Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective study

Abstract MRI has relatively low sensitivity and specificity in detecting lymph node metastases. This study aimed to develop and validate an MRI radiomics-based model for predicting lateral pelvic lymph node (LPLN) metastasis in rectal cancer patients who underwent LPLN dissection, and to compare its...

Full description

Saved in:
Bibliographic Details
Main Authors: Jeongin Yoo, Jun Young Han, Won Chang, Bo Yun Hur, Jae Hyun Kim, Yunhee Choi, Soo Jin Kim, Se Hyung Kim
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-99029-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850042069169471488
author Jeongin Yoo
Jun Young Han
Won Chang
Bo Yun Hur
Jae Hyun Kim
Yunhee Choi
Soo Jin Kim
Se Hyung Kim
author_facet Jeongin Yoo
Jun Young Han
Won Chang
Bo Yun Hur
Jae Hyun Kim
Yunhee Choi
Soo Jin Kim
Se Hyung Kim
author_sort Jeongin Yoo
collection DOAJ
description Abstract MRI has relatively low sensitivity and specificity in detecting lymph node metastases. This study aimed to develop and validate an MRI radiomics-based model for predicting lateral pelvic lymph node (LPLN) metastasis in rectal cancer patients who underwent LPLN dissection, and to compare its performance with that of radiologists. This multicenter retrospective study included 336 rectal cancer patients (199 men; mean age, 58.9 years ± 11.1 [standard deviation]) who underwent LPLN dissection. Patients were divided into development (n = 190) and validation (n = 146) cohorts. Radiomics features were extracted from MR images, and the Least Absolute Shrinkage and Selection Operator regression was used to construct radiomics and clinical-radiomics models. Model performance was compared with radiologists using receiver operating characteristic (ROC) analysis. Malignant LPLN was diagnosed in 32.4% of the development cohort (65/190) and 32.9% of the validation cohort (48/146) (P = 0.798). Seven radiomics features and two clinical features were selected. The radiomics and clinical-radiomics models demonstrated area under the curves (AUCs) of 0.819 and 0.830 in the development cohort and 0.821 and 0.829 in the validation cohort, respectively. The optimal cut-off (− 0.47) yielded sensitivities of 72.3% and 45.8% and specificities of 82.4% and 87.8% in the development and validation cohorts, respectively. Decision curve analysis indicated no additional net benefit from the clinical-radiomics model compared to the radiomics-only model. Radiologists’ AUCs were significantly lower than that of the radiomics model (0.842) and improved with radiomics probability scores (0.734 vs. 0.801; 0.668 vs. 0.791). The MRI-based radiomics model significantly improves the prediction of LPLN metastasis in rectal cancer, outperforming conventional criteria used by radiologists. Trial registration: Retrospectively registered.
format Article
id doaj-art-c9c216a32b024cf2954e3d45c0d10170
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c9c216a32b024cf2954e3d45c0d101702025-08-20T02:55:38ZengNature PortfolioScientific Reports2045-23222025-04-0115111310.1038/s41598-025-99029-1Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective studyJeongin Yoo0Jun Young Han1Won Chang2Bo Yun Hur3Jae Hyun Kim4Yunhee Choi5Soo Jin Kim6Se Hyung Kim7Department of Radiology, Seoul National University HospitalCollege of Medicine, Seoul National UniversityDepartment of Radiology, Seoul National University Bundang HospitalDepartment of Radiology, Healthcare System Gangnam Center, Seoul National University HospitalDepartment of Radiology, Seoul National University HospitalMedical Research Collaborating Center, Seoul National University HospitalDepartment of Radiology, National Cancer CenterDepartment of Radiology, Seoul National University HospitalAbstract MRI has relatively low sensitivity and specificity in detecting lymph node metastases. This study aimed to develop and validate an MRI radiomics-based model for predicting lateral pelvic lymph node (LPLN) metastasis in rectal cancer patients who underwent LPLN dissection, and to compare its performance with that of radiologists. This multicenter retrospective study included 336 rectal cancer patients (199 men; mean age, 58.9 years ± 11.1 [standard deviation]) who underwent LPLN dissection. Patients were divided into development (n = 190) and validation (n = 146) cohorts. Radiomics features were extracted from MR images, and the Least Absolute Shrinkage and Selection Operator regression was used to construct radiomics and clinical-radiomics models. Model performance was compared with radiologists using receiver operating characteristic (ROC) analysis. Malignant LPLN was diagnosed in 32.4% of the development cohort (65/190) and 32.9% of the validation cohort (48/146) (P = 0.798). Seven radiomics features and two clinical features were selected. The radiomics and clinical-radiomics models demonstrated area under the curves (AUCs) of 0.819 and 0.830 in the development cohort and 0.821 and 0.829 in the validation cohort, respectively. The optimal cut-off (− 0.47) yielded sensitivities of 72.3% and 45.8% and specificities of 82.4% and 87.8% in the development and validation cohorts, respectively. Decision curve analysis indicated no additional net benefit from the clinical-radiomics model compared to the radiomics-only model. Radiologists’ AUCs were significantly lower than that of the radiomics model (0.842) and improved with radiomics probability scores (0.734 vs. 0.801; 0.668 vs. 0.791). The MRI-based radiomics model significantly improves the prediction of LPLN metastasis in rectal cancer, outperforming conventional criteria used by radiologists. Trial registration: Retrospectively registered.https://doi.org/10.1038/s41598-025-99029-1Rectal neoplasmsMagnetic resonance imagingRadiomicsLymphatic metastasisLymph node excision
spellingShingle Jeongin Yoo
Jun Young Han
Won Chang
Bo Yun Hur
Jae Hyun Kim
Yunhee Choi
Soo Jin Kim
Se Hyung Kim
Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective study
Scientific Reports
Rectal neoplasms
Magnetic resonance imaging
Radiomics
Lymphatic metastasis
Lymph node excision
title Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective study
title_full Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective study
title_fullStr Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective study
title_full_unstemmed Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective study
title_short Predicting lateral pelvic lymph node metastasis in rectal cancer patients using MRI radiomics: a multicenter retrospective study
title_sort predicting lateral pelvic lymph node metastasis in rectal cancer patients using mri radiomics a multicenter retrospective study
topic Rectal neoplasms
Magnetic resonance imaging
Radiomics
Lymphatic metastasis
Lymph node excision
url https://doi.org/10.1038/s41598-025-99029-1
work_keys_str_mv AT jeonginyoo predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy
AT junyounghan predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy
AT wonchang predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy
AT boyunhur predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy
AT jaehyunkim predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy
AT yunheechoi predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy
AT soojinkim predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy
AT sehyungkim predictinglateralpelviclymphnodemetastasisinrectalcancerpatientsusingmriradiomicsamulticenterretrospectivestudy