . 2020;21:11–18.
Wu Y, Qin X, Pan Y, et al. Convolution neural network based transfer learning for classification of flowers. 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP). IEEE . 2018;562–566.
Nonis F, Barbiero P, Cirrincione G, et al. Understanding abstraction in deep CNN: an application on facial emotion recognition. In: Esposito A, Faundez-Zanuy M, Carlo Morabito F, et al., eds. Progresses in Artificial Intelligence and Neural Systems . Singapore: Springer; 2021:281–290.