{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T09:14:04Z","timestamp":1790932444305,"version":"4.1.0"},"reference-count":36,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2020R1F1A1077320"],"award-info":[{"award-number":["NRF-2020R1F1A1077320"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>We assessed the feasibility of using deep learning-based image harmonization to improve the reproducibility of radiomics features in abdominal CT scans. In CT imaging, harmonization adjusts images from different institutions to ensure consistency despite variations in scanners and acquisition protocols. This process is essential because such differences can lead to variability in radiomics features, affecting reproducibility and accuracy. Harmonizing images minimizes these inconsistencies, supporting more reliable and clinically applicable results across diverse settings. A pre-trained harmonization algorithm was applied to 63 dual-energy abdominal CT images, which were reconstructed into four different types, and 10 regions of interest (ROIs) were analyzed. From the original 455 radiomics features per ROI, 387 were used after excluding redundant features. Reproducibility was measured using the intraclass correlation coefficient (ICC), with a threshold of ICC \u2265 0.85 indicating acceptable reproducibility. The region-based analysis revealed significant improvements in reproducibility post-harmonization, especially in vessel features, which increased from 14% to 69%. Other regions, including the spleen, kidney, muscle, and liver parenchyma, also saw notable improvements, although air reproducibility slightly decreased from 95% to 94%, impacting only a few features. In patient-based analysis, reproducible features increased from 18% to 65%, with an average of 179 additional reproducible features per patient after harmonization. These results demonstrate that deep learning-based harmonization can significantly enhance the reproducibility of radiomics features in abdominal CT, offering promising potential for advancing radiomics development and its clinical applications.<\/jats:p>","DOI":"10.3390\/bioengineering11121212","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T05:43:43Z","timestamp":1733118223000},"page":"1212","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Enhancing Radiomics Reproducibility: Deep Learning-Based Harmonization of Abdominal Computed Tomography (CT) Images"],"prefix":"10.3390","volume":"11","author":[{"given":"Seul Bi","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2104-5905","authenticated-orcid":false,"given":"Youngtaek","family":"Hong","sequence":"additional","affiliation":[{"name":"CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9820-3030","authenticated-orcid":false,"given":"Yeon Jin","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"},{"name":"Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9791-9555","authenticated-orcid":false,"given":"Dawun","family":"Jeong","sequence":"additional","affiliation":[{"name":"CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul 03080, Republic of Korea"},{"name":"Brain Korea 21 PLUS Project for Medical Science, Yonsei University, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jina","family":"Lee","sequence":"additional","affiliation":[{"name":"CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul 03080, Republic of Korea"},{"name":"Brain Korea 21 PLUS Project for Medical Science, Yonsei University, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5937-7238","authenticated-orcid":false,"given":"Jae Won","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2777-3444","authenticated-orcid":false,"given":"Jae Yeon","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-0640","authenticated-orcid":false,"given":"Seunghyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"},{"name":"Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Hun","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"},{"name":"Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jung-Eun","family":"Cheon","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"},{"name":"Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"},{"name":"Institute of Radiation Medicine, Seoul National University Medical Research Center, 103 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,11,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: Extracting more information from medical images using advanced feature analysis","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur. J. Cancer"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/0962280214537332","article-title":"Introduction to metrology series","volume":"24","author":"Sullivan","year":"2015","journal-title":"Stat. Methods Med Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.3348\/kjr.2018.0070","article-title":"Reproducibility and generalizability in radiomics modeling: Possible strategies in radiologic and statistical perspectives","volume":"20","author":"Park","year":"2019","journal-title":"Korean J. Radiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1097\/RLI.0000000000000834","article-title":"Repeatability and reproducibility of computed tomography radiomics for pulmonary nodules: A multicenter phantom study","volume":"57","author":"Peng","year":"2022","journal-title":"Investig. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Escudero Sanchez, L., Rundo, L., Gill, A.B., Hoare, M., Mendes Serrao, E., and Sala, E. (2021). Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-87598-w"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1002\/mp.12123","article-title":"Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels","volume":"44","author":"Zhang","year":"2017","journal-title":"Med. Phys."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1148\/radiol.2018172361","article-title":"Radiomics of CT features may be nonreproducible and redundant: Influence of CT acquisition parameters","volume":"288","author":"Berenguer","year":"2018","journal-title":"Radiology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1148\/radiol.2019181960","article-title":"Deep learning\u2013based image conversion of CT reconstruction kernels improves radiomics reproducibility for pulmonary nodules or masses","volume":"292","author":"Choe","year":"2019","journal-title":"Radiology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1097\/RLI.0000000000000180","article-title":"Measuring computed tomography scanner variability of radiomics features","volume":"50","author":"Mackin","year":"2015","journal-title":"Investig. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1148\/radiol.2019190928","article-title":"Reproducibility of CT radiomic features within the same patient: Influence of radiation dose and CT reconstruction settings","volume":"293","author":"Meyer","year":"2019","journal-title":"Radiology"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3054","DOI":"10.1002\/mp.14173","article-title":"Multicenter evaluation of MRI-based radiomic features: A phantom study","volume":"47","author":"Rai","year":"2020","journal-title":"Med. Phys."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1097\/RLI.0000000000000839","article-title":"Deep learning-based image conversion improves the reproducibility of computed tomography radiomics features: A phantom study","volume":"57","author":"Lee","year":"2022","journal-title":"Investig. Radiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"294","DOI":"10.3348\/kjr.2022.0588","article-title":"Deep learning-based computed tomography image standardization to improve generalizability of deep learning-based hepatic segmentation","volume":"24","author":"Lee","year":"2023","journal-title":"Korean J. Radiol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., and Wang, Z. (2016, January 27\u201330). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Schonfeld, E., Schiele, B., and Khoreva, A. (2020, January 13\u201319). A u-net based discriminator for generative adversarial networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00823"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"27648","DOI":"10.1109\/ACCESS.2024.3366989","article-title":"Improving the Reproducibility of Computed Tomography Radiomic Features Using an Enhanced Hierarchical Feature Synthesis Network","volume":"12","author":"Jeong","year":"2024","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational Radiomics System to Decode the Radiographic Phenotype","volume":"77","author":"Fedorov","year":"2017","journal-title":"Cancer Res."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhao, B., Tan, Y., Tsai, W.-Y., Qi, J., Xie, C., Lu, L., and Schwartz, L.H. (2016). Reproducibility of radiomics for deciphering tumor phenotype with imaging. Sci. Rep., 6.","DOI":"10.1038\/srep23428"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mali, S.A., Ibrahim, A., Woodruff, H.C., Andrearczyk, V., M\u00fcller, H., Primakov, S., Salahuddin, Z., Chatterjee, A., and Lambin, P. (2021). Making radiomics more reproducible across scanner and imaging protocol variations: A review of harmonization methods. J. Pers. Med., 11.","DOI":"10.3390\/jpm11090842"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"011020","DOI":"10.1117\/1.JMI.5.1.011020","article-title":"Influence of CT acquisition and reconstruction parameters on radiomic feature reproducibility","volume":"5","author":"Midya","year":"2018","journal-title":"J. Med. Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e13739","DOI":"10.1002\/acm2.13739","article-title":"Improving reproducibility and performance of radiomics in low-dose CT using cycle GANs","volume":"23","author":"Chen","year":"2022","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhang, C., Traverso, A., Zhovannik, I., Dekker, A., Wee, L., and Bermejo, I. (2021). Generative models improve radiomics reproducibility in low dose CTs: A simulation study. Phys. Med. Biol., 66.","DOI":"10.1088\/1361-6560\/ac16c0"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lee, J., Jeon, J., Hong, Y., Jeong, D., Jang, Y., Jeon, B., Baek, H.J., Cho, E., Shim, H., and Chang, H.-J. (2023). Generative adversarial network with radiomic feature reproducibility analysis for computed tomography denoising. Comput. Biol. Med., 159.","DOI":"10.1016\/j.compbiomed.2023.106931"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4431","DOI":"10.21037\/qims-21-86","article-title":"Radiomics Feature Reliability Assessed by Intraclass Correlation Coefficient: A Systematic Review","volume":"11","author":"Xue","year":"2021","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.jcmg.2016.12.003","article-title":"Use of imaging endpoints in clinical trials","volume":"10","author":"Gillam","year":"2017","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1007\/s00259-014-2961-x","article-title":"FDG PET\/CT: EANM procedure guidelines for tumour imaging: Version 2.0","volume":"42","author":"Boellaard","year":"2015","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"469","DOI":"10.2967\/jnumed.119.229724","article-title":"Experimental multicenter and multivendor evaluation of the performance of PET radiomic features using 3-dimensionally printed phantom inserts","volume":"61","author":"Pfaehler","year":"2020","journal-title":"J. Nucl. Med."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lee, H., Huang, C., Yune, S., Tajmir, S.H., Kim, M., and Do, S. (2019). Machine friendly machine learning: Interpretation of computed tomography without image reconstruction. Sci. Rep., 9.","DOI":"10.1038\/s41598-019-51779-5"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Le, E.P., Rundo, L., Tarkin, J.M., Evans, N.R., Chowdhury, M.M., Coughlin, P.A., Pavey, H., Wall, C., Zaccagna, F., and Gallagher, F.A. (2021). Assessing robustness of carotid artery CT angiography radiomics in the identification of culprit lesions in cerebrovascular events. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-82760-w"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.ymeth.2020.08.007","article-title":"Variability of computed tomography radiomics features of fibrosing interstitial lung disease: A test-retest study","volume":"188","author":"Prayer","year":"2021","journal-title":"Methods"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Shafiq-ul-Hassan, M., Latifi, K., Zhang, G., Ullah, G., Gillies, R., and Moros, E. (2018). Voxel size and gray level normalization of CT radiomic features in lung cancer. Sci. Rep., 8.","DOI":"10.1038\/s41598-018-28895-9"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4498","DOI":"10.1007\/s00330-017-4859-z","article-title":"The impact of image reconstruction settings on 18F-FDG PET radiomic features: Multi-scanner phantom and patient studies","volume":"27","author":"Shiri","year":"2017","journal-title":"Eur. Radiol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardization initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Da-Ano, R., Masson, I., Lucia, F., Dor\u00e9, M., Robin, P., Alfieri, J., Rousseau, C., Mervoyer, A., Reinhold, C., and Castelli, J. (2020). Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-66110-w"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, X., Xie, L., Dong, C., and Shan, Y. (2021, January 11\u201317). Real-esrgan: Training real-world blind super-resolution with pure synthetic data. Proceedings of the IEEE\/CVF International Conference on Computer Vision 2021, Montreal, BC, Canada.","DOI":"10.1109\/ICCVW54120.2021.00217"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/11\/12\/1212\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:43:16Z","timestamp":1760114596000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/11\/12\/1212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,30]]},"references-count":36,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["bioengineering11121212"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering11121212","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,30]]}}}