Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 21, Issue 1
  5. Article
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Muscle infiltration of bladder cancer has become the most important index to evaluate its prognosis. Machine learning is expected to accurately identify its muscle infiltration status on images.

Objective

This study aimed to establish and validate a machine learning prediction model based on multi-phase contrast-enhanced CT (MCECT) for preoperatively evaluating the muscle-invasive status of bladder cancer.

Methods

A retrospective study was conducted on bladder cancer patients who underwent surgical resection and pathological confirmation by MCECT scans. They were randomly divided into training and testing groups at a ratio of 8:2; we used an independent external testing set for verification. The radiomics features of lesions were extracted from MCECT images and radiomics signatures were established by dual sample T-test and least absolute shrinkage selection operator (LASSO) regression. Afterward, four machine learning classifier models were established. The receiver operating characteristic (ROC) curve, calibration, and decision curve analysis were employed to evaluate the efficiency of the model and analyze diagnostic performance using accuracy, precision, sensitivity, specificity, and F1-score.

Results

The best predictive model was found to have logic regression as the classifier. The AUC value was 0.89 (5-fold cross-validation range 0.83-0.96) in the training group, 0.80 in the test group, and 0.87 in the external testing group. In the testing and external testing group, the diagnostic accuracy, precision, sensitivity, specificity, and F1-score were 0.759, 0.826, 0.863, 0.729, 0.785, and 0.794, 0.755, 0.953, 0.720, and 0.809, respectively.

Conclusion

The machine learning model showed good accuracy in predicting the muscle infiltration status of bladder cancer before surgery.

© 2025 The Author(s). Published by Bentham Science Publishers.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056377754250304040058
2025-03-17
2025-07-03

  • From This Site

    /content/journals/cmir/10.2174/0115734056377754250304040058
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. AntoniS. FerlayJ. SoerjomataramI. ZnaorA. JemalA. BrayF. Bladder cancer incidence and mortality: A global overview and recent trends.Eur. Urol.20177119610810.1016/j.eururo.2016.06.01027370177
     [Google Scholar]
  2. WangH. XuX. ZhangX. LiuY. OuyangL. DuP. LiS. TianQ. LingJ. GuoY. LuH. Elaboration of a multisequence MRI-based radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer: A double-center study.Eur. Radiol.20203094816482710.1007/s00330‑020‑06796‑832318846
     [Google Scholar]
  3. DobruchJ. OszczudłowskiM. Bladder cancer: Current challenges and future directions.Medicina (Kaunas)202157874910.3390/medicina5708074934440955
     [Google Scholar]
  4. BabjukM. BurgerM. CapounO. CohenD. CompératE.M. Dominguez EscrigJ.L. GonteroP. LiedbergF. Masson-LecomteA. MostafidA.H. PalouJ. van RhijnB.W.G. RouprêtM. ShariatS.F. SeisenT. SoukupV. SylvesterR.J. European association of urology guidelines on non–muscle-invasive bladder cancer (TA, T1, and carcinoma in situ).Eur. Urol.2022811759410.1016/j.eururo.2021.08.01034511303
     [Google Scholar]
  5. BrocklehurstA. VarugheseM. BirtleA. Bladder preservation for muscle-invasive bladder cancer with variant histology.Semin. Radiat. Oncol.2023331626910.1016/j.semradonc.2022.10.00836517195
     [Google Scholar]
  6. UcpinarB. ErbinA. AyranciA. CaglarU. AlisD. BasalS. SarilarO. AkbulutM.F. Prediction of recurrence in non-muscle invasive bladder cancer patients. Do patient characteristics matter?J. Buon.20192441659166531646822
     [Google Scholar]
  7. WongV.K. GaneshanD. JensenC.T. DevineC.E. Imaging and management of bladder cancer.Cancers (Basel)2021136139610.3390/cancers1306139633808614
     [Google Scholar]
  8. Alfred WitjesJ. Max BruinsH. CarriónA. CathomasR. CompératE. EfstathiouJ.A. FietkauR. GakisG. LorchA. MartiniA. MertensL.S. MeijerR.P. MilowskyM.I. NeuzilletY. PanebiancoV. RedlefJ. RinkM. RouanneM. ThalmannG.N. SæbjørnsenS. VeskimäeE. van der HeijdenA.G. European association of urology guidelines on muscle-invasive and metastatic bladder cancer: Summary of the 2023 guidelines.Eur. Urol.2024851173110.1016/j.eururo.2023.08.01637858453
     [Google Scholar]
  9. LiJ. MaS. WuD. ZhangZ. ChenY. LiuB. LiC. JiaH. CT-based radiomics and cluster analysis for the prediction of local progression in stage I NSCLC patients treated with microwave ablation.iScience202528111155210.1016/j.isci.2024.11155239807170
     [Google Scholar]
  10. AkcayA. YagciA.B. CelenS. OzlulerdenY. TurkN.S. UfukF. VI-RADS score and tumor contact length in MRI: A potential method for the detection of muscle invasion in bladder cancer.Clin. Imaging202177253610.1016/j.clinimag.2021.02.02633639497
     [Google Scholar]
  11. ZhangG. XuL. ZhaoL. MaoL. LiX. JinZ. SunH. CT-based radiomics to predict the pathological grade of bladder cancer.Eur. Radiol.202030126749675610.1007/s00330‑020‑06893‑832601949
     [Google Scholar]
  12. WangH. HuD. YaoH. ChenM. LiS. ChenH. LuoJ. FengY. GuoY. Radiomics analysis of multiparametric MRI for the preoperative evaluation of pathological grade in bladder cancer tumors.Eur. Radiol.201929116182619010.1007/s00330‑019‑06222‑831016445
     [Google Scholar]
  13. CuiY. SunZ. LiuX. ZhangX. WangX. CT-based radiomics for the preoperative prediction of the muscle-invasive status of bladder cancer and comparison to radiologists’ assessment.Clin. Radiol.2022776e473e48210.1016/j.crad.2022.02.01935367051
     [Google Scholar]
  14. ZhengZ. XuF. GuZ. YanY. XuT. LiuS. YaoX. Combining multiparametric MRI radiomics signature with the vesical imaging-reporting and data system (VI-RADS) score to preoperatively differentiate muscle invasion of bladder cancer.Front. Oncol.20211161989310.3389/fonc.2021.61989334055600
     [Google Scholar]
  15. ChenG. FanX. WangT. ZhangE. ShaoJ. ChenS. ZhangD. ZhangJ. GuoT. YuanZ. TangH. YuY. ChenJ. WangX. A machine learning model based on MRI for the preoperative prediction of bladder cancer invasion depth.Eur. Radiol.202333128821883210.1007/s00330‑023‑09960‑y37470826
     [Google Scholar]
  16. SylvesterR.J. van der MeijdenA.P.M. OosterlinckW. WitjesJ.A. BouffiouxC. DenisL. NewlingD.W.W. KurthK. Predicting recurrence and progression in individual patients with stage Ta T1 bladder cancer using EORTC risk tables: A combined analysis of 2596 patients from seven EORTC trials.Eur. Urol.200649346647710.1016/j.eururo.2005.12.03116442208
     [Google Scholar]
  17. SherifA. JonssonM.N. WiklundN.P. Treatment of muscle-invasive bladder cancer.Expert Rev. Anticancer Ther.2007791279128310.1586/14737140.7.9.127917892428
     [Google Scholar]
  18. HuangX. WangX. LanX. DengJ. LeiY. LinF. The role of radiomics with machine learning in the prediction of muscle-invasive bladder cancer: A mini review.Front. Oncol.20221299017610.3389/fonc.2022.99017636059618
     [Google Scholar]
  19. HensleyP.J. PanebiancoV. PietzakE. KutikovA. VikramR. GalskyM.D. ShariatS.F. RoupretM. KamatA.M. Contemporary staging for muscle-invasive bladder cancer: Accuracy and limitations.Eur. Urol. Oncol.20225440341110.1016/j.euo.2022.04.00835581143
     [Google Scholar]
  20. MariappanP. ZachouA. GrigorK.M. Detrusor muscle in the first, apparently complete transurethral resection of bladder tumour specimen is a surrogate marker of resection quality, predicts risk of early recurrence, and is dependent on operator experience.Eur. Urol.201057584384910.1016/j.eururo.2009.05.04719524354
     [Google Scholar]
  21. SvatekR.S. ShariatS.F. NovaraG. SkinnerE.C. FradetY. BastianP.J. KamatA.M. KassoufW. KarakiewiczP.I. FritscheH.M. IzawaJ.I. TilkiD. FicarraV. VolkmerB.G. IsbarnH. DinneyC.P. Discrepancy between clinical and pathological stage: External validation of the impact on prognosis in an international radical cystectomy cohort.BJU Int.2011107689890410.1111/j.1464‑410X.2010.09628.x21244604
     [Google Scholar]
  22. TurkerP. BostromP.J. WroclawskiM.L. van RhijnB. KortekangasH. KukC. MirttiT. FleshnerN.E. JewettM.A. FinelliA. KwastT.V. EvansA. SweetJ. LaatoM. ZlottaA.R. Upstaging of urothelial cancer at the time of radical cystectomy: Factors associated with upstaging and its effect on outcome.BJU Int.2012110680481110.1111/j.1464‑410X.2012.10939.x22321341
     [Google Scholar]
  23. YanagisawaT. KawadaT. von DeimlingM. BekkuK. LaukhtinaE. RajwaP. ChlostaM. PradereB. D’AndreaD. MoschiniM. KarakiewiczP.I. TeohJ.Y.C. MikiJ. KimuraT. ShariatS.F. Repeat transurethral resection for non–muscle-invasive bladder cancer: An updated systematic review and meta-analysis in the contemporary era.Eur. Urol. Focus2024101415610.1016/j.euf.2023.07.00237495458
     [Google Scholar]
  24. DobruchJ. DaneshmandS. FischM. LotanY. NoonA.P. ResnickM.J. ShariatS.F. ZlottaA.R. BoorjianS.A. Gender and bladder cancer: A collaborative review of etiology, biology, and outcomes.Eur. Urol.201669230031010.1016/j.eururo.2015.08.03726346676
     [Google Scholar]
  25. BarchettiG. SimoneG. CeravoloI. SalvoV. CampaR. Del GiudiceF. De BerardinisE. BuccilliD. CatalanoC. GallucciM. CattoJ.W.F. PanebiancoV. Multiparametric MRI of the bladder: Inter-observer agreement and accuracy with the Vesical Imaging-Reporting and Data System (VI-RADS) at a single reference center.Eur. Radiol.201929105498550610.1007/s00330‑019‑06117‑830887202
     [Google Scholar]
  26. WangH. LuoC. ZhangF. GuanJ. LiS. YaoH. ChenJ. LuoJ. ChenL. GuoY. Multiparametric MRI for bladder cancer: Validation of VI-RADS for the detection of detrusor muscle invasion.Radiology2019291366867410.1148/radiol.201918250631012814
     [Google Scholar]
  27. MetwallyM.I. ZeedN.A. HamedE.M. ElshetryA.S.F. ElfwakhryR.M. Alaa EldinA.M. SakrA. AlyS.A. MosallamW. ZiadaY.M.A. BalataR. HarbO.A. BashaM.A.A. The validity, reliability, and reviewer acceptance of VI-RADS in assessing muscle invasion by bladder cancer: A multicenter prospective study.Eur. Radiol.20213196949696110.1007/s00330‑021‑07765‑533606105
     [Google Scholar]
  28. UenoY. TamadaT. TakeuchiM. SofueK. TakahashiS. KamishimaY. UraseY. KidoA. HinataN. HaradaK. FujisawaM. MiyajiY. MurakamiT. VI-RADS: Multiinstitutional multireader diagnostic accuracy and interobserver agreement study.AJR Am. J. Roentgenol.202121651257126610.2214/AJR.20.2360432755215
     [Google Scholar]
  29. XuX. LiuY. ZhangX. TianQ. WuY. ZhangG. MengJ. YangZ. LuH. Preoperative prediction of muscular invasiveness of bladder cancer with radiomic features on conventional MRI and its high-order derivative maps.Abdom. Radiol. (N.Y.)20174271896190510.1007/s00261‑017‑1079‑628217825
     [Google Scholar]
  30. XuX. ZhangX. TianQ. WangH. CuiL.B. LiS. TangX. LiB. DolzJ. AyedI. LiangZ. YuanJ. DuP. LuH. LiuY. Quantitative identification of nonmuscle-invasive and muscle-invasive bladder carcinomas: A multiparametric MRI radiomics analysis.J. Magn. Reson. Imaging20194951489149810.1002/jmri.2632730252978
     [Google Scholar]
  31. LinP. WenD. ChenL. LiX. LiS. YanH. HeR. ChenG. HeY. YangH. A radiogenomics signature for predicting the clinical outcome of bladder urothelial carcinoma.Eur. Radiol.202030154755710.1007/s00330‑019‑06371‑w31396730
     [Google Scholar]
  32. ChaK.H. HadjiiskiL.M. CohanR.H. ChanH.P. CaoiliE.M. DavenportM.S. SamalaR.K. WeizerA.Z. AlvaA. Kirova-NedyalkovaG. ShampainK. MeyerN. BarkmeierD. WoolenS. ShankarP.R. FrancisI.R. PalmbosP. Diagnostic accuracy of CT for prediction of bladder cancer treatment response with and without computerized decision support.Acad. Radiol.20192691137114510.1016/j.acra.2018.10.01030424999
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056377754250304040058
Loading
A Machine Learning Model Based on Multi-Phase Contrast-enhanced CT for the Preoperative Prediction of the Muscle-Invasive Status of Bladder Cancer
Curr. Med. Imaging 21, E15734056377754 (2025); https://doi.org/10.2174/0115734056377754250304040058
/content/journals/cmir/10.2174/0115734056377754250304040058
/content/journals/cmir/10.2174/0115734056377754250304040058
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Bladder cancer; Contrast-enhanced computer tomography (CECT); Least absolute shrinkage selection operator (LASSO); Machine learning (ML); Muscle-invasive; Receiver operating characteristic (ROC); Uroepithelial carcinoma

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test