Top

European Radiology

Published in:

01-08-2021 | Computed Tomography | Imaging Informatics and Artificial Intelligence

Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging

Authors: Hubert Beaumont, Antoine Iannessi, Anne-Sophie Bertrand, Jean Michel Cucchi, Olivier Lucidarme

Published in: European Radiology | Issue 8/2021

Abstract

Objectives

Following the craze for radiomic features (RF), their lack of reliability raised the question of the generalizability of classification models. Inter-site harmonization of images therefore becomes a central issue. We compared RF harmonization processing designed to detect liver diseases in CT images.

Methods

We retrospectively analyzed 76 multi-center portal CT series of non-diseased (NDL) and diseased liver (DL) patients. In each series, we positioned volumes of interest in spleen and liver, then extracted 9 RF (histogram and texture). We evaluated two RF harmonization approaches. First, in each series, we computed the Z-score of liver measurements based on those computed in the spleen. Second, we evaluated the ComBat method according to each imaging center; parameters were computed in the spleen and applied to the liver. We compared RF distributions and classification performances before/after harmonization. We classified NDL versus spleen and versus DL tissues.

Results

The RF distributions were all different between liver and spleen (p < 0.05). The Z-score harmonization outperformed for the detection of liver versus spleen: AUC = 93.1% (p < 0.001). For the detection of DL versus NDL, in a case/control setting, we found no differences between the harmonizations: mean AUC = 73.6% (p = 0.49). Using the whole datasets, the performances were improved using ComBat (p = 0.05) AUC = 82.4% and degraded with Z-score AUC = 67.4% (p = 0.008).

Conclusions

Data harmonization requires to first focus on data structuring to not degrade the performances of subsequent classifications. Liver tissue classification after harmonization of spleen-based RF is a promising strategy for improving the detection of DL tissue.

Key Points

• Variability of acquisition parameter makes radiomics of CT features non-reproducible.

• Data harmonization can help circumvent the inter-site variability of acquisition protocols.

• Inter-site harmonization must be carefully implemented and requires designing consistent data sets.

Available only for authorised users

Alic L, Niessen WJ, Veenland JF (2014) Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review. PLoS One 9:e110300. https://doi.org/10.1371/journal.pone.0110300CrossRefPubMedPubMedCentral

Traverso A, Wee L, Dekker A, Gillies R (2018) Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys 102:1143–1158. https://doi.org/10.1016/j.ijrobp.2018.05.053CrossRefPubMedPubMedCentral

Lubner MG, Smith AD, Sandrasegaran K, Sahani DV, Pickhardt PJ (2017) CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics 37:1483–1503. https://doi.org/10.1148/rg.2017170056

Hatt M, Tixier F, Pierce L, Kinahan PE, Le Rest CC, Visvikis D (2017) Characterization of PET/CT images using texture analysis: the past, the present… any future? Eur J Nucl Med Mol Imaging 44:151–165. https://doi.org/10.1007/s00259-016-3427-0

Eisenhauer EA, Therasse P, Bogaerts J et al (2009) New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer 45:228–247. https://doi.org/10.1016/j.ejca.2008.10.026CrossRef

Kumar V, Gu Y, Basu S et al (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30:1234–1248. https://doi.org/10.1016/j.mri.2012.06.010CrossRefPubMedPubMedCentral

O’Connor JPB, Aboagye EO, Adams JE et al (2017) Imaging biomarker roadmap for cancer studies. Nat Rev Clin Oncol 14:169–186. https://doi.org/10.1038/nrclinonc.2016.162CrossRefPubMed

Kalendralis P, Traverso A, Shi Z et al (2019) Multicenter CT phantoms public dataset for radiomics reproducibility tests. Med Phys 46:1512–1518. https://doi.org/10.1002/mp.13385CrossRefPubMed

Mackin D, Fave X, Zhang L et al (2015) Measuring CT scanner variability of radiomics features. Invest Radiol 50:757–765. https://doi.org/10.1097/RLI.0000000000000180CrossRefPubMedPubMedCentral

10.

Simon P, Uma V (2018) Review of texture descriptors for texture classification. Data Eng Intell Comp 542:159–176. https://doi.org/10.1007/978-981-10-3223-3_15CrossRef

11.

Ger RB, Zhou S, Chi PCM et al (2018) Comprehensive investigation on controlling for CT imaging variabilities in radiomics studies. Sci Rep 8:1–14. https://doi.org/10.1038/s41598-018-31509-zCrossRef

12.

Berenguer R, Del Rosario Pastor-Juan M, Canales-Vázquez J et al (2018) Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 288:407–415. https://doi.org/10.1148/radiol.2018172361CrossRefPubMed

13.

Johnson WE, Li C, Rabinovic A (2007) Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8:118–127. https://doi.org/10.1093/biostatistics/kxj037CrossRefPubMed

14.

Orlhac F, Frouin F, Nioche C, Ayache N, Buvat I (2019) Validation of a method to compensate multicenter effects affecting CT radiomics. Radiology 291:53–59. https://doi.org/10.1148/radiol.2019182023

15.

Nioche C, Orlhac F, Boughdad S et al (2018) Lifex: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res 78:4786–4789. https://doi.org/10.1158/0008-5472.CAN-18-0125CrossRefPubMed

16.

Orlhac F, Soussan M, Chouahnia K, Martinod E, Buvat I (2015) 18F-FDG PET-derived textural indices reflect tissue-specific uptake pattern in non-small cell lung cancer. PLoS One 10:1–16. https://doi.org/10.1371/journal.pone.0145063

17.

Caramella C, Allorant A, Orlhac F et al (2018) Can we trust the calculation of texture indices of CT images? A phantom study. Med Phys 45:1529–1536. https://doi.org/10.1002/mp.12809CrossRefPubMed

18.

Burke Ó, Benton S, Szafranski P et al (2016) Extending the scope of pooled analyses of individual patient biomarker data from heterogeneous laboratory platforms and cohorts using merging algorithms. Pregnancy Hypertens 6:53–59. https://doi.org/10.1016/j.preghy.2015.12.002CrossRefPubMed

19.

Mergo PJ, Ros PR, Buetow PC, Buck JL (1994) Diffuse disease of the liver: radiologic-pathologic correlation. Radiographics 14:1291–1307. https://doi.org/10.1148/radiographics.14.6.7855342CrossRefPubMed

20.

Ahmed AM, Ebid ME, Ajlan AM, Al-Mallah MH (2017) Low-dose attenuation correction in diagnosis of non-alcoholic fatty liver disease. Abdom Radiol (NY) 42:2454–2459. https://doi.org/10.1007/s00261-017-1166-8CrossRef

21.

Team RDC (2011) R: a language and environment for statistical computing. R Found Stat Comput 1:409

22.

Nygaard V, Rødland EA, Hovig E (2016) Methods that remove batch effects while retaining group differences may lead to exaggerated confidence in downstream analyses. Biostatistics 17:29–39. https://doi.org/10.1093/biostatistics/kxv027CrossRefPubMed

23.

Perrin T, Midya A, Yamashita R et al (2018) Short-term reproducibility of radiomic features in liver parenchyma and liver malignancies on contrast-enhanced CT imaging. Abdom Radiol (NY) 43:3271–3278. https://doi.org/10.1007/s00261-018-1600-6CrossRef

24.

Brenet Defour L, Mulé S, Tenenhaus A et al (2019) Hepatocellular carcinoma: CT texture analysis as a predictor of survival after surgical resection. Eur Radiol 29:1231–1239. https://doi.org/10.1007/s00330-018-5679-5CrossRefPubMed

25.

Chen S, Zhu Y, Liu Z, Liang C (2017) Texture analysis of baseline multiphasic hepatic computed tomography images for the prognosis of single hepatocellular carcinoma after hepatectomy: A retrospective pilot study. Eur J Radiol 90:198–204. https://doi.org/10.1016/j.ejrad.2017.02.035CrossRefPubMed

26.

Park HJ, Kim JH, Choi S et al (2017) Prediction of therapeutic response of hepatocellular carcinoma to transcatheter arterial chemoembolization based on pretherapeutic dynamic CT and textural findings. AJR Am J Roentgenol 209:W211–W220. https://doi.org/10.2214/AJR.16.17398CrossRefPubMed

27.

Chang C-C, Chen H-H, Chang Y-C et al (2017) Computer-aided diagnosis of liver tumors on computed tomography images. Comput Methods Programs Biomed 145:45–51. https://doi.org/10.1016/j.cmpb.2017.04.008CrossRefPubMed

28.

Reinert CP, Kloth C, Fritz J, Nikolaoua K, Horgera M (2018) Discriminatory CT-textural features in splenic infiltration of lymphoma versus splenomegaly in liver cirrhosis versus normal spleens in controls and evaluation of their role for longitudinal lymphoma monitoring. Eur J Radiol 104:129–135. https://doi.org/10.1016/j.ejrad.2018.05.010

29.

Cozzi L, Dinapoli N, Fogliata A et al (2017) Radiomics based analysis to predict local control and survival in hepatocellular carcinoma patients treated with volumetric modulated arc therapy. BMC Cancer 17:1–10. https://doi.org/10.1186/s12885-017-3847-7CrossRef

30.

Beckers RCJ, Trebeschi S, Maas M et al (2018) CT texture analysis in colorectal liver metastases and the surrounding liver parenchyma and its potential as an imaging biomarker of disease aggressiveness, response and survival. Eur J Radiol 102:15–21. https://doi.org/10.1016/j.ejrad.2018.02.031CrossRefPubMed

31.

Lee SJ, Zea R, Kim DH, Lubner MG, Deming DA, Pickhardt PJ (2018) CT texture features of liver parenchyma for predicting development of metastatic disease and overall survival in patients with colorectal cancer. Eur Radiol 28:1520–1528. https://doi.org/10.1007/s00330-017-5111-6

Title: Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging
Authors: Hubert Beaumont
Antoine Iannessi
Anne-Sophie Bertrand
Jean Michel Cucchi
Olivier Lucidarme
Publication date: 01-08-2021
Publisher: Springer Berlin Heidelberg
Keywords: Computed Tomography
Computed Tomography
Published in: European Radiology / Issue 8/2021
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-020-07641-8

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Please log in to get access to this content

Other articles of this Issue 8/2021

Liver surface nodularity: a novel predictor of post-hepatectomy liver failure in patients with colorectal liver metastases following chemotherapy

Brain MRI radiomics analysis may predict poor psychomotor outcome in preterm neonates

Predicting the outcome of asymptomatic univesicular liver hydatids: diagnostic accuracy of unenhanced CT

Vascular Ehlers–Danlos syndrome (vEDS): CT and histologic findings of pleural and lung parenchymal damage

Training opportunities of artificial intelligence (AI) in radiology: a systematic review

Deep learning–based metal artefact reduction in PET/CT imaging