There was a mistake in Table 1 as published. “Test Set” was incorrectly written as “Training Set”. The numbers for the Test Set in Table 1 were mislabeled: low-grade (n = 79) and high-grade (n = 29). The corrected Table 1 appears below.

CharacteristicTraining set(n = 108)P-valueTest set(n = 46)P-valueLow-gradeHigh-gradeLow-gradeHigh-grade(n = 79)(n = 29)(n = 35)(n = 11)Age60.076 ± 10.79363.862 ± 8.0390.08854.514 ± 12.83259.818 ± 9.9180.216Maximum Tumor Diameter3.756 ± 2.1886.928 ± 2.342<0.0013.583 ± 1.4508.182 ± 2.297<0.001Renal sinus involvement0.241 ± 0.4300.759 ± 0.435<0.0010.143 ± 0.3550.818 ± 0.405<0.001Sex0.7880.464Female23 (29.114)7 (24.138)16 (45.714)3 (27.273)Male56 (70.886)22 (75.862)19 (54.286)8 (72.727)Tumor location1.0000.066Left37 (46.835)13 (44.828)16 (45.714)1 (9.091)Right42 (53.165)16 (55.172)19 (54.286)10 (90.909)Lesion margin<0.0010.052Clear59 (74.684)10 (34.483)26 (74.286)4 (36.364)Unclear20 (25.316)19 (65.517)9 (25.714)7 (63.636)Smoking history1.0000.199Absent53 (67.089)20 (68.966)28 (80.000)6 (54.545)Present26 (32.911)9 (31.034)7 (20.000)5 (45.455)History of hypertension1.0001.000Absent38 (48.101)14 (48.276)15 (42.857)5 (45.455)Present41 (51.899)15 (51.724)20 (57.143)6 (54.545)History of diabetes0.6220.762Absent60 (75.949)24 (82.759)29 (82.857)8 (72.727)Present19 (24.051)5 (17.241)6 (17.143)3 (27.273)Hematuria0.5010.427Absent71 (89.873)24 (82.759)31 (88.571)8 (72.727)Present8 (10.127)5 (17.241)4 (11.429)3 (27.273)Pseudocapsule1.0001.000Absent39 (49.367)15 (51.724)17 (48.571)6 (54.545)Present40 (50.633)14 (48.276)18 (51.429)5 (45.455)Intratumoral vessels<0.001<0.001Absent59 (74.684)9 (31.034)31 (88.571)3 (27.273)Present20 (25.316)20 (68.966)4 (11.429)8 (72.727)Renal vein invasion<0.0010.002Absent75 (94.937)20 (68.966)34 (97.143)6 (54.545)Present4 (5.063)9 (31.034)1 (2.857)5 (45.455)Cystic necrosis0.0920.281Absent32 (40.506)6 (20.690)11 (31.429)1 (9.091)Present47 (59.494)23 (79.310)24 (68.571)10 (90.909)Corticomedullary Enhancement Level<0.0010.038Lower than renal parenchyma21 (26.582)20 (68.966)11 (31.429)8 (72.727)Higher than or equal to renal parenchyma58 (73.418)9 (31.034)24 (68.571)3 (27.273)

Comparison of clinical features between the training set and test set.

The original version of this article has been updated.

StatementsPublisher’s note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Keywords

clear cell renal cell carcinoma, habitat, peritumoral, radiomics, WHO/ISUP nuclear grade

Citation

Shi N, Zhang C, Li X, Hao M and Liu C (2026) Correction: MRI-based habitat radiomics for predicting WHO/ISUP nuclear grade in clear cell renal cell carcinoma. Front. Oncol. 16:1802556. doi: 10.3389/fonc.2026.1802556

Received

03 February 2026

Revised

03 February 2026

Accepted

05 May 2026

Published

18 May 2026

Volume

16 - 2026

Edited by

Sharon R. Pine, University of Colorado Anschutz Medical Campus, United States

Reviewed by

Matteo Pacini, University of Pisa, Italy

Updates

Copyright

© 2026 Shi, Zhang, Li, Hao and Liu.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Chong Liu, chongliuabc@163.com

Disclaimer

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.