Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background:

Renal cell carcinoma, especially in small renal masses (≤ 4 cm) (SRM), has increased. Pathological analysis revealed a high proportion of benign masses, highlighting the urgent need for precise SRM differentiation.

Objectives:

This research aimed to independently validate the performance of machine learning-based ultrasound (US) radiomics analysis in differentiating benign from malignant SRM, and to compare its performance with that of radiologists.

Methods:

A total of 499 patients from two hospitals were retrospectively included in this study and divided into two cohorts. US images were used to extract radiomics features. To obtain the most robust features, inter-observer correlation coefficient, Spearman correlation coefficient, and least absolute shrinkage and selection operator methods were applied for feature selection. Three models were developed in the training data using the stochastic gradient boosting algorithm, including a clinical model, a radiomics model, and a combined model that integrated clinical factors and radiomics features. The performance of these models was evaluated in the independent external validation data, including discrimination, calibration, and clinical usefulness, and compared with pooled radiologists' assessments.

Results:

The AUCs of the clinical, radiomics, and combined models were 0.844, 0.942, and 0.954, respectively. The radiomics and combined models significantly outperformed the clinical model (all < 0.05), while no significant difference was observed between them ( = 0.32). The radiomics and combined models showed good discrimination and calibration. Decision curve analysis exhibited that the combined model had clinical usefulness. Compared with the pooled radiologists’ assessment (AUC, 0.799), the combined model showed superior classification results ( < 0.01) and higher specificity ( < 0.01) with similar sensitivity ( = 0.62).

Conclusion:

The combined model incorporating clinical factors and radiomics features accurately distinguished benign from malignant SRM.

© 2024 The Author(s). Published by Bentham Science Publisher.
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/10.2174/0115734056268527231117074443
2023-11-29
2025-01-18

  • From This Site

    /content/journals/cmir/10.2174/0115734056268527231117074443
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/20/1/e15734056268527.html?itemId=/content/journals/cmir/10.2174/0115734056268527231117074443&mimeType=html&fmt=ahah

References

  1. SiegelR.L. MillerK.D. JemalA. Cancer statistics, 2016.CA Cancer J. Clin.201666173010.3322/caac.2133226742998
     [Google Scholar]
  2. NguyenMM GillIS EllisonLM The evolving presentation of renal carcinoma in the United States: Trends from the Surveillance, Epidemiology, and End Results program.J Urol200617623972400
     [Google Scholar]
  3. KimJ.H. LiS. KhandwalaY. ChungK.J. ParkH.K. ChungB.I. Association of prevalence of benign pathologic findings after partial nephrectomy with preoperative imaging patterns in the united states from 2007 to 2014.JAMA Surg.2019154322523110.1001/jamasurg.2018.460230516801
     [Google Scholar]
  4. FrankI. BluteM.L. ChevilleJ.C. LohseC.M. WeaverA.L. ZinckeH. Solid renal tumors: An analysis of pathological features related to tumor size.J. Urol.200317062217222010.1097/01.ju.0000095475.12515.5e14634382
     [Google Scholar]
  5. KutikovA. FossettL.K. RamchandaniP. TomaszewskiJ.E. SiegelmanE.S. BannerM.P. Van ArsdalenK.N. WeinA.J. MalkowiczS.B. Incidence of benign pathologic findings at partial nephrectomy for solitary renal mass presumed to be renal cell carcinoma on preoperative imaging.Urology200668473774010.1016/j.urology.2006.04.01117070344
     [Google Scholar]
  6. FujiiY. KomaiY. SaitoK. IimuraY. YoneseJ. KawakamiS. IshikawaY. KumagaiJ. KiharaK. FukuiI. Incidence of benign pathologic lesions at partial nephrectomy for presumed RCC renal masses: Japanese dual-center experience with 176 consecutive patients.Urology200872359860210.1016/j.urology.2008.04.05418649929
     [Google Scholar]
  7. LjungbergB. BensalahK. CanfieldS. DabestaniS. HofmannF. HoraM. KuczykM.A. LamT. MarconiL. MerseburgerA.S. MuldersP. PowlesT. StaehlerM. VolpeA. BexA. EAU guidelines on renal cell carcinoma: 2014 update.Eur. Urol.201567591392410.1016/j.eururo.2015.01.00525616710
     [Google Scholar]
  8. SasaguriK. TakahashiN. Gomez-CardonaD. LengS. SchmitG.D. CarterR.E. LeibovichB.C. KawashimaA. Small (< 4 cm) renal mass: Differentiation of oncocytoma from renal cell carcinoma on biphasic contrast-enhanced CT.AJR Am. J. Roentgenol.20152055999100710.2214/AJR.14.1396626496547
     [Google Scholar]
  9. KimJ.Y. KimJ.K. KimN. ChoK.S. CT histogram analysis: Differentiation of angiomyolipoma without visible fat from renal cell carcinoma at CT imaging.Radiology2008246247247910.1148/radiol.246206131218094264
     [Google Scholar]
  10. MamoulakisC. TsarouhasK. FragkiadoulakiI. HeretisI. WilksM.F. SpandidosD.A. TsitsimpikouC. TsatsakisA. Contrast-induced nephropathy: Basic concepts, pathophysiological implications and prevention strategies.Pharmacol. Ther.20171809911210.1016/j.pharmthera.2017.06.00928642116
     [Google Scholar]
  11. FerreroA. TakahashiN. VrtiskaT.J. KrambeckA.E. LieskeJ.C. McColloughC.H. Understanding, justifying, and optimizing radiation exposure for CT imaging in nephrourology.Nat. Rev. Urol.201916423124410.1038/s41585‑019‑0148‑830728476
     [Google Scholar]
  12. SilvermanS.G. GanY.U. MorteleK.J. TuncaliK. CibasE.S. Renal masses in the adult patient: The role of percutaneous biopsy.Radiology2006240162210.1148/radiol.240105006116709793
     [Google Scholar]
  13. PierorazioP.M. JohnsonM.H. PatelH.D. Management of Renal Masses and Localized Renal Cancer, Rockville (MD).USAgency for Healthcare Research and Quality2016
     [Google Scholar]
  14. LeveridgeM.J. FinelliA. KachuraJ.R. EvansA. ChungH. ShiffD.A. FernandesK. JewettM.A.S. Outcomes of small renal mass needle core biopsy, nondiagnostic percutaneous biopsy, and the role of repeat biopsy.Eur. Urol.201160357858410.1016/j.eururo.2011.06.02121704449
     [Google Scholar]
  15. Jamis-DowC.A. ChoykeP.L. JenningsS.B. LinehanW.M. ThakoreK.N. WaltherM.M. Small (< or = 3-cm) renal masses: Detection with CT versus US and pathologic correlation.Radiology1996198378578810.1148/radiology.198.3.86288728628872
     [Google Scholar]
  16. XuX. ZhangH.L. LiuQ.P. SunS.W. ZhangJ. ZhuF.P. YangG. YanX. ZhangY.D. LiuX.S. Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma.J. Hepatol.20197061133114410.1016/j.jhep.2019.02.02330876945
     [Google Scholar]
  17. MayerhoeferM.E. MaterkaA. LangsG. HäggströmI. SzczypińskiP. GibbsP. CookG. Introduction to radiomics.J. Nucl. Med.202061448849510.2967/jnumed.118.22289332060219
     [Google Scholar]
  18. XiongL. ChenH. TangX. ChenB. JiangX. LiuL. FengY. LiuL. LiL. Ultrasound-based radiomics analysis for predicting disease-free survival of invasive breast cancer.Front. Oncol.20211162199310.3389/fonc.2021.62199333996546
     [Google Scholar]
  19. ZhangD. WeiQ. WuG.G. ZhangX.Y. LuW.W. LvW.Z. LiaoJ.T. CuiX.W. NiX.J. DietrichC.F. Preoperative prediction of microvascular invasion in patients with hepatocellular carcinoma based on radiomics nomogram using contrast-enhanced ultrasound.Front. Oncol.20211170933910.3389/fonc.2021.70933934557410
     [Google Scholar]
  20. YuJ. DengY. LiuT. ZhouJ. JiaX. XiaoT. ZhouS. LiJ. GuoY. WangY. ZhouJ. ChangC. Lymph node metastasis prediction of papillary thyroid carcinoma based on transfer learning radiomics.Nat. Commun.2020111480710.1038/s41467‑020‑18497‑332968067
     [Google Scholar]
  21. YinR. JiangM. LvW.Z. JiangF. LiJ. HuB. CuiX.W. DietrichC.F. Study processes and applications of ultrasomics in precision medicine.Front. Oncol.202010173610.3389/fonc.2020.0173633014858
     [Google Scholar]
  22. LiC. QiaoG. LiJ. QiL. WeiX. ZhangT. LiX. DengS. WeiX. MaW. An ultrasonic-based radiomics nomogram for distinguishing between benign and malignant solid renal masses.Front. Oncol.20221284780510.3389/fonc.2022.84780535311142
     [Google Scholar]
  23. HabibollahiP. SultanL.R. BialoD. NazifA. FaiziN.A. SehgalC.M. ChauhanA. Hyperechoic renal masses: Differentiation of angiomyolipomas from renal cell carcinomas using tumor size and ultrasound radiomics.Ultrasound Med. Biol.202248588789410.1016/j.ultrasmedbio.2022.01.01135219511
     [Google Scholar]
  24. ZhangL. SunK. ShiL. Ultrasound image-based deep features and radiomics for the discrimination of small fat-poor angiomyolipoma and small renal cell carcinoma.Ultrasound Med Biol202249256056836376157
     [Google Scholar]
  25. DuronL. SavatovskyJ. FournierL. LeclerA. Can we use radiomics in ultrasound imaging? Impact of preprocessing on feature repeatability.Diagn. Interv. Imaging20211021165966710.1016/j.diii.2021.10.00434690106
     [Google Scholar]
  26. NieP. YangG. WangZ. YanL. MiaoW. HaoD. WuJ. ZhaoY. GongA. CuiJ. JiaY. NiuH. A CT-based radiomics nomogram for differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma.Eur. Radiol.20203021274128410.1007/s00330‑019‑06427‑x31506816
     [Google Scholar]
  27. LiX. MaQ. TaoC. LiuJ. NieP. DongC. A CT-based radiomics nomogram for differentiation of small masses (< 4 cm) of renal oncocytoma from clear cell renal cell carcinoma.Abdom. Radiol.202146115240524910.1007/s00261‑021‑03213‑634268628
     [Google Scholar]
  28. TanakaT. HuangY. MarukawaY. TsuboiY. MasaokaY. KojimaK. IguchiT. HirakiT. GobaraH. YanaiH. NasuY. KanazawaS. Differentiation of small (≤ 4 cm) renal masses on multiphase contrast-enhanced CT by deep learning.AJR Am. J. Roentgenol.2020214360561210.2214/AJR.19.2207431913072
     [Google Scholar]
  29. FengZ. RongP. CaoP. ZhouQ. ZhuW. YanZ. LiuQ. WangW. Machine learning-based quantitative texture analysis of CT images of small renal masses: Differentiation of angiomyolipoma without visible fat from renal cell carcinoma.Eur. Radiol.20182841625163310.1007/s00330‑017‑5118‑z29134348
     [Google Scholar]
  30. YangR. WuJ. SunL. LaiS. XuY. LiuX. MaY. ZhenX. Radiomics of small renal masses on multiphasic CT: Accuracy of machine learning–based classification models for the differentiation of renal cell carcinoma and angiomyolipoma without visible fat.Eur. Radiol.20203021254126310.1007/s00330‑019‑06384‑531468159
     [Google Scholar]
  31. McAlpineK. BreauR.H. StaceyD. KneeC. JewettM.A.S. VioletteP.D. RichardP.O. CagiannosI. MorashC. LavalléeL.T. Shared decision-making for the management of small renal masses — development and acceptability testing of a novel patient decision aid.Can. Urol. Assoc. J.2020141238539110.5489/cuaj.657532574143
     [Google Scholar]
  32. GoldbergH. AjajR. CáceresJ.O.H. BerlinA. ChandrasekarT. KlaassenZ. WallisC.J.D. AhmadA.E. LeaoR. PetrellaA.R. KachuraJ.R. FleshnerN. MatthewA. FinelliA. JewettM.A.S. HamiltonR.J. Psychological distress associated with active surveillance in patients younger than 70 with a small renal mass.Urol. Oncol.2020386603.e17603.e2510.1016/j.urolonc.2020.02.01532253117
     [Google Scholar]
  33. LiM.D. ChengM.Q. ChenL.D. HuH.T. ZhangJ.C. RuanS.M. HuangH. KuangM. LuM.D. LiW. WangW. Reproducibility of radiomics features from ultrasound images: Influence of image acquisition and processing.Eur. Radiol.20223295843585110.1007/s00330‑022‑08662‑135314881
     [Google Scholar]
  34. ParkK.J. KimM.H. KimJ.K. ChoK.S. Sonographic features of small (< 4 cm) renal tumors with low signal intensity on T2-weighted MR images: Differentiating minimal-fat angiomyolipoma from renal cell carcinoma.AJR Am. J. Roentgenol.2018211360561310.2214/AJR.17.1890930040467
     [Google Scholar]
  35. CookD.E. KramerH.M. TorresD.E. SeidlM.F. ThommaB.P.H.J. A unique chromatin profile defines adaptive genomic regions in a fungal plant pathogen.eLife20209e6220810.7554/eLife.6220833337321
     [Google Scholar]
  36. WangJ. ZhangJ. GongX. ZhangW. ZhouY. LouM. Prediction of large vessel occlusion for ischaemic stroke by using the machine learning model random forests.Stroke Vasc. Neurol.202272e00109610.1136/svn‑2021‑00109634702747
     [Google Scholar]
  37. PanP. LiY. XiaoY. HanB. SuL. SuM. LiY. ZhangS. JiangD. ChenX. ZhouF. MaL. BaoP. XieL. Prognostic assessment of COVID-19 in the intensive care unit by machine learning methods: Model development and validation.J. Med. Internet Res.20202211e2312810.2196/2312833035175
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056268527231117074443
Loading
External Validation of Ultrasound Radiomics for Small (≤ 4 cm) Renal Mass Differentiation: A Comparison with Radiologists
Curr. Med. Imaging 20, e15734056268527 (2024); https://doi.org/10.2174/0115734056268527231117074443
/content/journals/cmir/10.2174/0115734056268527231117074443
/content/journals/cmir/10.2174/0115734056268527231117074443
Loading

Data & Media loading...

Supplements

Table . Characteristics of patients in the training and independent external validation cohorts. Appedix Radiomics feature classification and derivation. Appedix Hyperparameters of the three optimal models. Table . The Chosen 14 features were selected and coefficients by the Lasso method.

file format download Download

  • Article Type:     Research Article
Keyword(s): Decision curve analysis; Machine learning; Radiomics; Renal cell carcinoma; Small renal masses; Ultrasound

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