Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets

Abstract Background To investigate a non-invasive radiomics-based machine learning algorithm to differentiate upper urinary tract urothelial carcinoma (UTUC) from renal cell carcinoma (RCC) prior to surgical intervention. Methods Preoperative computed tomography venous-phase datasets from patients t...

Full description

Saved in:
Bibliographic Details
Main Authors: Julian Marcon, Philipp Weinhold, Mona Rzany, Matthias P. Fabritius, Michael Winkelmann, Alexander Buchner, Lennert Eismann, Jan-Friedrich Jokisch, Jozefina Casuscelli, Gerald B. Schulz, Thomas Knösel, Michael Ingrisch, Jens Ricke, Christian G. Stief, Severin Rodler, Philipp M. Kazmierczak
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01727-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704739025977344
author Julian Marcon
Philipp Weinhold
Mona Rzany
Matthias P. Fabritius
Michael Winkelmann
Alexander Buchner
Lennert Eismann
Jan-Friedrich Jokisch
Jozefina Casuscelli
Gerald B. Schulz
Thomas Knösel
Michael Ingrisch
Jens Ricke
Christian G. Stief
Severin Rodler
Philipp M. Kazmierczak
author_facet Julian Marcon
Philipp Weinhold
Mona Rzany
Matthias P. Fabritius
Michael Winkelmann
Alexander Buchner
Lennert Eismann
Jan-Friedrich Jokisch
Jozefina Casuscelli
Gerald B. Schulz
Thomas Knösel
Michael Ingrisch
Jens Ricke
Christian G. Stief
Severin Rodler
Philipp M. Kazmierczak
author_sort Julian Marcon
collection DOAJ
description Abstract Background To investigate a non-invasive radiomics-based machine learning algorithm to differentiate upper urinary tract urothelial carcinoma (UTUC) from renal cell carcinoma (RCC) prior to surgical intervention. Methods Preoperative computed tomography venous-phase datasets from patients that underwent procedures for histopathologically confirmed UTUC or RCC were retrospectively analyzed. Tumor segmentation was performed manually, and radiomic features were extracted according to the International Image Biomarker Standardization Initiative. Features were normalized using z-scores, and a predictive model was developed using the least absolute shrinkage and selection operator (LASSO). The dataset was split into a training cohort (70%) and a test cohort (30%). Results A total of 236 patients [30.5% female, median age 70.5 years (IQR: 59.5–77), median tumor size 5.8 cm (range: 4.1–8.2 cm)] were included. For differentiating UTUC from RCC, the model achieved a sensitivity of 88.4% and specificity of 81% (AUC: 0.93, radiomics score cutoff: 0.467) in the training cohort. In the validation cohort, the sensitivity was 80.6% and specificity 80% (AUC: 0.87, radiomics score cutoff: 0.601). Subgroup analysis of the validation cohort demonstrated robust performance, particularly in distinguishing clear cell RCC from high-grade UTUC (sensitivity: 84%, specificity: 73.1%, AUC: 0.84) and high-grade from low-grade UTUC (sensitivity: 57.7%, specificity: 88.9%, AUC: 0.68). Limitations include the need for independent validation in future randomized controlled trials (RCTs). Conclusions Machine learning-based radiomics models can reliably differentiate between RCC and UTUC in preoperative CT imaging. With a suggested performance benefit compared to conventional imaging, this technology might be added to the current preoperative diagnostic workflow. Clinical trial number Local ethics committee no. 20–179
format Article
id doaj-art-648febe9faab46fe8d13d18481b0e792
institution DOAJ
issn 1471-2342
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-648febe9faab46fe8d13d18481b0e7922025-08-20T03:16:39ZengBMCBMC Medical Imaging1471-23422025-05-0125111010.1186/s12880-025-01727-9Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasetsJulian Marcon0Philipp Weinhold1Mona Rzany2Matthias P. Fabritius3Michael Winkelmann4Alexander Buchner5Lennert Eismann6Jan-Friedrich Jokisch7Jozefina Casuscelli8Gerald B. Schulz9Thomas Knösel10Michael Ingrisch11Jens Ricke12Christian G. Stief13Severin Rodler14Philipp M. Kazmierczak15Department of Urology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Radiology, University Hospital, LMU MunichDepartment of Radiology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Pathology, University Hospital, LMU MunichDepartment of Radiology, University Hospital, LMU MunichDepartment of Radiology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Urology, University Hospital, LMU MunichDepartment of Radiology, University Hospital, LMU MunichAbstract Background To investigate a non-invasive radiomics-based machine learning algorithm to differentiate upper urinary tract urothelial carcinoma (UTUC) from renal cell carcinoma (RCC) prior to surgical intervention. Methods Preoperative computed tomography venous-phase datasets from patients that underwent procedures for histopathologically confirmed UTUC or RCC were retrospectively analyzed. Tumor segmentation was performed manually, and radiomic features were extracted according to the International Image Biomarker Standardization Initiative. Features were normalized using z-scores, and a predictive model was developed using the least absolute shrinkage and selection operator (LASSO). The dataset was split into a training cohort (70%) and a test cohort (30%). Results A total of 236 patients [30.5% female, median age 70.5 years (IQR: 59.5–77), median tumor size 5.8 cm (range: 4.1–8.2 cm)] were included. For differentiating UTUC from RCC, the model achieved a sensitivity of 88.4% and specificity of 81% (AUC: 0.93, radiomics score cutoff: 0.467) in the training cohort. In the validation cohort, the sensitivity was 80.6% and specificity 80% (AUC: 0.87, radiomics score cutoff: 0.601). Subgroup analysis of the validation cohort demonstrated robust performance, particularly in distinguishing clear cell RCC from high-grade UTUC (sensitivity: 84%, specificity: 73.1%, AUC: 0.84) and high-grade from low-grade UTUC (sensitivity: 57.7%, specificity: 88.9%, AUC: 0.68). Limitations include the need for independent validation in future randomized controlled trials (RCTs). Conclusions Machine learning-based radiomics models can reliably differentiate between RCC and UTUC in preoperative CT imaging. With a suggested performance benefit compared to conventional imaging, this technology might be added to the current preoperative diagnostic workflow. Clinical trial number Local ethics committee no. 20–179https://doi.org/10.1186/s12880-025-01727-9Machine learningRadiomicsRenal cell carcinomaUpper tract urothelial carcinoma
spellingShingle Julian Marcon
Philipp Weinhold
Mona Rzany
Matthias P. Fabritius
Michael Winkelmann
Alexander Buchner
Lennert Eismann
Jan-Friedrich Jokisch
Jozefina Casuscelli
Gerald B. Schulz
Thomas Knösel
Michael Ingrisch
Jens Ricke
Christian G. Stief
Severin Rodler
Philipp M. Kazmierczak
Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets
BMC Medical Imaging
Machine learning
Radiomics
Renal cell carcinoma
Upper tract urothelial carcinoma
title Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets
title_full Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets
title_fullStr Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets
title_full_unstemmed Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets
title_short Radiomics-based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets
title_sort radiomics based differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets
topic Machine learning
Radiomics
Renal cell carcinoma
Upper tract urothelial carcinoma
url https://doi.org/10.1186/s12880-025-01727-9
work_keys_str_mv AT julianmarcon radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT philippweinhold radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT monarzany radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT matthiaspfabritius radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT michaelwinkelmann radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT alexanderbuchner radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT lennerteismann radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT janfriedrichjokisch radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT jozefinacasuscelli radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT geraldbschulz radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT thomasknosel radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT michaelingrisch radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT jensricke radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT christiangstief radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT severinrodler radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets
AT philippmkazmierczak radiomicsbaseddifferentiationofupperurinarytracturothelialandrenalcellcarcinomainpreoperativecomputedtomographydatasets